Existing Chinese named entity recognition algorithms inadequately consider the data features of entity recognition tasks, leading to imbalance in the categories of Chinese sample data, excessive noise in the training data, and significant differences in the distribution of generated data. An improved Chinese named entity recognition model based on BERT-BiLSTM-CRF ( Bidirectional Encoder Representations from Transformers-Bidirectional Long Short-Term Memory-Conditional Random Field) is proposed. The first improvement involves combining the P-Tuning v2 technology with BERT-BiLSTM-CRF to accurately extract data features. And three
loss functions, including Focal Loss, Label Smoothing, and KL Loss(Kullback-Leibler divergence loss), are utilized as regularization terms in the loss calculation to address the problems. The improved model achieves F1 scores of 71. 13% ,96. 31% , and 95. 90% on the Weibo, Resume, and MSRA( Microsoft Research Asia)datasets, respectively. The results validate that the proposed algorithm outperforms previous research achievements in terms of performance and is easy to combine and extend with other neural networks for various downstream tasks.

Weil pairing and Tate pairing are widely used in encryption, signature, password exchange and cryptosystem security analysis. It has been suggested that the computational efficiency of Tate pairing is better than that of Weil pairing, but this problem is still doubtful and needs to be further verified. The parameter selection algorithm of binary group structure proposed by Miller belongs to probabilistic algorithm, and the algorithm efficiency is not high. To solve the above problems, the analysis models of Tate pairing and Weil pairing on execution efficiency are established, and a new method is proposed to find the parameters of the distortion value by using the quadratic relation of the order of the elliptic curve. The research shows that when the distortion value is small, the computational efficiency of Tate pairing is better than that of Weil pairing, which is consistent with previous studies. However, when the distortion value is large, the computational efficiency of Weil pairing is better than that of Tate pairing, and the time complexity of the new method to find the distortion value parameter is less than that of Miller method O(M). Compared with Miller’s probabilistic

method, the new method is deterministic. The correctness of the analysis model is verified by analysis and example, and the new method greatly improves the efficiency and accuracy of parameter selection.

The current intelligent prediction methods for traffic flow have not analyzed and considered the spatiotemporal correlation of the road network. We conduct research and improvement to address this issue by adding spatiotemporal correlation information to the intelligent prediction methods to solve the problem of reduced prediction accuracy caused by the lack of spatiotemporal information. The spatiotemporal correlation of the urban road network is analyzed by combining the map connection of the traffic network and the vehicle traffic delay. Considering the spatiotemporal correlation of urban traffic, based on the GCN( Graph Convolutional Neural)

network and LSTM ( Long Short-Term Memory) network methods, the urban traffic flow prediction method considering spatiotemporal information based on GCN and LSTM is studied. Urban traffic flow prediction network is optimized and trained by using the open source urban traffic flow dataset. The performance of LSTM, BiLSTM (Bidirectional Long Short-Term Memory) network and different number of nodes in solving the traffic flow prediction problem is compared. The results of this research show that the proposed method can effectively predict urban traffic flow, and the accuracy of the proposed method is improved compared with the prediction method without considering spatiotemporal information. This research can provide a theoretical reference for traffic prediction in intelligent transportation systems.

At the traditional image processing algorithms for the detection of steel surface defects, there are problems such as low recognition efficiency and a high false detection rate of leakage. The YOLOv8-DSG (Deformable Convolution Network Squeeze and Excitation Network Generalized Intersection over Union) steel surface defect detection algorithm is proposed. Based on the traditional YOLOv8 algorithm, several improvements are made. Firstly, the DCN ( Deformable Convolutional Network) is embedded in the C2f ( Convolution to Feature) module of the Backbone network, which enhances the feature extraction ability of the model under

complex background conditions. Secondly, the SE ( Squeeze and Excitation network ) attention module is introduced into the Neck network, which highlights the important feature information of the steel surface and enhances the richness of the feature fusion. Lastly, the GIOU ( Generalized Intersection Over Union) loss function is used instead of the original CIOU(Complete Intersection Over Union). Compared with CIOU, GIOU introduces the minimum enclosing frame area ratio, which can more accurately measure the overlapping area of the frames. The experimental results show that the YOLOv8-DSG algorithm achieves an average accuracy mAP of

80% on the NEU-DET dataset, which is 3. 3% higher compared to the original YOLOv8 algorithm. And it has a low rate of misdetection and omission, demonstrating higher detection accuracy and arithmetic efficiency. This algorithm can play an important role in quality inspection.

A single embedded processor is difficult to efficiently complete the massive computing tasks such as image processing. Therefore, a set of SoC(System on Chip) with image processing function is designed based on FPGA(Field-Programmable Gate Array) and Coretx-M3 processor kernel. Based on Xilinx’s Kintex-7 FPGA and Arm’s Cortex-M3 kernel, the processor architecture is implemented on FPGA. The memory, bus system and basic peripherals are designed using IP(Internet Protocol) core and Verilog, and are connected to the processor through the bus. The image processing unit is designed, and the commonly used digital image processing

algorithm is mapped to the hardware description language. And the bus interface is designed to connect to the processor, providing the image processing capability for SoC. Based on Keil MDK tool and C language, the drivers for the peripheral and image processing unit of SoC are written, and the system function is simulated. And the digital image processing based on Matlab and the image processing unit in SoC are fully compared and tested by taking the binarization algorithm as an example. This image processing SoC has excellent performance and all the advantages of FPGA and SoC. The author has successfully developed a SoC with image processing function based on FPGA platform. The system is board-validated on Xilinx’s Kintex-7 family, model XC7K325TFFG676-2 FPGAs. This design reflects the high flexibility and efficiency of the system designed on FPGA platform, and provides a solution to solve the disadvantages of a single embedded processor that is difficult to efficiently complete the massive computing tasks such as image processing. The system is designed based on a reconfigurable platform, which can realize the customization of peripheral functions according to requirements, and has the advantage of higher flexibility.

Traditional methods for identifying table structures are difficult to fully learn complex table structures such as merge cells with multiple rows and columns, blank cells, nested cells, and are lack of information in the process of extracting features. An OCR(Optical Character Recognition) table structure identification method based on improved SLANet (Structure Location Alignment Network) is proposed. Firstly, the lightweight CPU (Central Processing Unit) convolutional neural network is used and attention mechanism is introduced to enhance the generalization ability and explanation ability of the network. The information vector obtained by training is

inputed into the lightweight high-low level feature fusion module to extract features, and then the outputted features are aligned with the structure and position information through the feature decoded module to obtain the prediction label. Experiments show that compared to EDD ( Encoder-Dual-Decoder), TableMaster and other models, the accuracy of the proposed method has been significantly improved, reaching 76. 95% , and the TEDS (Tree-Edit-Distance-based Similarity) has reached 95. 57% , which significantly enhances the model’s ability to identify complex table structures and provides an optimization strategy for identifying table structures.

In traditional mobile edge computing systems, users face issues such as communication channel interruptions caused by dense obstacles and terrain structures, and under-utilization of idle system resources.These issues make it challenging to complete intensive computing tasks with low delay and power consumption.To address this, a UAV(Unmanned Aerial Vehicle)-assisted terminal pass-through collaborative mobile edge computing system is established. In this system, the computing user offloads part of the task to the idle user by establishing a direct connection link on the ground. The idle user uses their computing resources to assist with the calculation while offloading the remaining tasks to the UAV configured with a mobile edge computing server.A mathematical model of this new system is established, and a computational offloading strategy based on the deep deterministic policy gradient algorithm is proposed. This strategy optimizes the dual offloading rate and the maneuverability of the UAV to minimize the processing delay of computing tasks, under the constraints of UAV power and user movement range. Simulation tests in a simulated continuous state space environment show that the proposed offloading computing strategy optimization scheme can efficiently use resources in the collaborative network and effectively reduce task processing delay compared to other baseline algorithms.

AI(Artificial Intelligence) plays an important role in medical imaging education, driving innovation in teaching methods and medical education. With the continuous development of AI technology, especially breakthroughs in deep learning, image recognition, and natural language processing, AI is gradually demonstrating its unique advantages in the field of medical imaging education. AI helps students and healthcare professionals quickly identify disease features, and provides automated image analysis results, allowing learners to intuitively understand the imaging manifestations of different diseases. It enhances the interactivity and practicality of learning. AI can offer personalized learning paths recommending relevant educational content or exercises based on the student’s progress and understanding, ensuring that learners receive tailored educational services. The efficiency and accuracy of AI assist students in better comprehending complex medical imaging content improving learning outcomes. However, AI in medical imaging education also faces certain challenges.As technology continues to advance, AI will play a more significant role in medical imaging education. Future educational systems are likely to become more intelligent, integrating technologies such as virtual reality and augmented reality to provide students with a more immersive learning experience.

In order to reduce the total overhead of the MEC (Mobile Edge Computing) system, the weighted sum of latency and energy consumption of all devices are considered as the optimization objective, and the problem of task offloading is solved in a multi-user multi-channel mobile edge computing system. Specifically, multiple user devices are able to offload computationally-heavy tasks to the MEC server over a wireless channel. Considering the difference in residual energy among multiple smart devices, an energy factor is introduced to measure the bias of smart devices between energy consumption and latency. A reinforcement learning scheme based on the Q-learning algorithm is applied to co-optimize the offloading decision, the allocation of computational resources, and the selection of wireless channels. Simulation results show that the algorithm can effectively reduce the delay and energy consumption of task processing and accommodate more users.

As the most widely adopted backbone network in classification, object detection and instance segmentation tasks, the representation capability of ResNet ( Residual Neural Network) has gained extensive recognition. However, there are still certain limitations that hinder the representation ability of ResNet, including feature redundancy and inadequate effective receptive field. To address these problems, a feature fusion block is proposed, which can fuse features of different scales to construct multi-scale features with richer information and improve channel utilization, when the model channel is increased. The block employs a small number of large kernel convolutions, which is benefit to the expansion of the effective receptive field of the model and the trade-off between performance and computational efficiency. And a lightweight downsampling block and a shuffle compression block are also proposed, which can effectively reduce the parameters of the model and make the entire method more efficient. The feature fusion block, downsampling block and shuffling compression block are introduced to the ResNet can build a FFNet(Feature Fusion Network), which will have faster convergence speed and a larger effective receptive field and better performance. Extensive experimental results on CIFAR (Canadian
Institute for Advanced Research ), ImageNet and COCO ( Microsoft Common Objects in Context ) datasets demonstrate that the feature fusion network can bring significant performance improvements in classification, object detection and instance segmentation tasks while only adding a small number of parameters and FLOPs(Floating Point Operations).

With advancements in modern science and technology across structural design, materials, and sensor manufacturing processes, pipeline leak detection sensors are becoming increasingly miniaturized and intelligent, and technologies for measuring physical changes caused by pipeline leaks continue to mature. For the convenience of technology selection and optimzation in pipeline leak detection, a systematic review of widely used piezoelectric, optical fiber, and laser sensors in pipeline leak detection is provided, with a focus on analyzing their characteristics and differences in materials, structures, and working principles. It further explores their performance in practical applications and the current state of research both domestically and internationally, offering theoretical support and technical references for the selection, optimization, and future development of pipeline leak detection technologies.

To address the deficiency in the local search ability of the artificial bee colony algorithm, a multi-strategy self-optimizing artificial bee colony algorithm based on reinforcement learning is proposed. This algorithm combines the Q-learning method in reinforcement learning with the artificial bee colony algorithm. The distance between the best value of the population and the individual fitness value, along with the diversity of the population are used as the basis for dividing the state. The algorithm creates an action set that contains multiple search strategies, adopts the ε-greedy strategy for selecting the best, produces high-quality offspring, and achieves intelligent selection of the ABC (Artificial Bee Colony) algorithm update strategy. Through 20 test functions and application in stock prediction, the results show that the proposed algorithm has better performance, a better balance between exploration and exploitation, faster convergence speed, and better self- optimizing ability.

In order to better utilize solar energy, it is very important to accurately predict photovoltaic power generation. To improve the accuracy of photovoltaic power prediction,a photovoltaic power prediction method based on the combination of factor-related complementary ensemble empirical mode decomposition and optimized long short-term memory network is proposed. Firstly, the CEEMD(Complementary Ensemble Empirical Mode Decomposition) algorithm is used to decompose the photovoltaic power sequence, and the Pearson correlation coefficient matrix of the decomposed power components and environmental factors is established. Three key factors are selected as the input of the subsequent prediction for each decomposed power component.

In order to improve the safety and efficiency of tunnel operation, a multi-sensor based tunnel operation risk perception method is proposed. Firstly, an object detection method based on YOLOv7(You Only Look Once v7) is used to effectively detect information such as traffic flow and speed from video sensors, and a deep temporal convolutional network algorithm is used to dynamically evaluate tunnel operation risks. Video sensors are integrated with multiple sensing devices such as smoke and temperature sensors to form a fire risk monitoring system, and multiple sensing devices are integrated to form a fire monitoring system. By numerically modeling
the fire monitoring status under different combustion conditions inside the tunnel, the distribution and development patterns of temperature, toxic gas concentration, and smoke inside the tunnel are analyzed, providing a risk assessment of tunnel fires. This method is applied in some tunnels of Shandong Jiwei Expressway to ensure the safety of the tunnels.

The L_OOA(An Improved Osprey Optimization Algorithm) is proposed to address the issues of the original OOA (Osprey Optimization Algorithm), which is prone to local optima and slow optimization speed. Firstly, to maintain population diversity, the Tent chaotic mapping strategy is adopted to initialize the individual positions of the population. Secondly, by introducing the Levy strategy to update the position of the Osprey, the Osprey Optimization Algorithm can improve its ability to jump out of local optima. The spiral curve strategy is introduced into the Osprey optimization algorithm to improve its computational accuracy. Finally, comparative

experiments are conducted with other intelligent algorithms on the CEC2021 ( Computational Experimental Competition 2021)testfunction set. Experiments prove that L_OOA has better accuracy and faster speed.

In order to solve the problem of network traffic management in the development of campus network informatization, associated with the practical problems of campus network management of a university in Xinjiang, a network traffic monitoring platform based on CactiEz is proposed and implemented. Based on the actual environment of the campus network, the current situation of the campus network is analyzed, and the traffic is monitored with specific hardware and software equipment. The application results show that the monitoring system can monitor the changes of network traffic in real time, reflect the network status in time, and carry out statistics and analysis of network traffic, providing data support for network performance and security. Therefore, the network traffic monitoring platform based on CactiEz plays a significant role in improving the efficiency of campus network management and helps to optimize network management.

In order to show the virtual image more intuitively, a visual communication algorithm for small and weak target images in virtual reality environment is studied. An image model is constructed based on the imaging characteristics and influencing factors of the target image in the virtual environment, the image target is adjusted based on the actual situation and image model, time domain and spatial domain are combined, and the spatial background is constrained to suppress the background image. The filtered image and residual background are used to complete image denoising. Based on the above preprocessing results, and other control factors such as the motion speed of the target image sequence, characteristic window area, and so on, image sequences are sampled, and feature tracking is converted into optical flow calculations, accurately tracking target images, obtaining optical flow results, and achieving visual communication of small and weak target images. Experimental results show that this algorithm has a higher success rate in visual communication, a shorter communication time, and a higher visual communication integrity.

The era of big data has arrived, and the digitization of archive information is the future development trend. How to protect the privacy of digital archive information is a key research topic in the computer field. At present, the archive privacy protection algorithm based on blockchain technology has problems such as poor protection effect and long operation time. In order to solve the problems existing in traditional methods, a digital archive information privacy protection algorithm based on blockchain technology is proposed. Firstly, apply blockchain technology to the privacy protection process of digital archive information. The specific protection

process is as follows: the data owner uses symmetric encryption algorithms to encrypt the digital archive information and upload it to the private chain; At the same time, generate a secure index of digital archive information and upload it to the alliance chain; The data user generates a query threshold for the keywords to be queried, sends it to the private chain, obtains the query results on the private chain, and sends them to the alliance chain. The alliance chain cooperates with the private chain to verify the correctness of the query results. If it is correct, the alliance chain will send the converted encrypted data to the data user. The experimental results show that the privacy protection algorithm for digital archive information of the proposed method has good privacy protection effect and practical application effect.

The channel resources of RFID ( Radio Frequency Identification) systems are limited, and when multiple tags compete for the same frequency or time slot, it can lead to collisions and conflicts. In order to optimize the communication efficiency of broadcast channels, a collision prevention algorithm for RFID broadcast channels in the Internet of Things based on frame time slot ALOHA is proposed. This method introduces the concept of frame time slots and divides the communication time into time slots; By analyzing the probability of occurrence of idle, successful identification, and collision states within the time slot, the cause of collision in the

broadcast channel is obtained. By combining Bayesian algorithm and Poisson distribution rules, the probability distribution of the number of tags is calculated to estimate the number of tags within the range of the reader and writer, and the next frame length is adjusted based on the calculation result of the number of tags. If there is still label collision problem within the adjusted frame time slot range, FastICA( Indcpendent Component Analysis) independent principal component analysis is used to transform the label recognition problem within the frame time slot into an EPC(Electronic Product Code) encoding generation problem, thereby achieving parallel recognition of multiple labels within a unified time slot and avoiding collision situations. The experiment shows that the estimation of the number of labels proposed is accurate, which can improve the label recognition rate within the time slot and effectively improve the propagation efficiency of the broadcast channel while ensuring the stability of the communication channel.

Although traditional recommendation systems use graph structure information, most of them only consider the basic attributes of users and items, ignoring the important factor of contextual interaction information between users and items. Even if contextual interaction information is taken into account, there is a lack of attention in the layer combination stage. force mechanism to assign weight. To solve this problem, a CIAGCN (Context Information Attention Graph Convolutional Networks) recommendation model that integrates contextual interactive information and attention mechanism is proposed. This model utilizes the contextual interaction

information of users and items while applying the high-order connectivity theory of graphs to obtain deeper collaborative signals. An attention mechanism is introduced in the layer combination stage to improve the interpretability of this stage. The model was experimentally compared on the Yelp-OH, Yelp-NC and Amazon- Book data sets. The results showed that the model had a certain effect compared with other algorithms, indicating that the recommendation effect was better than some traditional recommendation models.

When using data from a single data source to complete tasks, there may be significant errors in the data, and there may even be data missing, which can affect the progress of the task. A dual channel data association and fusion algorithm based on fuzzy mathematics theory is proposed for this purpose. The correlation of dual channel data is measured and the missing data in the dual channel data is predicted according to the missing data prediction process. The missing data in the dual channel dataset is filled in to obtain complete dual channel data. The dual channel data is standardized, and the principal component analysis is used to calculate

the similarity between the dual channel data and the principal components, obtaining the comprehensive support level of the dataset, and obtain effective data. By using fuzzy mathematics theory, effective data is fuzzified, and the closeness between the fuzzification results and real data is calculated to determine the data fusion weight, in order to achieve dual channel data association and fusion. The experimental results show that using the proposed algorithm for dual channel data association fusion, when the total number of data reaches 1 500, the value of the comprehensive evaluation index exceeds 9, indicating that the proposed algorithm can improve the accuracy of dual channel data association fusion and has good dual channel data association fusion results.

Air combat is an intense, complex, and continuous process, filled with many influencing factors,complex interactions, and uncertainties. Aiming at the problem of low accuracy of UAV ( Unmanned Aerial Vehicle) cluster air combat effectiveness assessment, a method based on System Dynamics is proposed. The interactions between various factors is analyzed in the UAV air combat system during a reconnaissance and strike mission carried out by the red formation. A causal relationship model and a stock flow model are established.The evaluation indicators of combat effectiveness are constructed based on three aspects: combat effect, combat
efficiency, and combat cost. These indicators include mission completion, combat efficiency, and combat loss rate. Then, the influencing factors of the air combat system and the combat effectiveness under different equipment schemes are studied. finally the feasibility and effectiveness of the proposed method are verified through simulation, which solves the complexity and uncertainty problems arising in the assessment process.

Rolling bearing is one of the key components in rotating machinery, and long-term mechanical operation leads to wear easily. Traditional fault diagnosis relies on feature extraction, but due to loud noise during mechanical operation, effective signals are drowned. And the fault diagnosis network structure is complicated and there are too many parameters. Therefore, a bearing fault diagnosis model based on variational mode decomposition and deep learning is proposed for bearing wear detection. Firstly, the bearing signal is decomposed by VMD( Variational Mode Decomposition) and denoised by Hausdorff distance. Secondly, the

selected effective signals are inputted into the network structure of one-dimensional convolutional neural network and gate recurrent unit to complete the classification of data and realize the fault diagnosis of bearings. Compared to common bearing fault diagnosis methods, the proposed VMD-1DCNN-GRU(Variational Mode Decomposition- 1D Convolutional Neural Networks-Gate Recurrent Unit) model has the highest accuracy. The experimental results verify the feasibility of the proposed model for the effective classification of bearing faults, which has certain research significance.

To address the efficiency and quality issues in current molecular diagnosis talent cultivation, the application status and future development trends of AI(Artificial Intelligence) technology in molecular diagnosis talent cultivation is explored. The research content covers the current application of AI technology in molecular diagnostics, its advantages and challenges, and focuses on analyzing how AI can enhance the efficiency and quality of talent cultivation through automated experimental processes, precise data analysis, and
interdisciplinary knowledge integration. The study summarizes practical experiences from domestic and international universities in integrating AI with molecular diagnostic talent cultivation and outlines future development trends, including the integration of VR ( Virtual Reality ) and AR ( Augmented Reality )technologies, the precision of intelligent diagnostic systems, and the intelligence of personalized learning platforms. The conclusion of the study indicates that AI technology holds great potential in the cultivation of
molecular diagnostic talents, significantly enhancing their comprehensive competitiveness and promoting the further development of molecular diagnostic technologies to provide robust talent support for precision medicine. However, the application of AI technology still faces multiple challenges, including the integration of interdisciplinary knowledge, data quality, and ethical and privacy issues, which need to be addressed through the joint efforts of educational institutions, industries, and governments.

Considering that the traditional trial-and-error method of parameter setting for rotary inverted pendulum PD( Proportion Differentiation) controller has strong subjectivity and poor response ability, genetic algorithm is used to set parameters of PD controller so as to conduct model simulation and to ensure its operation on QUBE-Servo2 rotary inverted pendulum experiment system. The experiment shows that compared to the trial and error method, the PD controller parameters obtained by genetic algorithm further optimize the response performance of the system, and are not limited by subjective experience. The steady-state errors of the swing rod and swing arm are both within 0. 01 rad.

To accurately obtain the longitudinal velocity of the vehicle, a longitudinal velocity estimation method applicable to four-wheel drive vehicles is proposed. Firstly, a finite state machine is utilized to identify the vehicle state at the current moment and the vehicle state in the time-domain window, which effectively switches between the adaptive Kalman filtering method and the integration method. For the four-wheel non-total skidding state, an adaptive Kalman filter method that updates the measurement noise in real time is designed. This method introduces the measurement value and estimation error in the time-domain window to improve the estimation accuracy. For the four-wheel total skidding state, the last longitudinal velocity estimate from adaptive Kalman filtering is used as the initial value, and the longitudinal velocity is calculated by integrating the longitudinal acceleration of the vehicle. The effectiveness of the algorithm is verified by Carsim and Simulink joint simulation experiments and real vehicle data experiments. The experimental results show that the estimation accuracy of the proposed estimation method is improved by at least 65% and 75% on low-adhesion road surfaces such as snow and ice, respectively, compared with the integral method and the method of estimating longitudinal velocity using wheel speeds.

To address the issues of motion distortion and error accumulation in SLAM(Simultaneous Localization and Mapping) systems during prolonged operations, a mapping method called IRIS-LOAM ( Lidar-Iris Based Lidar Odometry and Mapping in Real-Time ) is proposed, which leverages Lidar-Iris to construct global descriptors for loop closure detection. This algorithm has two major  innovations based on the LOAM algorithm.First, in the data processing stage, it integrates lidar data with IMU(Inertial Measurement Unit) data and uses the IMU data to correct the point cloud data. Second, in the mapping optimization stage, it employs an information matrix-based graph optimization algorithm and utilizes Lidar-Iris global descriptors for loop closure detection of key frames. And it preprocesses the input point cloud to improve the time efficiency of optimization. Comparing the improved algorithm with A _ LOAM through experiments, the results show that IRIS-LOAM achieves better mapping performance in various real-world scenarios, demonstrating its feasibility and practicality.

UAV(Unmanned Aerial Vehicle) aerial photography, characterized by multi-angle, large field of view, and large-scale scenes, often results in images with numerous small objects, complex backgrounds, and difficult feature extraction. To address these issues, a new model, CA-NWD-YOLOV5 ( Coordinate Attention- Normalized Wasserstein Distance-You Only Look Once v5) is proposed. Based on the YOLOv5 model, a multi- scale detection layer is added to the head network to extract the features of small targets. It also incorporates a CA attention mechanism into the backbone network to prevent the model from overlooking target location

information. Lastly, the normalized Wasserstein distance loss function replaces the loss function based on intersection ratio, enhancing the model’s sensitivity to small targets. Experiments on the VisDrone2019 dataset demonstrate that, compared to the improved YOLOv5 model, the CA-NWD-YOLOv5 model can effectively enhance the detection accuracy of small and medium-sized targets in UAV aerial photography images. The mAP_ 0. 5 of the improved algorithm reaches 50% , proving its effective application to the detection of small targets in aerial photography.

To maintain the security of network operation and ensure the secure storage of network information, a network security situation assessment system based on multi-source data mining is proposed. This study first establishes a three-layer network security situation system architecture with application layer, control layer, and data forwarding layer as the core. To ensure effective information transmission between the application layer and network devices, the OSGi (Open Service Gateway Initiative) design pattern is used to construct a five layer parallel architecture for the ONOS(Oper Network Operating System) controller of the control layer to ensure the decision-making response of the network security situation. Utilize the deployment of multiple detectors within the traffic detection module to achieve deep mining of network multi-source data; Introduce the LEACH(Low Energy Adaptive Clustering Hierarchy) algorithm to achieve multi-source data fusion at the network cluster head. After analyzing the threat level of network intrusion factors through the security situation assessment module, combined with the weight coefficient theory, the threat level of the network situation threat factors is assigned. Combined with the network hierarchical division method, the security situation of the operational network service layer, host layer, and network layer is evaluated in layers. The experiment shows that the proposed method has a high ability to analyze the operational status of network data, and can accurately identify attacks from multiple types of network threat factors, providing important guarantees for network security operation.

In order to solve the problems of uncertainty, discontinuity, randomness and nonlinearity in stock price forecasting, a TRSSA-ELM ( Tent Random Walk Sparrow Optimization Algorithm-Extreme Learning Machine) stock price forecasting model is proposed. Firstly, adaptive Tent chaotic mapping and random walk strategy are used to improve the algorithm, which enhances the diversity and randomness of the population and improves the local and global optimization ability of the algorithm. Secondly, the performance of TRSSA( Tent Random Walk Sparrow Optimization Algorithm) is verified by using single peak, multi-peak and fixed multi-peak

test functions. Compared to SSA( Sparrow Optimization Algorithm), AO( Aquila Optimizer), POA( Pelican Optimization Algorithm) and GWO(Grey Wolf Optimizer), TRSSA algorithm has better convergence speed, accuracy and statistical properties. Finally, because the ELM ( Extreme Learning Machine) model randomly generates weights and thresholds, which reduces the prediction accuracy and generalization ability, TRSSA algorithm is applied to optimize the weights and thresholds of the ELM model, and the TRSSA-ELM model is tested in Sanan Optoelectronic stock data set. The experimental results show that TRSSA-ELM model has better prediction accuracy and stability than SSA-ELM, ELM, SVR(Support Vector Regression) and GBDT(Gradient Boosting Decision Tree).

Big data usually comes from different data sources with diverse formats, structures, and qualities. Big data often contains a large number of redundant features, which can affect the accuracy of data classification during feature integration. To address these issues, a deep learning-based algorithm is proposed for feature integration classification in hospital big data. A feature extraction model is established based on deep learning to extract relevant features from the data. However, since the training process of the model introduces a significant amount of noise, the extracted features may contain irrelevant information, which can impact the results of feature integration classification. Therefore, a stacked sparse denoising autoencoder is employed to suppress irrelevant features. The best training parameters are determined using divergence functions and greedy algorithms, and a loss function is utilized to sparsify the irrelevant features in the feature space, resulting in practical data features.A feature integration classification model is constructed using an autoencoder network, and with the assistance of type-constrained functions and objective functions, the optimal integration centers for each class are obtained to achieve data feature integration classification. Experimental results demonstrate that the proposed method exhibits excellent classification performance, with macro-averaged values above 0. 95, and it also shows fast classification speed, indicating its effectiveness in classification.

Currently, the docking of single-column steel pipe towers in power systems mainly relies on manual implementation, which has a high risk factor and is time-consuming and laborious. Aiming to research the autonomous docking technology of single-column steel pipe tower for this specific technical condition and environment, a vision-based navigation-based hydraulically driven autonomous flexible docking system for single- column steel pipe tower is proposed. The single-post steel pipe tower autonomous flexible docking system uses a microcontroller that enables autonomous positioning and docking through image tracking control, and the

computational performance of the microcontroller makes it easier for technicians to operate. Numerical simulations and hardware tests are carried out for the docking of a single column steel pipe tower in the two- dimensional plane. The results show that the effectiveness of the proposed method is verified by controlling the motion of the steel pipe tower assembly at the docking interface using a small steel pipe tower model with air bearings in the two-dimensional plane with a minimum propellant thruster and a small control moment gyroscope.

In order to fulfill the observation requirements for the total magnetic field intensity of geomagnetic stations, a specialized magnetometer architecture is independently designed for the stations, and the Overhauser magnetometer is developed for station monitoring. Sensitivity evaluations are conducted using both single-station direct measurement and dual-station synchronized methods under field conditions with low noise and in environments with high electromagnetic interference. The experimental results from both direct measurement and synchronized methods indicate that the sensitivity of the JOM-5J magnetometer can reach 0. 02 nT at a 1s period. It is capable of replacing the GSM-90F for applications in earthquake precursor observations and long-term

volcano monitoring.

The scale of multimedia digital image data is enormous, including ordinary RGB(Red Green Blue)images and various types of data such as depth maps, texture information, and normal maps. The difficulty of depth estimation leads to low accuracy in 3D scene reconstruction. To effectively address this issue, an interactive 3D virtual scene algorithm for multimedia digital images is proposed. Corners from multimedia digital images are extracted and they are used as initial values to perform a checkerboard edge search to determine the true corners. All corners are used as feature points to perform camera calibration and obtain the corresponding
camera pose for each multimedia digital image. By using the improved PatchMatchNet to perform depth estimation on the reference image, the output depth map is obtained through multiple iterations. By using the method of reprojection to filter the outer points of the depth map and projecting it into the world coordinate system, an interactive 3D virtual scene is finally obtained. The experimental results show that the proposed algorithm can obtain high-precision interactive 3D virtual scene reconstruction results, and the reconstruction time is less than 50 ms.

In order to suppress the influence of low-frequency magnetic field interference, such as geomagnetic diurnal variation, on the measurement results, multiple magnetometers are usually used for synchronous measurement. The time synchronization error has an obvious influence on the suppression effect. The influence of different time synchronization errors is studied on the JOM-5SF Overhauser magnetometer in geomagnetic detection and instrument sensitivity evaluation, based on the magnetometer developed in the laboratory. Two Overhauser magnetometers are used to conduct experiments on the campus of Jilin University. After comparing

the experimental results with the evaluation results of professional institutions, it is found that the smaller the time synchronization error, the smaller the difference between the magnetic field values of the two instruments, and the more accurate the sensitivity of the evaluation instruments by the synchronous method.

In order to effectively improve the visual effect and matching degree of text matching generated images, a text matching generated image model based on improved GAN( Generating Adversarial Networks) algorithm is proposed. Initial matching of text and images are unfolded through a mixed index tree. On the basis of GAN, they are improved to form an adversarial generation network based on cross attention mechanism encoding, and the improved GAN is used to establish a text matching image generation model. The cross attention encoder in the bidirectional LSTM( Long Short-Term Memory) network optimization model is used to translate and align text and visual information, obtaining cross modal mapping relationships between text and images, completing fine matching between text and images, and ultimately generating images that meet the requirements of the text. The experimental results show that the proposed model can generate images with higher quality that match image details with text.

In order to distinguish the effective component and noise component after VMD(Variational Mode Decomposition), and improve the denoising effect of VMD. A denoising algorithm (VMD-HD-VMD) combining VMD and HD(Hausdorff Distance) is proposed. Firstly, the original signal is decomposed into K IMF(Intrinsic Mode Functions) by VMD, the HD value of the probability density function of IMF component is calculated respectively, and the effective component and noise component are distinguished according to the HD value. Then the noise component is decomposed by VMD again, the effective component is selected by correlation coefficient, and reconstructed with the effective component decomposed for the first time. This method is applied to the denoising of pipeline leakage signal. The simulation experiment and pipeline leakage signal processing show that this method has better effect than EEMD(Ensemble Empirical Mode Decomposition), VMD and VMD combined wavelet denoising.

To address the challenge of efficiently mining spatiotemporal information for traffic prediction, a novel vehicle travel time prediction method is proposed based on bidirectional multi-attention spatiotemporal graph convolution. To extract the spatial dependencies within the road network, a traffic transfer matrix is constructed using a Markov chain approach, which captures the bidirectional traffic flow transfer relationships. Graph convolution is employed to learn the spatial dependencies within the graph network. Subsequently, an attention mechanism is utilized to capture both local and global temporal features within the traffic flow map. Finally, a MLP ( Multi-Layer Perceptron) is used to forecast travel times, producing the final prediction results. The Xuancheng road network traffic data is selected for model validation. The results demonstrate that the proposed model reduces the RMSE (Root Mean Square Error) by 7. 6% , 3. 7% , and 9% , respectively, compared to baseline models such as STGCN( Spatio-Temporal Graph Convolutional Networks), ASTGCN(Attention Based Spatial-Temporal Graph Convolutional Networks), and A3T-GCN ( Attention Temporal Graph Convolutional Network). This significant reduction in RMSE indicates that this model substantially improves prediction accuracy, highlighting its effectiveness in capturing and utilizing spatiotemporal information for more precise traffic predictions.

Aiming at the limitations of existing named entity recognition methods in identifying entities involving multiple elements and nested entities in oil and gas exploration texts, a novel approach is proposed. This approach integrates multiple features using a BERT-CNN-BiGRU-Attention-CRF(Bidirectional Encoder Representations from Transformers-Convolutional Neural Network-Bidirectional Gated Recurrent Unit-Attention-Conditional Random Field) architecture for named entity recognition. The model leverages BERT's semantic extraction capability to obtain character Vectors with global features for the entire sentence. Additionally, it utilizes CNN's ability to capture local features, overcoming limitations of BERT character Vectors, and obtains character-level Vectors for words. By incorporating a custom oil and gas exploration domain dictionary and employing a bidirectional maximum matching method, dictionary feature Vectors are obtained. These three types of Vectors are concatenated and used as input for the BiGRU-Attention-CRF model. Experimental results on a self-constructed small-scale oil and gas exploration dataset demonstrate an F₁ score of 91.10% . Compared to other mainstream NER ( Named Entity Recognition) methods, this model exhibits superior recognition performance. Furthermore, it provides valuable assistance in constructing knowledge graphs for the oil and gas exploration domain.

As the environment of geophysical exploration becomes more complex, and it is limited by acquisition and processing technology which results in low resolution and signal-to-noise ratio of post-stack seismic data.Therefore, how to enhance its resolution while realizing noise attenuation is a non-negligible problem. A design called DESRGAN(Depth-Enhanced Super-Resolution Generative Adversarial Network) is proposed, which is intended to be applied to the task of super-resolution reconstruction of seismic data. DESRGAN uses a LRDB(Lightweight Residual Dense Block) as the base unit to improve the efficiency and stability of the training
process, passes through channel attention in the deep feature extraction phase to increase the focus on important features and performs an up-sampling operation using pixel reorganization instead of interpolation to take into account the spatial relationship between pixels. Experimental results on synthetic and field data show that the network can reconstruct the synthetic data as the test set and it is well generalized to the field data. Compared with classic GAN(Generative Adversarial Network) and CNN(Convolutional Neural Network), the reconstructed results are visually clearer, and have higher peak signal-to-noise ratio and structural similarity in quantitative analysis.

When solving high-dimensional equations, the CS (Cuckoo Search) has the drawback of falling into local optima. To address this deficiency, an improved hybrid cuckoo search is proposed. Firstly, the population is initialized using chaotic mapping and reversed learning mechanisms. Then the search mechanisms of TLBO (Teaching Learning Based Optimization) and CS are performed alternately. Finally, the discovery probability and embeds DE (Differential Evolution) are dynamically adjusted to comprehensively improve the algorithm's performance. The comparative results of simulation experiments with 6 benchmark functions and 1 optimized grating coupler design show that this algorithm is better for solving high-dimensional equations and effectively avoids the CS algorithm getting stuck in local optima.

Magnus rotor is a new type of auxiliary propulsion device for ships. Addressing the disparity between the lift model of Magnus rotors and traditional lift formulae, a combined approach of theory and numerical simulation is employed for investigation. Initially, the geometric and flow domain models of the Magnus rotor are established. Subsequently, computational fluid dynamics software is utilized for grid independence verification and numerical validation. A numerical simulation method is then employed to analyze the aerodynamic characteristics of the Magnus rotor model, considering the impact of various wind speeds and rotor rotation rates on the generated thrust. Finally, based on the obtained data, adjustments are made to the traditional lift model, and the reliability of the modified model is verified by comparing simulation data under different conditions with literature data. The results indicate that the propulsion force of the Magnus rotor increases with the increase of rotation ratio, and the optimized lift model exhibits a high degree of fit with simulated values, demonstrating higher accuracy. 

In view of the defects that the projection matrix learned from LatLRR ( Latent Low Rank Representation) can not explain the importance of the extracted features and preserve the local geometry of data, a novel method named LLRSP (Latent Low-Rank and Sparse Projection) with dual neighborhood preserving and feature selection is proposed. The algorithm first combines low-rank constraint and orthogonal reconstruction to hold the main energy of the original data, and then applies a row sparse constraint to the projection matrix for feature selection, which makes the features to be more compact and interpretable. Furthermore, a l^2,1 norm is introduced to regularize the error component to make the model more robust to noise. Finally, neighborhood preserving regularization is applied on the low dimensional data and low-rank representation matrix to preserve the local manifold geometrical structure of data. Datasets results of extensive experimental on various benchmark show that this method can obtain better performance than other state-of-the-art methods.

In order to ensure the normal operation of the ventilator, an intelligent monitoring method for the operating status of the ventilator based on the HHT(Hilbert-Huang Transform) algorithm is proposed. Firstly,wavelet neural network is used to denoise the running signal of the ventilator; Secondly, combined with the HHT algorithm, the denoised ventilator operation signal is decomposed by EMD(Empirical Mode Decomposition), and the decomposed IMF( Intrinsic Mode Functions) component is transformed by Hilbert spectrum to obtain the signal spectrum as the signal feature. Finally, the obtained signal spectrum is placed in the MLP neural network
classifier, and the backpropagation algorithm is used to train the MLP neural network to achieve recognition of the operating status of the ventilator. The experimental results show that the proposed method has a good denoising effect, and the monitored results are consistent with the actual spectrum. At the same time, the sensitivity of monitoring is above 96% , and the accuracy of operating status recognition is above 95% . This indicates that the proposed method can effectively monitor the operating status of the ventilator and has good monitoring performance.

To ensure stable transmission of big data, a device big data transmission load optimization algorithm based on 5G network is proposed. The factors that affect the performance of big data transmission are analyzed,including data latency, average stream bandwidth utilization, and throughput. Morphological filtering algorithms are used to perform low-pass filtering on big data, eliminating noise in the data and reducing data transmission delay. Dynamically big data transmission channels are selected to avoid data congestion in the network and improve network throughput. On the basis of information transmission matrix mapping, data transmission accuracy is improved, and a capacity expansion mechanism is designed to improve network bandwidth utilization
and complete load optimization. The experimental results show that after optimization using the proposed algorithm, the bandwidth utilization rate is improved, and the network energy consumption and data transmission delay are reduced.

The EEMD(Ensemble Empirical Mode Decomposition) algorithm faces challenges in aligning the generated IMF(Intrinsic Mode Function) components during the decomposition process. To address this issue, a novel denoising method that combines EEMD with the PRT(Phase Randomization Technique) is proposed, enhancing the denoising performance of the improved EEMD algorithm. By incorporating PRT, the method effectively handles nonlinear and nonstationary signals, significantly improving the stability and reliability of the IMFs, and enhances the performance of the EEMD algorithm in noisy environments. The experimental results strongly demonstrate the innovation’s value, as the EEMD-PRT algorithm shows superior performance compared to traditional methods by improving the signal-to-noise ratio and correlation coefficient of noisy signals, reducing the mean square error and mean absolute error. Furthermore, its effectiveness has been thoroughly validated in pipeline leak detection for pipes with varying diameters.

Deep learning methods have improved the efficiency and accuracy of fault identification, but current research often relies on extracting fault features from single attributes such as seismic amplitude, which leads to issues like poor fault continuity and missed detections. These problems limit the exploration and development of oil and gas reservoirs in complex areas. An intelligent fault identification method based on deep learning technology is proposed, which adopts a multi-level fusion strategy to construct a dual-attribute parallel fusion network PE-Net(Parallel Elements Network). Firstly, the ant body attributes and amplitude attributes are input
into the ant body feature extraction network and the amplitude feature extraction network respectively, capturing the fault features of different angles from both paths using the AIFM ( Attribute Intensive Feature Module). Secondly, two attribute feature modules are used to integrate cross-layer features of the output of each branch, mining multi-scale information and mitigating scale changes. Finally, the FFM(Feature Fusion Module) is used to integrate the two parallel branches, reducing the limitation of a single attribute. Synthetic data experiments demonstrate that the PE-Net model achieves an accuracy of 97. 95% , with a 1. 33% improvement compared to the U-Net model. The fault identification results on the Kerry3D dataset and ablation experiments confirm that the proposed method is capable of capturing more contextual fault features, reducing missed and false detections,thereby improving the accuracy of complex fault identification and enhancing the detection of small faults.

 In order to solve the problems of low brightness, serious noise, and color distortion of color polarization images in low-illumination scenes, an unsupervised learning algorithm for color enhancement of low- illumination color polarization images is proposed, which is named LPEGAN(Low-Light Polarization Enhance Generative Adversarial Network). Firstly, a double-branch feature extraction module is designed and used different branches to extract features from Stokes parameters S0 and S1 ,S2 , respectively. Secondly, the residual void convolution module is constructed. And the different expansion rates can expand the receptive field to improve the model extraction ability and reduce the image color distortion. The edge texture loss function is constructed to ensure the structural similarity between the enhanced image and the input image. Experimental verification is carried out on the public datasets LLCP(Low-Light Chromatic Intensity-Polarization Imaging), IPLNet(Intensity-Polarization Imaging in Low Light Network), and self-built datasets. The experimental results show that the proposed algorithm has better visual effects, and all evaluation indicators are significantly improved. Polarized image brightness is enhanced, noise is significantly suppressed, and image colors are more realistic and natural.

The specific high complexity and nonlinear characteristics of large-scale road network traffic flow in a short period of time affect the accuracy of short-term traffic flow prediction. A short-term prediction method for large-scale road network traffic flow is studied based on improved neural network algorithms. Large-scale road network functions are constructed, road network functions are optimized by treating road sections as the core of the network and treating road nodes as corresponding connecting elements. Based on the optimized road network function, traffic flow features are extracted by combining the K-means algorithm with the EM ( Expectation-Maximization) algorithm. By combining genetic algorithm with Elman neural network algorithm, a short-term prediction of the traffic flow of the road network is carried out, and relevant prediction results are obtained.Experimental results have shown that the improved method's single point average speed prediction results are closer to the actual values, and the short-term prediction error of large-scale road network traffic flow is lower,resulting in higher reliability of the prediction results.

In order to explore the analysis of research points and theme evolution of science and technology resources in China. Bibliometrics and knowledge mapping analysis tools are used to statistically and visually analyse the research papers on S&T resources in China in the past 10 years. The results show that China's technological resources resources are in the growth period, with China Institute of Science and Technology Information, National Science and Technology Basic Condition Platform Centre and Guilin University of Science
and Technology as the main issuing institutions, Research on Science and Technology Management, China Science and Technology Resource Guide, and Science and Technology Progress and Countermeasures as the main journals carrying the papers, and the hotspots of research are the allocation of S&T resources and the influencing factors, the sharing and integration of S&T resources, and the construction of the resource-sharing platform and the The research hotspots are S&T resource allocation and influencing factors, S&T resource sharing and integration, resource sharing platform and service platform construction, collaborative innovation is the research hotspot after 2014, and S&T resource structure, innovation chain and S&T resource pool are the cutting-edge hotspots in the recent three years.

In order to solve the problem that most of the existing microelectronics major courses are based on theory and lack simulation experiments, a set of FPGA(Field Programmable Gate Array) microelectronics and integrated circuit design experiment system are designed based on RISC-V(Reduced Instruction Set Computer) CPU(Central Processing Unit). The ModelSim software compiler is used to simulate and verify, and FPGA is used as development platform to realize CPU system functions. Taking RISC-V reduced instruction set as the instruction set of the CPU and modularization as the design idea, the five-level pipeline CPU is designed from the local microprocessor to the whole. The five-level pipeline includes value, decoding, execution, memory access and write back. The system integrates software and hardware development to stimulate students' interest in learning. The experimental platform built gradually realizes the configuration and instruction set of CPU to the architecture, programming, simulation, writing and debugging of the whole CPU, enabling students to have a deep understanding of the design of integrated circuit system with FPGA, which is conducive to the study of professional theoretical courses. The design simulation content comes from the application of OBE(Outcomes- Based Education) teaching theory to integrated circuit EDA(Electronic Design Automation) course. This design method and content can also be applied to the combination of industry, university and research to improve innovation and entrepreneurship ability of students. 

A proton magnetometer is a type of geomagnetic field measuring instrument based on the Larmor precession effect. However, a proton magnetometer with a single sensor is easily affected by geomagnetic diurnal variation and environmental interference. To improve the measurement accuracy of the proton magnetometer, sensor design and system performance evaluation are studied. Firstly, based on MAXWELL electromagnetic simulation software, simulation models of four kinds of sensors are established, including solenoid, cylindrical coil, ring coil, and "8" coil, and the directivity and anti-interference ability of the four coils are analyzed. Finally, it is determined that the "8" coil is used as the sensor to build a proton magnetic gradiometer. Secondly, the single and differential measurement results based on the fourth-order difference and mean square error algorithms are evaluated to analyze the performance of the magnetic gradiometer. The experimental results show that the initial signal-to-noise ratio of the "8"coil sensor can reach 40 / 1, the sensitivity of the single-channel mode can reach 0. 054 nT, and the sensitivity of the dual-channel differential mode can reach 0. 071 nT even under strong interference conditions, which is √2 times that of the single-channel mode.

In order to encrypt and store communication network faster and more effectively, a communication network data encryption and the data of storage method based on improved RSA(Rivest-Shamir-Adleman) algorithm is proposed. Firstly, wavelet transform method is combined with empirical mode decomposition method of complementary set to denoise communication network data and improve the accuracy of communication network data. Then, the fuzzy C-means clustering algorithm is used to cluster communication network data, and similar data is uniformly encrypted to improve the efficiency of data encryption storage. Finally, the conventional distributed access management mode is replaced in communication networks with hash access data algorithms to enhance the security of data storage and prevent data loss. By improving the encryption process of RSA encryption algorithm, encrypted storage of communication network data is achieved. The experimental results show that the proposed method has good denoising effect, high security, and high encryption storage efficiency, making it suitable for encrypted storage of communication network data. 

 The low efficiency of video surveillance in identifying emergencies results in that the recognition system is unable to detect and respond to emergencies in a timely manner, increasing the risk of potential hazards. Therefore, a recognition algorithms of monitoring image abnormal behavior based on computer vision is proposed. Based on the initial background of the monitoring image, a differential operation is used to obtain the differential image between the background image and the monitoring image, and the background subtraction method is used to perform binary processing on the combined sorted new monitoring image to complete target area recognition. Then, a rectangle is used to traverse the target area, collect effective motion blocks from the target area, extract the feature vectors of the motion blocks, and complete the extraction of abnormal behavior features in the monitoring image. And the identification of abnormal behavior in monitoring images through Kuhntak conditions is completed. The experimental results show that the proposed method has an abnormal behavior recognition time of less than 1. 0 s, and the recognition accuracy remains above 94%. It can accurately identify abnormal behavior in monitoring images, effectively improving recognition efficiency and recognition rate.

Currently, the lack of standardized support for ontology quality assessment models in the field of data governance is a significant issue. Building a standardized ontology quality assessment model is of utmost importance in addressing this challenge. By studying the dimensions under ISO/ IEC 25012 data quality standards, the GQM (Goal-Question-Metric) methodology is used as a guide to define metrics under the dimensions and realize the mapping from metrics to dimensions. Finally, based on the DQV(Data Quality Vocabulary)data quality model proposed by W3C(World Wide Web Consortium), a scalable and robust ontology quality model is constructed. The proposed quality assessment model provides a complete, unified, and standardized terminology system to describe the various elements of ontology quality, and provides a standardized quality knowledge representation model for ontology quality assessment. Finally, taking the completeness dimension as an example,the corresponding quality assessment model is constructed, and the feasibility of the model is verified by using the downhole operation data set. It effectively solves the problem of the lack of standardization of ontology quality assessment model in data governance field, and provides a unified and standardized term system to describe each element of ontology quality in data governance field. 

With the emergence of advanced communication technologies such as high-throughput satellites, the integration of power satellite and smart grid has become an inevitable trend, and its related security certification has become the focus of research. However, the existing authentication schemes are mainly studied under the isomorphic architecture focusing on ensuring the authenticity verification of entities. Therefore, a heterogeneous authentication scheme for smart grid based on power satellite is introduced. The proposed scheme realizes the authenticity verification of each communication entity in a heterogeneous environment, and provides a validity verification method for terminals. Security analysis confirms the correctness and security of the scheme, and performance analysis shows that the proposed scheme effectively reduce the time cost of authentication phase than the existing schemes. 

In order to reduce the error between the target drilling trajectory and the actual drilling trajectory measurement results, a drilling trajectory measurement error correction method based on particle swarm optimization algorithm is proposed. A drilling trajectory calculation model is established, the values of drilling inclination angle, drilling orientation angle, and drilling azimuth angle are determined, and drilling trajectory data is collected. The sources of errors in drilling trajectory measurement is analyzed, an error transfer state space model is constructed, and the historical errors are merged to complete the calculation of drilling trajectory

measurement errors. The error correction objective function is constructed with the goal of minimizing the measurement error of the borehole trajectory. The velocity and position of particles are updated, and the fitness function is constructed. The objective function is solved by continuously updating and calculating the fitness function to complete the correction of the measurement error of the borehole trajectory. The experimental results show that the roll angle error in each direction of the proposed method is only between 0. 3° and 1. 8 °, and the drilling trajectory is highly fitted with the actual value curve, which can effectively correct the trajectory

measurement error and provide valuable reference for the actual exploration work of underground engineering.

A modified detection algorithm of electric bicycle helmet based on YOLOv5s(You Only Look Once version 5 small) is proposed to address the issues of small target missed detection and low accuracy in electric bicycle helmet wearing detection. CBAM ( Convolutional Block Attention Module) is introduced into the backbone network enhancing attention to clustered targets and effectively solving the problem of poor detection performance caused by occlusion. The PANet structure in the neck network is changed to a feature fusion structure that combines the idea of cross-scale feature fusion network (BiFPN: Bidirectional Feature Pyramid Network) enhances the multi-scale fusion ability of the model in different directions and effectively fuses multi- scale features of the target. Using SIoU(Structured Intersection over Union)localization loss function instead of CIoU(Complete Intersection over Union)loss function improves the accuracy of bounding box regression. The experimental results show that the accuracy P and recall R of the improved YOLOv5s model are 94. 7% and 91. 2%, respectively, and the average accuracy value mAP is 95. 6%, which is 6%,7%, and 6. 5% higher than that of the original YOLOv5s model, respectively. The method has significantly improved the accuracy of electric bicycle helmet wearing detection.

In order to effectively improve the efficiency and performance of intelligent retrieval of book information resource services, a machine learning algorithm based intelligent retrieval method is proposed. Machine learning algorithms are used to classify the keyword frequency of books, providing the corresponding index for each class, calculating the weight of feature words corresponding to each document in the classification,and obtaining the score of feature words through repeated iterations. A contextual feature matrix is established,the corresponding score for each class is calculated, and the feature with the highest score is selected for classification processing. Based on the classification results of book information resources, grid computing technology is introduced to construct an intelligent retrieval model for book information resource services, and the model is used to achieve intelligent retrieval of book information resource services. The experimental results show that when using the proposed method for intelligent retrieval of book information resource services, the precision obtained is above 96. 0% , the recall rate remains above 90% , and the retrieval time under different datasets is around 450 ms, indicating that the proposed method has good performance in intelligent retrieval of book information resource services.

 In order to solve the problem of constructing the overall impedance model of electric vehicle cascade- type charging module, a cascade-type charging module impedance modeling method based on VIENNA rectifier and full-bridge LLC resonant converter is proposed. Firstly, a typical topology of the charging module is determined, and the small signal model of the front VIENNA rectifier based on the state space method and the rear full-bridge LLC resonant converter based on the equivalent circuit method are constructed respectively. Secondly, the closed-loop output impedance of VIENNA rectifier and the closed-loop output impedance and input impedance of full-bridge LLC resonant converter are obtained by combining the control strategy. The small Signal circuit model of the charging module can be obtained by integrating the front and rear small signal models and control strategies, and then the overall impedance model of the charging module can be derived. According to Nyquist stability criterion, the influence of system parameters on the stability of charging module is analyzed. The charging module simulation system is built based module. The proposed modeling method realizes the overall impedance modeling of single-stage to two-stage charging modules, and provides a theoretical basis for analyzing the parallel stability of charging modules in the future.

The anti-disturbance ability and dynamic performance are poor in the inverter stage of PET(Power Electronic Transformer)based on traditional VSG(Virtual Synchronous Generator)control. In order to address the problem, a VSG control combined with linear active disturbance rejection control is proposed. A second-order active disturbance rejection controller is added to the active part of the traditional VSG control. State observation and feedback are introduced to the controller to estimate the system error in real time, so that the frequency and power of the inverter can be stably tracked under different operating conditions, while the oscillation phenomenon is weakened. With the improved control strategy, the maximum overshoot is reduced by 54. 5 percent and the frequency fluctuation time is reduced by 0. 22 s, which make the PET inverter stage have stronger dynamic response and steady-state performance. The simulation demonstrates that the control strategy is feasible and effective. It also shows that the improved VSG control strategy accelerates the recovery speed of the PET inverter stage after being disturbed, and has better dynamic performance.

 In order to solve the problems of low efficiency of manual laboratory management, slow transmission speed of monitoring data and insufficient level of informatized management, an intelligent laboratory management and control system based on all optical access network is designed and implemented. It consists of laboratory front-end monitoring module, all optical access network data transmission module and laboratory management and control center module. The ESP 8266 microcontroller is used as main control chip in the laboratory front-end monitoring module. The acquisition unit of laboratory operation status data is designed. It consists of fingerprint recognition module, temperature and humidity sensor, smoke sensor and network camera. Real-time data acquisition of personnel management and control, video surveillance and environmental monitoring is thus realized. Optical network units, optical fiber distribution network and optical line terminal are utilized to construct all optical access network data transmission module, realizing remote high-speed transmission of each laboratory monitoring data. The web page of laboratory management and control platform is developed, real-time operation status data of each laboratory is displayed in terminal management and control server. The joint debugging result shows that real-time personnel management and control, video surveillance and environmental monitoring are realized, and the laboratory management and control system provides reliable stability in a long time. 

 Due to the Irreversible process of scrambling and extraction process, the hidden information of digital media video image information can not be completely recovered in the extraction process, resulting in information loss or error, and reducing the effectiveness of the hiding algorithm. To solve this problem, a digital media video image information hiding algorithm based on reference frames is proposed. Firstly, the NLEMD(Neighborhood Limited Empirical Mode Decomposition) algorithm is used to enhance digital media video images and improve video image quality. Secondly, the Arnold transform scrambling method is used to perform scrambling transformation on the enhanced image, completing the preprocessing of information hiding. Finally, the scrambled digital media video image information is hidden through an information hiding algorithm based on reference frames. The experimental results show that the proposed method can improve the peak signal-to-noise ratio of digital media video images, reduce the time required for embedding and extracting hidden information,and achieve high accuracy in information extraction.

Due to the limitation of environmental and economic factors, the collected seismic records usually have a lot of noise interference, which may cause some obstacles to the subsequent seismic data processing. Effectively attenuating noise is a key issue in seismology. In recent years, CNNs ( Convolutional Neural Networks) have achieved some success in the field of seismic data denoising. However, weak signal recovery in the presence of strong background noise is insufficient for existing convolutional neural networks. To address the above issues, a denoising network called MAUnet(Multi-Scale U-Net and An Attention Fusion Mechanism) is proposed. based on a multi-scale U-Net and an attention fusion mechanism. MAUnet innovatively introduces a dual-mechanism architecture, where a multi-scale module enables the network to learn features at different scales. And an attention-based feature fusion mechanism allows the network to combine shallow high-frequency details with deep semantic information, enhancing its learning capability and achieving feature complementarity. Experimental results demonstrate that our method has better noise attenuation and recovery capability for weak signals than competitive methods. 

There are many types of information features in the supply chain privacy network, and it is difficult to determine data ciphertext, which leads to high encryption difficulty. Therefore, a chaotic sequence based information encryption algorithm is proposed. Considering the risk of privacy information being leaked or tampered with, the risk variation is used as a reference feature for encryption algorithms. The risk index is obtained by solving the same, different, and opposite risk variation characteristics of privacy information through ternary and quinary functions. A chaotic sequence is established based on the risk index of the information to be
encrypted, a key sequence is generated through the chaotic sequence, the dimensions corresponding to different types of information are calculated, and finally the information encryption is achieved through chaotic mapping between the information and the key sequence. Experimental data shows that the proposed algorithm has high accuracy in encrypting supply chain privacy network information, low packet loss rate, and can effectively improve the phenomenon of privacy information leakage and loss during transmission.

Due to the lack of practical teaching resource of optical communication network, an all-optical access network practical teaching system based on virtual-real combination is designed. The communication service opening is regarded as main task, a real practical teaching system is built based on all-optical access network commercial equipment. The application layer server and communication user terminal are simulated by software and hardware combination. Configuration information from application layer server to communication user terminal through all-optical access network is planned and the success of various communication services opening is verified. The network troubleshooting is regarded as main task, a virtual simulation experiment teaching system of all-optical access network is developed by utilizing virtual reality technology. The virtual campus application scenarios including central office, fiber distribution terminal and university-enterprise joint laboratory are constructed. Concentrated presentation of optical distribution network, multi-service gateway, optical line terminal and application layer server related network troubles is realized. With the design and application of this practical teaching system, the teachers’ construction ability of optical network practical teaching resources is improved, and the students’ practice and innovation ability to solve complex problems in the application of optical network is cultivated. 

In order to make up for the lack of selectivity of a single gas sensor in the face of a variety of gases and to identify a variety of gases more accurately, an improved convolutional neural network based on structural reparameterization technology and depth-separable convolution technology is proposed. It integrates the multi- branch convolution structure during model training into the single branch simple convolution layer during inference. In addition to simplifying the complexity of the inference model, the feature extraction ability of the model for gas response data is greatly enhanced. When this method is applied to a common data set of gas sensor array containing 10 common VOCs, the recognition accuracy reaches 96. 46%, and the accuracy reaches 97. 44% after adjusting the complexity of the model and adding the convolutional layer.

The warship’s common computing environment integrates computing and storage resources through virtualization technology to build a public infrastructure platform for warships. However, it is limited by the space and energy consumption requirements of the maritime combat platform. Optimizing the virtual machine deployment strategy is an important development to reduce the energy consumption level of the warship’s commoncomputing environment and improve basic resource support capabilities. Several commonly used virtual machine optimization deployment methods are compared and a virtual machine deployment strategy for warship’s common computing environments is proposed based on an improved flower pollination algorithm. An improved maximum

and minimum distance method is designed and applied to the initial population generation process to enhance the initial solution. To improve the quality, a local search strategy with an information exchange mechanism is proposed by introducing the hybrid frog leaping algorithm. And an adaptive switching probability strategy is proposed to balance global pollination and local pollination, and generate an optimized deployment plan for mapping virtual machines to servers. It is verified through simulation experiments that the proposed virtual machine deployment optimization strategy can significantly reduce the energy consumption level of the warship’s common computing environment.

 In order to enhance the overall efficiency of the laser pump source system, a design for a load- adaptive semiconductor laser array constant current driver is presented. This driver can adaptively adjust the supply voltage of the load based on the number of series loads in the laser array and the changes in the drive current, thereby optimizing work efficiency. The maximum output voltage of the driver is 22 V, and the maximum output current is 1 200 mA. When driving eight series loads of the laser array, the efficiency can exceed 91. 6%. This load-adaptive technology provides a new approach for designing efficient semiconductor laser drivers. 

 In order to improve the accuracy and efficiency of face recognition results of smart access control system, and thus enhance the intelligent service of smart door security, a smart access control face recognition algorithm based on twin neural network is proposed. The wavelet coefficients of the face image signal are obtained by wavelet transform, the appropriate threshold is selected to process the wavelet coefficients, and the inverse transform of the wavelet coefficients is carried out again to obtain the de-noised face image. After the face image is de-noised, the output value of the face image is mapped and processed in the twin neural network to form a feature vector with a dimension of 128. The contrast loss function is introduced to determine the similarity of the face image by comparing the Euclidean distance between the output feature vectors of the sample network, and finally realize intelligent access control face recognition. The experimental results show that the intelligent access control face recognition results and recognition efficiency of the proposed algorithm are significantly better than other algorithms. 

To address the problem of determining the optimal strategy for air combat maneuver decision making with incomplete information, an evaluation method based on interval projection pursuit is proposed. Firstly, the interval number is introduced to represent the incomplete air combat data, the Euclidean distance in the TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) is replaced by the grey relational degree, the positive and negative ideal solutions are given, and the RIGRA-TOPSIS(Referential Interval Grey Relation Analysis- Technique for Order Preference by Similarity to Ideal Solution) method is proposed to quantitatively obtain the objective weight of air combat indicators. Then, an improved interval projection pursuit method is introduced, which takes the obtained objective weights as the initial projection vector of the interval projection pursuit method, uses Gini coefficient instead of standard deviation to calculate the projection density, uses the particle swarm optimization algorithm to calculate the projection value, and determines the optimal strategy corresponding to the maximum projection value in the air combat game. The simulation results show that the proposed method has a good effect in the case of small sample air combat strategy set.

Integrated passenger transport hubs usually involve a large number of vehicles and routes, and the traffic flow, passenger demand, and traffic conditions of passenger transport hubs are dynamically changing, which can easily lead to schedule conflicts and make multi route vehicle scheduling difficult. Therefore, a comprehensive passenger transportation hub vehicle multi line scheduling method based on improved ant colony algorithm is proposed. Considering the reduction of operating costs, waiting time, and overall travel time, with the goal of minimizing the operating costs and passenger travel time of the integrated passenger transport hub system, a scheduling optimization model is constructed. Ant colony algorithm is used to the model, introducing search hotspots, optimizing pheromone update strategies and heuristic factors to improve the ant colony algorithm, and the multi line scheduling of comprehensive passenger transportation hub is completed. The experimental results show that the proposed method can more comprehensively carry out multi line scheduling of vehicles, with a waiting rate of less than 5% and an average scheduling time of only 5. 8 s, effectively improving convergence rate, accuracy, and efficiency.

Aiming at the problem of limited communication conditions in the control of severe slug flow in the horizontal pipe-downward inclined pipe-riser system of submarine mixed transportation, a MPC (Model Predictive Control) strategy based on DET (Dynamic Event Triggering) is proposed. Firstly, the causes and processes of slug flow are described, and the simplified model for control is analyzed. Secondly, a dynamic event triggering mechanism based on the deviation between predicted value and actual value is designed to monitor the running state of the system in real time and adjust the event triggering conditions to improve the steady-state performance of the system and reduce the triggering frequency. Finally, the comparative experiment analysis is carried out. The results show that the proposed method can effectively reduce the triggering frequency of the system on the basis of ensuring the control performance. Compared to the small opening valve, the oil production increases by about 2. 8%.

For the classification of networked data, most relational network classifiers are based on the homophily hypothesis, and the simplified processing based on the first-order Markov assumption has certain limitations. The local graph ranking algorithm ( activation spreading) is introduced into the network Bayes classifier instead of the original direct neighborhood acquisition method. The neighborhood range of nodes to be classified is appropriately expanded by setting the initial energy and the minimum energy threshold, increasing the homophily of nodes. Combined to the collective inference method of relaxation labeling, the classification
accuracy of network data is improved to a certain extent. Compared to 4 network classifiers, the experimental results show that the classification performance of the proposed method on 6 networked datasets is improved in different degrees.

For a class of uncertain networked stochastic T-S(Takagi-Sugeno) fuzzy systems with time-varying delay, quantization error, the problem of hybrid-triggered robust H∞ control system with two-terminal quantization is studied. Firstly, in order to alleviate the burden of networked communication, a hybrid-triggered scheme is adopted to reduce data transmission. The construction of quantizers at the sensor side and the actuator side is stadied to quantify the sampling and control signal respectively, and the quantization error is considered to improve the control accuracy of the system. By taking the effect of network-induced delay, uncertainty and quantization error are taken into consideration, the T-S fuzzy systems based on the hybrid-triggered mechanism is remodeled. Secondly, by selecting the delay-dependent and fuzzy basis-dependent Lyapunov function, and introducing the free weight matrix, the sufficient conditions for the double-terminal quantized fuzzy system are satisfied, and the influence of energy bounded noise signals on the output is suppressed under the H∞ performance index γ. Finally, the simulation proves that the proposed scheme can reduce data transmission effectively, improve the system control accuracy, and reduce the conservatism of design. 

Because there are many factors affecting the network link state, it is difficult to accurately judge the network link state and the location where congestion is about to occur, resulting in the decline of the quality for network link congestion control. A priority based mathematical modeling method for network link congestion automatic control is proposed. A heterogeneous network model combined with the current occupation and change of network interface queue buffer space is built to detect the network link congestion, and judge the network link status and the location where congestion is about to occur. Through the data request sending mechanism, the
detection results are fed back to other network nodes in time. The high priority burst packets in the network nodes are set to have absolute priority. The burst packets of the network link are divided and deflected to realize the automatic control of network link congestion. The experimental results show that the model can effectively detect the current network link congestion and control the congestion degree of the network. It has better network communication data transmission effect, blocking rate, better throughput and higher control quality.

Texture feature extraction is the key to texture classification, and there are various factors such as rotation, illumination, and scale variations in texture images. To enhance the robustness of the texture feature extraction algorithm for rotation, illumination, and scale variations, the FWLMP ( Fractal Weighted Local Morphological Pattern) is proposed. First, a scale-invariant descriptor is constructed by using the relative invariance of fractal dimensionality to scale variation. Then, it is sampled and analyzed using the expansion, erosion, and opening-closing operations in mathematical morphology, and its weights are calculated by using the fractal dimension image. This algorithm is scale-invariant and robust to rotation and illumination changes. To achieve the classification of Qing Dynasty costume images, the Qing Dynasty Buzi image dataset is constructed. The FWLMP and similar algorithms are tested on four public texture datasets and a private dataset constructed by ourselves. The experimental results show that the FWLMP algorithm performs well in texture image classification and in Buzi image classification for Qing Dynasty civil and military officials. 

To protect the valuable field geological resources that have become increasingly vulnerable to natural or human damage in recent years, and to facilitate teaching reform in online virtual geological practice in the post-pandemic era, an automatic field geological section reconstruction technology based on 3D laser scanning is proposed. Using the FARO 3D laser scanner, 3D high-density point cloud data is collected from field geological outcrops of various scales. By processing, optimizing, and visually modeling the high-quality data collected from the field, this technology can protect precious field geological resources and enrich students’ virtual geological practice resources. Taking some field geological outcrops from the Longhuitou Scenic Area in Xingcheng City, Liaoning Province, as examples, virtual geological modeling and visualization applications are carried out, enhancing the quality of geological practice teaching. This approach serves the preservation of field geological legacies and significantly contributes to the advancement of geological education by providing a more interactive and enriched virtual learning environment.

A crowd counting model based on background suppression and noise monitoring is proposed to solve the problems of large-scale change of crowd, complex background, and label noise. In the coding stage, the first 13 layers of VGG16_bn are used as the backbone, and the initially extracted features are sent to the two-branch feature extraction module and the background information aggregation module respectively, to mitigate the large- scale changes of the population and improve the discriminability of the background. Finally, the information processed by the two modules is fused, and the predictive density map is generated by decoder regression, which is supervised with the ground truth density map to achieve noise suppression. Compared with other algorithms, the counting accuracy of this model has been improved. MAE(Mean Absolute Error) and MSE(Mean Squared Error) on ShanghaiTech PartA are 58. 1 and 95. 9 respectively. Ablation experiments conducted on ShanghaiTech PartA also verified the effectiveness of the modules. Experimental results show that the algorithm can effectively improve the accuracy of crowd counting. 

In order to solve the problem of poor obstacle avoidance and low efficiency of robots in obstacle environments, a wheeled industrial robot obstacle avoidance control algorithm based on neighborhood rough sets is proposed. Firstly, the environment perception method based on 2D Laser rangefinder is used to analyze the local environment of the robot and the obstacle environment, so as to provide accurate environmental information for subsequent obstacle avoidance control; Secondly, based on the initial obstacle avoidance decision rules of robots, the knowledge reduction effect of neighborhood rough sets is utilized to reduce them to the minimum obstacle avoidance decision rules, and a feasible path set is obtained; Finally, based on the feasible path set, the ND +(Nondimensional) algorithm is used to determine the direction of the robot’s obstacle avoidance decision, thereby achieving obstacle avoidance control for wheeled industrial robots. The experimental results show that this method can achieve high accuracy and control efficiency of machine obstacle avoidance control while ensuring the stability of obstacle avoidance control. 

The recognition rate of gesture recognition is low because of the poor segmentation effect. Therefore, a dynamic multi-point gesture recognition method based on improved support vector machine is proposed. The depth threshold method is used to segment the dynamic multi-point gesture image, extract the largest circular fine hand area in the palm, obtain 7-dimensional HOG(Histogram of Oriented Gradients) feature vector of the hand, complete the gesture action image preprocessing, introduce support vector machine, and improve the algorithm by error term, and adopt the optimized linear classification feature vector of the improved support vector machine. The dynamic multi-point gesture recognition is realized by using the gesture feature vector after input classification by support vector machine. The experimental results show that the recognition rate reaches more than 92. 5% under the condition of illumination, while the recognition rate is still higher than 90. 0% under the condition of no illumination. The proposed method has little fluctuation under the influence of illumination, and the image segmentation information is complete and the recognition accuracy is high.

Geomagnetic navigation utilizes geomagnetic field information for positioning and navigation. However, due to the slow changes in the geomagnetic field and small variations in the total geomagnetic field gradient, the available information is limited and lacks identification accuracy during geomagnetic matching, thereby restricting improvements in positioning accuracy. To enhance the identification accuracy of the geomagnetic field and improve positioning precision, a novel approach employing a combined artificial magnetic source is proposed. A cylindrical permanent magnet composed of rare-earth neodymium iron boron material is chosen as the magnetic source. The spatial distribution of the magnetic field is analyzed through modeling and simulation using COMSOL software to determine an optimal design scheme for the magnetic beacon. Evaluation metrics such as standard deviation, roughness, and information entropy are employed to assess enhancement in characteristics of the geomagnetic map resulting from this magnetic beacon scheme, ultimately leading to a more reasonable design that improves positioning accuracy. Experimental results demonstrate that within a specific test area, centimeter-level positioning accuracy can be achieved with this combined magnetic beacon scheme. 

Due to differences in the environment of different network channels, delay control is difficult. To solve this problem, a transmission delay consistency control algorithm based on discrete mathematics model is proposed. First, based on the discrete mathematics model, the transmission time matching function in a single channel unit is designed, and the data transmission delay is estimated to establish the transmission delay function. Then, discretization processing is adopted to obtain the limiting spectrum parameters with the greatest correlation with transmission delay parameters. Using this parameter as a reference, the conditions that the maximum allowable delay needs to meet is set, a balanced transmission amplitude response model is established based on the balanced signal-to-noise ratio, and delay consistency equalization control is implemented using adaptive equalization scheduling method. Experiments show that the transmission delay and control overhead are significantly reduced, and the network throughput is increased after the application of the algorithm.

The electricity demand of industry users is usually affected by seasonal and cyclical factors, and sometimes the data obtained is incomplete, missing, or incorrect, which can have a negative impact on the accuracy of predictions. In order to achieve accurate prediction of industry user electricity demand, a data-driven and heterogeneous computing method for predicting industry user electricity demand is proposed. The Lagrange interpolation algorithm is used to fill in the missing part of user electricity data, the standardized preprocessing of electricity data is used to make electricity demand prediction accurate enough, denoising autoencoders and sparse constraint functions are used to extract electricity data features. The long-term memory neural network’s forgetting gate layer, input gate layer, update gate layer, and output gate layer are used to obtain the future trend of electricity demand, the task of industry user electricity demand prediction is completed. The experimental results show that the proposed method is suitable for long-term and short-term industry user electricity prediction, and the prediction results have high accuracy and short time consumption. 

S-Band Polymer Waveguide Amplifier Based on Thulium Ytterbium Co-Doped Nanocrystals LIU Tingting, WANG Jiahe, ZHAO Dan, WANG Fei (College of Electronic Science and Engineering, Jilin University, Changchun 130012, China) Abstract: In order to solve the problem of insufficient communication bandwidth caused by the constantly growing network capacity, expanding the optical communication band from the main C-band (1 530 ~1 565 nm) to the S-band (1 460 ~1 530 nm) and L-band (1 565 ~1 630 nm) has become an effective way to address this issue. Tm3+can emit light at a wavelength of ~1 490 nm under pump excitation, and doping it into a waveguide can achieve S-band optical amplifier. The NaYF4 : Tm3+, Yb3+nanocrystals are introduced into polymer materials as amplifier gain media, a planar waveguide amplifier structure is designed, and the gain performance of the device is simulated in the S-band. Four waveguide amplifier samples with different Yb3+doping concentrations (x=5,10,15,20) are prepared using NaYF4 :1% Tm3+ and x% Yb3+ nanocrystals, and the device gain performance is tested. The experimental results show that when the Yb3+doping concentration is 10%, the gain of the waveguide amplifier is maximum, and the 1 cm long device achieves a relative gain of 8.2 dB at a pump power of 400 mW. The modeling and simulation of the Tm3+and Yb3+co doped system proposed in this paper provide theoretical guidance for the development of high-performance S-band waveguide amplifiers. Using NaYF4 , the polymer optical waveguide amplifier prepared by Tm3+ and Yb3+ nanocrystals has achieved S-band optical amplification and is expected to be widely used in optical communication.

In order to improve the data utilization rate and avoid the influence of risk factors in information on intelligence analysis, a risk feature screening algorithm for intelligent intelligence analysis data based on SVM (Support Vector Machine) is proposed. The continuous wavelet transform method is used to eliminate the influence of noise signals in intelligence data on the analysis results, and the projection matrix is established by combining principal component analysis method to extract the main features of various types of noise-free intelligence data. The main feature extraction results of various kinds of intelligence data are input into support vector machine, and the classification plane in support vector machine is established by using optimization theory, and the classification rules of feature data in the classification plane are defined to screen the risk features of intelligence data. The experimental results show that the proposed method can accurately classify intelligence data, and the risk data detection efficiency is high, which can realize effective screening of risk data.

At present, the need for high-quality and semantically rich data has become increasingly urgent as data-driven artificial intelligence is being applied in a wide and in-depth manner in a variety of fields. Data governance works in various fields focus on the governance of data models. However, both internationally and domestically, research on data semantic governance is still insufficient. In particular, there is a lack of systematic exploration of semantics from the underlying basic theory. Therefore, the essence of semantic organization and representation from the basic theory is revealed, and a conceptual system model of conceptual world is put forward. A nature characteristic conceptual semantic registration metamodel and a relational characteristic conceptual semantic registration metamodel is constracted based on the ISO/ IEC(International Organization for Standardization/ International Electrotechnical Commission) 11179 series of standards, achieving the registration and management of rich semantic knowledge. Finally, a metadata registration and governance system is designed and developed in the context of data governance in the field of oil and gas exploration and evaluation. The two types of semantic models based on the MDR(Metadata Registry) standard have been verified, reflecting their effectiveness in practical applications. 

Traditional methods of classroom quality evaluation mainly rely on manual observation, which suffers from low efficiency and poor accuracy. To establish a more comprehensive evaluation system, a lightweight classroom evaluation model based on an improved YOLOv5s(You Only Look Once version 5 small) is proposed. By adopting this model and the AHP(Analytic Hierarchy Process), a comprehensive classroom evaluation system is established. The model integrates the CBAM(Convolutional Block Attention Module) attention mechanism into the neck network, enhancing the model’s recognition accuracy. incorporates the Ghost module into the backbone network, significantly reducing the model’s complexity. and utilizes the Focal Loss function to effectively mitigate the problem of class imbalance. Experimental results show that, compared to the YOLOv5s model, the improved model increases average precision by 7. 3%, reduces the number of parameters by 42. 0%, decreases computation by 33. 1%, and improves detection speed by 4%. Finally, a classroom quality evaluation system is established by combining the AHP and the entropy weight method, dynamically displaying the current classroom quality score, which meets the actual needs of the classroom.

In the process of super-resolution processing, the noise inherent in low resolution images will be amplified, resulting in distortion of super-resolution images. To this end, a super-resolution image noise recognition method based on neural networks has been proposed. The Activation function in the neural network is used to determine the peak signal to noise ratio. By combining the noise data set and hyperparameter coefficients, residual values are obtained, and combined with the noise information distribution density, super- resolution image noise recognition is achieved. The experimental results show that the proposed method has high clarity and good recognition performance in super-resolution images, with a maximum peak signal-to-noise ratio of 50 dB, indicating that the use of the proposed method can improve image quality.

The current challenges in deep learning for 3D reconstruction are difficulty in extracting comprehensive scene information from images and insufficient consideration of depth consistency between views. A multi-view stereo network with adaptive depth consistency and cross-frequency attention (ADCFA-MVSNet: Multi-View Stereo with Adaptive Depth Consistency and Cross-Frequency Attention) is proposed. The CFA (Cross-Frequency Attention) module integrates high-frequency, low-frequency information within images and global scene information across views, enabling more comprehensive feature extraction. The AD(Adaptive Depth) consistency module precisely captures the geometric structure of the scene and dynamically considers the contribution of different views to depth consistency, enhancing it across various scales. The innovation of this method lies in utilizing comprehensive image information to ensure geometric consistency, achieving excellent performance in 3D reconstruction tasks. On the DTU(Technical University of Denmark) dataset, it achievs an accuracy of 0. 319, completeness of 0.285, and an overall score of 0.302, surpassing other methods. On the BlendedMVS dataset, the EPE(End-Point-Error) score is 0.27, e1 score is 5.28, and e3 score is 1.84, outperforming other methods. These results demonstrate the effectiveness of ADCFA-MVSNet in improving the completeness and accuracy of multi-view 3D reconstruction. Experimental results show that this method enhances the quality of multi-view reconstruction and achieves good reconstruction effects.

Intelligent vehicle is a strategic focus of the global automotive industry. To meet new demands for experimental teaching in this field, we designed and constructed a camera-injection experimental platform. First, a virtual-physical integration scheme is implemented by combining simulation environments with an in-vehicle domain controller to define the overall architecture. Second, a camera simulation model is developed and virtually calibrated , on which a data link is built using GMSL2(Gigabit Multimedia Serial Link 2) and CSI-2 (Camera Serial Interface 2) protocols to enable seamless interaction between simulated video streams and controller hardware. Next, we quantized offline-trained deep-learning models, converted them into a universal format, and deployed them on the domain controller for real-time interaction with the virtual environment. Finally, this platform is used to provide students with an integrated theory-and-practice learning environment, deepening their understanding of camera principles and mastery of multi-channel video signal generation, transmission, and perception. This system effectively enhances students‘ practical skills and innovation capacity in intelligent vehicle technology.

In order to solve the problem that the accuracy of deep neural network model learning is affected by the small sample of rice disease image dataset, an improved adversarial generative network model ViT-WGAN-GP (The Fusion of Vision Transformer and Wasserstein Generative Adversarial Networks with Gradient Penalty) is proposed for enhancing the image dataset. Firstly, the Vision Transformer structure is introduced in the generation model to enhance the learning of global features. Secondly, the WGAN-GP structure is used in the discrimination model to ensure the stability of the model training and improved the effect of the generated images through the Wasserstein measure function and the gradient penalty term. Finally, the enhanced sample set is used to train the deep neural network model. The experimental results show that the ViT-WGAN-GP model generates images with significant improvement compared with GAN and WGAN-GP. The average accuracy of rice disease recognition is 94. 3%,96. 2%, and 97. 5% for VGG16, ResNet34, which are improved by 9. 7%, 2. 8%, and 4.8%, respectively. The proposed ViT-WGAN-GP model can generate more realistic rice disease images and can improve the recognition accuracy of deep neural network models significantly with small sample sets.

 Financial announcement is the carrier for enterprises to publicly inform the society of major financial events, and its information is of great significance to financial practitioners. However, financial events have the characteristics of strong argument specialization and high dispersion, and traditional event extraction methods are difficult to achieve accurate extraction. Therefore an event extraction method combining the local features of paragraphs and the global features of documents is proposed. This method first segments the financial announcement document, and then uses all the paragraphs in parallel Fin-BERT(Financial Bidirectional Encoder Representation from Transformers ) Pre training model, convolutional neural network and self attention mechanism to obtain local features of documents. Then Bi LSTM(Bi directional Long Short Term Memory) is used to learn the semantic information of the whole document to obtain the global features of the document. Finally, the local features of the paragraph and the global features of the document are fused to output event arguments and event types. A series of experiments are carried out on the financial open data set chfinann. The experimental results show that the method achieves an average F1 value of 80. 2%, which is better than the baseline model, and proves the effectiveness of the method. 

An improved scorpion-simulated method for estimating the position of a vibration source is proposed, to address the issue of limited positioning accuracy due to incomplete scorpion-simulated vibration source positioning models. Based on the different attenuation rates of vibration signal frequency components with increasing distance, the method first improves the existing scorpion vibration source positioning mechanism to address the lack of distance estimation in current models. Then, it extracts the features of the vibration source location based on the improved model and constructs a complete feature database. Next, the K-means method is used to create sub-databases to reduce data matching time. Finally, the KNN(K-Nearest Neighbor)algorithm is used to estimate the position of the vibration source. To verify the effectiveness of the proposed method, tests are conducted on a dataset containing 64 locations of personnel stepping signals in a concentric circle with an inner radius of 2 m and an outer radius of 6 m. The results show that the improved method for simulating scorpion vibration source positioning increases the average positioning accuracy by 0. 439 6 m compared to the existing method and improves the positioning time by 31. 34% compared to the original matching method. Therefore, the improved method has achieved significant enhancements in both positioning accuracy and efficiency.

 Deep neural network techniques based on supervised learning have been extensively employed in the field of welding. However, in real industrial scenarios, obtaining labeled data samples is challenging, which limits the performance of deep network models. For unlabeled or partially labeled datasets, transfer learning algorithms offer a novel solution. Transfer learning algorithms in terms of domain adaptation and pre-training-fine- tuning are introduced and a summary of current research on their development over recent years and their applications in weld penetration identification and defect detection is provided. And transfer learning issues in welding that require further attention and exploration in the futureis highlighted. Transfer learning methods can enhance the effectiveness of deep learning models by better utilizing existing data and knowledge in the welding field, specifically in weld penetration recognition and welding defect detection accuracy. This promotes the development of intelligent welding manufacturing technology. 

When there is a large amount of text data, it is necessary to extract effective features from the text data to capture important information of the text to facilitate the storage and querying of the text. Therefore a machine learning based text classification and label prediction algorithm research is proposed. Conditional random field method is used to annotate and segment the part of speech of the processed text, and obtain the features of the texrt. Text features are inputted into a self attention mechanism recurrent convolutional neural network, and after model training, the classification results and label prediction results of the text outputted. After experimental verification, the proposed algorithm can effectively complete text classification and label prediction, with an average false rate of 95. 2% in text classification and an average loss of 0. 4% in text prediction ranking.

In community emergency management during scenarios such as pandemic disasters, traditional methods can not quickly and accurately capture community dynamics. Therefore, an intelligent perception system combining MLLMs(Multimodal Large Language Models) and YOLOv8(You Only Look Once version 8) is proposed. The system comprehensively analyzes textual data from social media and community video surveillance streams to identify changes in community public service needs in real-time. Experimental results demonstrate high accuracy and responsiveness in demand recognition and anomaly detection. This enhances the responsiveness of public services in emergency management and provides strong technical support for smart city development.

In order to improve the real-time performance and security of the traditional A* algorithm during path planning, a path planning method incorporating improved A* and DWA(Dynamic Window Approach) is proposed. Firstly, the search neighborhood of the A* algorithm is optimized to reduce the search direction of nodes. Secondly, the search mechanism is optimized by introducing bidirectional search and dynamically defining the target node strategy to carry out bidirectional path searching from the start node and the target node. Dynamic weighting coefficients are introduced to reduce the generation of redundant nodes in the process of path searching, and the paths are smoothed by the Bezier curves. And lastly, the improved A* algorithm is fused with the DWA algorithm to realize dynamic obstacle avoidance. Simulation is carried out using PyCharm, and the results show that, compared with the other two algorithms, the search nodes of the improved A* algorithm are reduced by more than 46.25%, and the search time is reduced by more than 24.06%. The integrated algorithm is able to realize dynamic obstacle avoidance, and the smoothness and safety of the planned paths have been improved.

 The environmental factors such as temperature, humidity, and air quality in the office area of power enterprises have dynamic changes and complex relationships with each other. The impact of these factors on energy consumption is difficult to accurately quantify, which increases the complexity of control algorithms. Therefore, an energy-saving power control algorithm for office energy consumption in power enterprises under the dual carbon background is proposed. Using environmental sensors to deploy sensor networks, collecting information data from office environments, and establishing a linear relationship between environmental factors and energy consumption and using regression models to quantify the impact of environmental factors on energy consumption. Based on the linear relationship between environmental factors and energy consumption, the power loss and annual electricity consumption of energy consuming equipment in the office environment are calculated, and the energy consumption changes of the enterprise‘s office during a specific period in the future are predicted. By setting the connection instructions between sensors and energy consumption data with the control center, a device energy consumption regulation constraint model is constructed, and an energy-saving control function is designed based on the energy consumption intensity and modulation power of the device, thereby achieving office  energy consumption energy-saving power control. The experimental results show that under the application of research methods, the energy-saving rate and emission reduction of the office environment in power enterprises are as high as 35% and 35 tons respectively, with good energy-saving and emission reduction effects, which can meet the requirements of the dual carbon target. 

The network nodes are fragile, with many potential attack behaviors and redundant intersection situations, resulting in poor feature recognition accuracy and classification performance and low monitoring stability and efficiency. Therefore, a network potential attack monitoring based on fuzzy Markov game algorithm was studied. Using the fusion degree compressed sensing method and the feature recognition degree parameter analysis method, the random discrete distribution sequence of network potential attack characteristics is analyzed, the characteristics of network potential attack spectrum is also extracted and analyzed. The random forest algorithm is adopted to distinguish the types of potential network attacks, and the fuzzy Markov game analysis of potential network attack risk is carried out. According to the risk state set and the principle of minimum and maximum, the potential network attack risk is monitored. The test results of the example show that after the proposed method is applied, potential attack behavior parameters are set, and the fluctuation of potential attack recognition rate is small. The fuzzy Markov game analysis results are closest to the actual risk value, and have high recognition accuracy, monitoring efficiency, and monitoring stability. 

Aiming at the problem of low accuracy of methods in Chinese word segmentation in professional domains due to the mismatch of cross-domain data distribution and the limitation of a large number of unregistered professional words, a professional domain word segmentation method based on XLBMC(XLNet- BiGRU-Multi-head Self-attention-Conditional Random Field) is proposed. Firs, the dynamic word vectors containing contextual semantic information is generated through an improved XLNet pre-training model, enabling the model to better utilize the boundary and semantic knowledge. Then the acquired word vectors are input into BiGRU for feature extraction to obtain the hidden state representation of each character. On the basis of BiGRU coding, a sparsified MHSA(Multi-head Self-Attention) mechanism is introduced to weight the representation of each character, which improves the prediction accuracy of the model for fine-grained and strongly long-term dependent time series under restricted memory budget. Finally, the CRF(Conditional Random Field) decodes the dependencies between neighboring tags and outputs the optimal segmentation sequence. Segmentation experiments are conducted on a self鄄constructed control engineering corpus. The results show that the accuracy of the proposed segmentation model is 94. 27%, the recall is 93. 24%, and the F1 value is 95.52%, which proves the reliability of the model in Chinese segmentation tasks in the professional domain.

In order to improve the accuracy and convenience of obtaining medical information for patients with chronic diseases, a chronic disease health knowledge Q&A(Question and Answer) system based on knowledge graph and WeChat mini program has been developed. The system includes question and answer library, server- side, and client-side. The question and answer library is built based on knowledge graph, text generation and matching technology, and the server-side is written in Python language, using WeChat mini program as the client. In terms of functionality, the system is capable of intelligent question answering, health data recording, health tweets, and knowledge base updates for disease knowledge. The application results indicate that the system can effectively complete the health knowledge question and answer task for chronic patients.

Due to the fact that resource filtering and deduplication are essential steps in ensuring the efficient operation of digital libraries, the process is susceptible to interference from redundant data, resource types, and differences in customer groups. Therefore, a digital information resource filtering and deduplication method based on GRNN algorithm is proposed. Firstly, the GRNN(General Regression Neural Network) algorithm is used to detect outliers in digital information resources, and the outliers are filtered through PSO-LSSVM(Purticle Swarm Optimization-Least Squares Support Vector Machine) to avoid interference from outlier data in the deduplication process. Then, a locally sensitive hash algorithm is used to convert the resource data into binary hash codes, and the filtering and deduplication of digital information resources are completed by detecting the Hamming distance similarity between hash codes. The experimental results show that this method takes short time and has high precision and rate of deduplication.

To tackle the inefficiencies, high miss-detection rates, and poor mobility of conventional security check methods in identifying contraband hidden on vehicle undercarriage surfaces, a cloud-based mobile intelligent underbody concealment detection system has been devised. This system uses robotics, network communication, image processing, and object recognition technologies to enable intelligent inspection. Employing the SIFT(Scale-Invariant Feature Transform) algorithm for feature information extraction from images, the system attains a panoramic view of the vehicle underside. Four categories of undercarriage concealments are detected using the YOLOv5(You Only Look Once version 5) deep neural network model. A cloud database is constructed to archive vehicle data, with TCP/ IP(Transmission Control Protocol/ Internet Protocol) protocol facilitating seamless interactions among the wheeled robot, the supervisory computer, and the cloud database. Preliminary testing confirms the system’s capability to conduct underbody concealment inspections within designated contexts, achieving 76.7% success rate in image stitching and 87.2% precision in target detection. Hence, it has considerable practical value for vehicle underbody security check applications.

 Aspect-level sentiment analysis is a prominent research task in the field of natural language processing. Aiming to analyze the sentiment tendencies of different aspects of texts, to address the issues of insufficient interaction between aspect words and context, and to deal with low classification accuracy of existing aspect-level sentiment classification models, an ASMFF(Aspect-level Sentiment classification method is proposed based on Multi-interaction Feature Fusion). Firstly, the context and aspect words are distinctly labeled and fed into the BERT(Bidirectional Encoder Representations from Transformers) coding layer for text feature vector extraction. Secondly, the text feature vectors are fed into AOA (Attention Over Attention) and IAN (Interactive Attention Networks) networks to extract the interactive attention feature vectors. Finally, the two interactive feature vectors obtained are fused and learned, and probability calculation, loss back propagation, and parameter updating are carried out using the cross-entropy loss function. Experimental results on three publicly available datasets, Laptop, Restaurant, and Twitter, show that the classification accuracy of the ASMFF model is 80. 25%,84.38%, and 75.29%, respectively, which is a significant improvement over the baseline model. 

The leakage of well site pumping units is an important issue that affects the safety production and stable operation of oil fields. The current object detection methods often overlook the special requirements of well site leakage detection, and there are some limitations in the process of feature recognition of well site leakage targets. An attention mechanism leak detection algorithm for small targets in well sites is proposed based on the YOLOv5(You Only Look Once 5) network, introducing channels and spatiotemporal attention modules into the backbone network, to obtain more feature discrimination information, to enhance the model’s attention to important features. An additional small object detection scale has been introduced in the backbone network, which enables the network to integrate more feature information of small target objects and enhance the detection ability of small targets. The effectiveness of the proposed algorithm is validated on a dataset of well site leaks. The experimental results showed that compared to similar algorithms, the proposed method has higher recognition accuracy and can provide reference for the practical application of automatic detection of oil field well site leaks. 

To address the issue of hesitation degree redistribution in similarity measurement of intuitionistic fuzzy sets, researchers typically rely on fixed formulas yielding constant results, which deviate from practical situations. To resolve this, a novel similarity measurement method for intuitionistic fuzzy sets is proposed. This method innovatively introduces a random function to perform fine-grained redistribution of hesitation degrees into membership and non-membership degrees, while preserving the remaining hesitation degree. This approach significantly enhances the discrimination ability and computational efficiency of the measurement while maintaining information integrity, fulfilling the core requirements of similarity measurement. Furthermore, the possible value range of the similarity between two intuitionistic fuzzy numbers is thoroughly discussed, enhancing the applicability of the similarity measure. The application of this method in the selection of cutting slope schemes verifies its rationality, practicality, and innovation, demonstrating promising application prospects.

To address the problem of low accuracy of oil and gas pipeline leakage identification, the digital twintechnology is introduced, and a digital twin pipeline leakage identification model is constructed based onarithmetic optimisation AOA-SVM(Arithmetic Optimization Algorithm-Support Vector Machine). Firstly, the 3DROM(3D Reduced Order Model) pipeline model of oil and gas pipelines is constructed using Ansys software.Secondly, the collected pipeline signals are imported into MySql database through Java interface, and then thedata are imported into the 3D ROM pipeline model. Finally, the AOA-SVM algorithm is used to carry out the work recognition of the pipeline signals in Matlab environment, and the recognition effect is shown in its dynamic form by Twin builder software. The recognition effect is shown in its dynamic form. In order to show the superiority of AOA-SVM condition recognition ability, it is compared with other popular SVM( Support Vector Machine) optimisation algorithms on the basis of the same signal. The comparison results show that AOA-SVM has the highest classification accuracy, which can reach 90. 5% , i. e. , the recognition model of the proposed digital twin can simulate the leakage of pipelines and has a high monitoring credibility.

Since network simulation consumes a lot of system resources and has complex parameter configuration, these factors will affect the test accuracy when performing network testing. Therefore, a lightweight network simulation method based on Linux namespace is designed. Based on Linux kernel virtualization technology, a simulation network is built. In order to solve the problem of complex parameter configuration caused by dynamic adjustment of topology during network testing and high resource consumption when running network simulation system, human-readable data serialization standard file is used to flexibly define the network, and completes the virtual network creation by calling system commands in user state with the help of Linux network namespace mechanism. An automated script is written to perform network testing using iperf3 tool. Experimental results show that the network throughput of the proposed method is close to the test theoretical bandwidth, the system shows high startup efficiency and low running resource overhead, can meet common network testing application scenarios, has good performance, and has certain research value.

Drug information data has the characteristic of imbalanced categories, with poor interpretability and a large number of sensitive data. The application effect and mining accuracy of sensitive data are low. Therefore, an improved Apriori based sensitive data mining algorithm for drug information is proposed. The drug data is decomposed into several band limited intrinsic mode functions, and is updated and denoised, the feature subset of the sensitive data is extracted according to the information gain of the feature subset of the drug sensitive data and the Monte Carlo sampling strategy. The relationship between the hidden layer output function and the feature subset is analyzed. The extreme learning machine is introduced to improve the Apriori algorithm. And the drug combinations with significant relevance are screened out and solved. The sensitive data features are matched corresponding to the candidate feature subset and a sensitive data mining function is constructed. The experimental results show that the data signal fluctuation amplitude is small, and sensitive data can be clearly distinguished. The number of erroneous data mined does not exceed 2, improving the interpretability of sensitive data.

In order to solve the problem that the Internet of Vehicles with limited computing power can not undertake a large number of real-time task computing, offloads vehicle tasks are introduced to the edge server for computing through MEC (Mobile Edge Computing), and a joint optimization scheme for the delay and energy consumption of vehicle task offloading is proposed based on the I-GWO( Improved Grey Wolf Optimizer). A computation offloading model constrained by computation delay, energy consumption, and edge server computing resources is established, and an offloading optimization problem with the goal of minimizing the total system consumption is proposed. By improving the GWO (Grey Wolf Optimizer ), the I-GWO used to solve optimization problem. Simulation results show that the proposed scheme can effectively reduce the total system consumption, and the convergence performance of I-GWO is greatly improved compared to GWO.

The original user side net load sequence of the power system is chaotic. In order to accurately predict the changes in user side load data of the power system, a heterogeneous computing based user side net load prediction algorithm is proposed. The user side net load data of the power system is analyzed with noise, the binary wavelet transform is expanded, and the user side net load data of the power system is preprocessed by setting threshold values and determining estimated signals. The empirical mode decomposition method is applied to decompose the user side net load of the power system. Two different algorithms, EKF(Extended Kalman Filter) and KELM(Kernel Extreme Learning Machine) are used to establish a power system user side net load prediction function based on EKF-KELM. The optimal parameters for IMF(Intrinsic Mode Function) components are calculated isomerically, and a kernel function is introduced to overlay all predicted values. The user side net load prediction results of the power system are obtained under heterogeneous computing. The experimental results show that the predicted value of the power system user side net load obtained by the proposed algorithm is basically consistent with the true value, with low root mean square error and average absolute error. This effectively reduces the time required for power system user side net load prediction and can obtain high-precision power system user side net load prediction results. 

In order to solve the problem of “peak-on-peak” load in distribution networks caused by the superposition of EV ( Electric Vehicle) users’ base load and unordered EV charging load in residential communities, the following solution is proposed Firstly, based on cloud-edge collaboration theory and big data technology, a cloud-edge collaborative optimization scheduling framework is established for comprehensive interconnection of distribution networks, charging station operators, intelligent charging piles, and EV user information. Secondly, an EV user charging scheduling mechanism considering the minimum profit or maximum cost acceptable to users is proposed. Then, a two-layer multi-objective orderly charge and discharge optimization regulation model is established from the perspectives of both the grid side and the user side. Finally, taking EV load data in residential areas as an example, the COA(Coati Optimization Algorithm) is proposed to solve the model. The simulation results verify the effectiveness and superiority of the proposed model and method. It can achieve better peak cutting and valley filling, and improve the user’s charging experience. 

When detecting false data injection attacks, if the detection accuracy of the detection model is poor, it will directly affect the detection effect of false data injection attacks. In order to effectively improve the detection accuracy of the detection model, the incremental detection of false data injection attacks based on the grey wolf algorithm is proposed to optimize the kernel extreme learning machine. The state of power system is estimated, and the attack behavior of false data injection is analyzed. On this basis, an incremental detection model of false data injection attack is established based on kernel extreme learning machine, and the model is optimized by grey wolf algorithm. Finally, the normalized results of the collected power system state data are used as the model input data, and the accurate detection of false data injection attacks in power system under incremental changes is realized through the optimized model. The experimental results show that using this method to detect false data injection attacks can get better detection effect and high precision results.

Aiming at the problem that most of the existing pumping unit fault diagnosis is based on indicator diagram, which leads to a relatively single diagnostic modality, a ShuffleNetV2ECA-MLP (ShuffleNetV2 with Efficient Channel Attention and Multilayer Perceptron, ShuffleNetV2ECA-MLP) multimodal decision fusion fault diagnosis model is proposed for pumping units. In order to improve the cross-channel interaction capability and recognition accuracy of the ShuffleNetV2 model, firstly, the ECA(Efficient Channel Attention) module with lightweight channel attention is introduced into the ShuffleNetV2 model, and the Hardswish activation function is applied to enhance the network蒺s ability to learn complex problems. Secondly, the improved ShuffleNetV2 network is used to diagnose the figure of merit, and the MLP(Multi-Layer Perceptron) network is used to process the production dynamic data. Finally, the diagnostic results of the two models are integrated using the weighted voting method. In order to verify the effectiveness of the improved ShuffleNetV2 and ShuffleNetV2ECA-MLP models, comparisons are made with the lightweight convolutional networks MobileNetV2, MobileNetV3, the classical convolutional network ResNet, and the VGG ( Visual Geometry Group) network model. The experimental results show that the storage space of the ShuffleNetV2ECA-MLPmodel is only 10. 16 MByte, and the fault diagnosis accuracy reaches 95. 35% , which better meets the needs of pumping unit fault diagnosis.

n response to the issue that photovoltaic energy storage charging stations have high operating cost and load fluctuations in the distribution grid caused by the shortcomings of the operating strategy, a multi-timescale optimal scheduling strategy based on time-varying boundary constraints for photovoltaic energy storage charging stations is proposed. Firstly, the goal is to minimize the daily operating cost, and the electric vehicle charging load and photovoltaic generation power intervals are predicted. Next, is to minimize the mean square deviation of load fluctuation on the distribution network. Constraints with time-varying boundaries are constructed based on the boundaries of the predicted intervals, grid feed-in pricing of photovoltaic and time-of-use pricing. Finally, setting multiple scenarios and utilizing the CPLEX solver in Matlab for optimization, The simulation results reveal that the scheduling strategy reduces daily operational costs and decreases the mean square deviation of load fluctuation.

In order to solve the energy limitation problem of oil and gas IoT, energy harvesting technology is introduced and an energy management algorithm for oil and gas IoT is proposed based on the data importance level. The working mode of sensor nodes is changed according to the energy threshold, and whether to transmit data is based on the importance level of data under the energy constrained situation to avoid the delay of important data. The algorithm selects cluster heads based on the ratio of energy harvesting and energy consumption of nodes, and the remaining energy of nodes, so as to achieve the purpose of extending the network lifetime while ensuring the transmission of important data. 

The accuracy of the existing estimation methods of human pose in the motion evaluation scene needs to be further improved. The methods rely on high-performance computing devices, and the reasoning speed on edge computing devices needs to be further enhanced. Therefore, improvement is made to the classic high-resolution network model to solve the problem of low real-time performance of the existing human pose estimation methods. To address the frequent occlusion issues in motion evaluation scene, random erasure enhancement is applied to the images in the dataset. After experimental comparison and verification, the improved method significantly reduces the number of model parameters and improves the inference speed of the model while ensuring the accuracy of attitude estimation. The algorithm exhibits stronger robustness for occlusion problems, and the improved method can meet the needs of motion evaluation scenarios.

Due to the complexity of multi tenant and multi-level security requirements in cloud computing environments, existing access control strategies are difficult to meet the needs of different users and applications, resulting in lower resource access security and more time consumption during encryption and decryption. To address the above issues, combining CP-ABE(Ciphertext Policy-Attribute Based Encryption) with asymmetric encryption RSA(Rivest Shamir Adleman) research on hierarchical access control of cloud computing resources is conducted. A CP-ABE access control architecture is established and encrypted access policies are developed. The trust values related to hierarchical access of cloud computing resources is used to clarify the trust relationship of access, and the trust degree of access subject and object resources are obtainined. Based on the calculated trust value, users are granted hierarchical authorization to meet the needs of multi tenant and multi-level security. Based on the results of user identity hierarchical authorization, the RSA algorithm is used to replace the complex bilinear mapping of CP-ABE for encryption and decryption, achieving precise control of resourcehierarchical access and reducing encryption and decryption time consumption. Through experimental testing, it was found that the proposed method can achieve a concurrent connection count of 400, a maximum over authorization rate of 6. 8% for hierarchical access, and an effective control of access control response time of less than 6 seconds, which can effectively meet the multi tenant and multi-level security needs of application scenarios. It has a good effect on hierarchical access control of cloud computing resources. 

To address the issue of catastrophic forgetting in decision-making for autonomous driving in multi-city scenarios, a framework based on continual reinforcement learning is proposed. This framework is built upon the IMPALA( Importance Weighted Actor-Learner Architecture) algorithm architecture. First, a co-attentive awareness module is combined to extract critical environmental representations through cross-scenario feature interaction. Second, a self-activating neural ensemble architecture is built to enable autonomous activation of knowledge modules. Finally, a replay mechanism is applied to relieve the problem of forgetting old knowledge by combining scenario-specific features with historical trajectory experience replay. Off-policy behavior cloning and on-policy learning are employed concurrently to maintain the plasticity and stability of the decision-making algorithm. Whether to use old modules or generate new ones is determined based on the requirements of different autonomous driving scenarios and tasks, and the issue of excessive memory usage is addressed through module fusion. Ablation experiments and comparative ones are conducted in two different groups of multiple city scenarios. The performance of the proposed method is validated by comparing path completion rates and cumulative rewards. Experimental results demonstrate that the average completion rate reaches approximately 85% in the first sequential scenario, and it reaches 81. 93% in the second sequential scenario. The proposed scheme can effectively relieve the issue of catastrophic forgetting in multi-scenario continual decision-making and achieve better stable driving performance. 

In order to improve the accuracy of video anomaly detection in complex scenes, a video anomaly detection framework based on improved GAN(Generative Adversarial Network) is proposed. Two discriminators are used for the adversarial training of the generator, and the bidirectional prediction consistency is enhanced through a regression loss function. FusionNet and LSTM(Long Short Term Memory) are combined to form a generator structure based on spatio-temporal feature fusion. Forward and backward video sequences are taken as the inputs of the generator, and predicted video frames and predicted video sequences are output respectively. Patch GAN architecture is adopted for both of the discriminators, the frame discriminator is used to distinguish synthetic frames and the sequence discriminator is used to determine whether the frame sequence contains at least one synthetic frame to maintain temporal consistency of the predicted frames, to improve the robustness and accuracy of the predicted network. Finally, the anomaly score is calculated based on the normalized mean PNSR (Peak Signal to Noise Ratio). Experimental results show that the proposed framework can effectively capture the bidirectional spatio-temporal features in video sequences and outperforms other state-of-the-art methods on thechallenging public video anomaly detection datasets UCF-Crime ( University of Central Florida Crime) and ShanghaiTech.

A real-time image feature tracking algorithm based on visual communication effect is proposed to address the issues of low extraction accuracy and poor tracking performance in real-time tracking of multi frame film and television images. By calculating the likelihood function of candidate target states, effective targets in multiple film and television images are obtained, and unnecessary information such as noise and artifacts in the images are removed through visual communication enhancement processing to improve the recognizability of effective targets. Considering the real-time tracking requirements of multi frame film and television images, after multi frame film and television image enhancement, particle swarm optimization algorithm is used to weight the features of multi frame film and television images, improve the weight of salient features, effectively highlight the tracking target, and achieve real-time tracking of multi frame film and television image features. The experimental results show that after processing with the proposed method, the signal-to-noise ratio of the image can reach 45 dB, and the position of the tracked target is relatively consistent with the original marked position. And the target recognition rate, recall rate, and comprehensive evaluation index are all maintained above 0. 9. It is demoustrated that the proposed method can filter out the interference of target image background and surrounding clutter, accurately obtain target feature points, and achieve real-time feature tracking of multiple film and television images. 

A new method for accurately identifying key information in financial bill images under the interference of stains is proposed to solve the problem of recognition failure caused by local information loss or misjudgment during the recognition of financial bill information containing stains. By integrating the gray scale and denoising of the image, dividing the bill area according to the threshold size, binary processing is achieved. Using the ROI (Region of Interest) principle, rough screening of information range is performed in the binary processed image to calculate the maximum coverage contour and key information adhesion area. Further segmentation and edge calibration are performed, and key information areas are located based on the ROI ratio. The features of key information areas is extracted, classification labels in an end-to-end manner are established by combining the features, and the recognition target is searched according to the label gradient in the coverage recognition area. The experimental results show that the retrieval rate obtained by the proposed method is between 80%-100%, and the efficiency is greatly improved with superior and reliable performance. 

Images in complex backgrounds may contain a large amount of interference information, making it difficult to accurately extract image feature vectors. Therefore, a salient target recognition algorithm for wireless sensor network images in complex backgrounds is proposed. Mean shift algorithm is used to cluster targets and achieve image segmentation, obtaining several segmented image feature vectors. By fusing rules, the pyramid shapes of each layer in the image pyramid are prosessed, and the image pyramid sequence is combined to achieve image reconstruction. The image saliency of pixels is determined based on the results of image reconstruction and histogram statistics, and image saliency target recognition is achieved through pixel order expansion and sorting. The experimental results show that the proposed algorithm can accurately identify salient targets in wireless sensor network images under complex backgrounds, and the texture details of the image are clear, with good practical application effects. 

Aiming at the problems of insufficient stability, weak generalization ability, and the influence of equipment configuration in the traditional scheduling method for the detection and scheduling of power metering equipment, a detection and scheduling model named GNN-RL(Graph Neural Network-Reinforcement Learning) is proposed. The model treats the scheduling problem as a Markov decision process. Firstly, the graph structure model of electric energy metering equipment detection and scheduling is constructed. Then, the problem features are extracted through the improved graph neural network and passed to the action selection network to generate decisions. After the scheduling, the model collects feedback information to train the scheduling policy in the reinforcement learning module. In the training phase, GNN-RL optimizes the message passing mechanism, employs a loss function closely related to the scheduling objective, and dynamically adjusts the learning rate. A multi-task learning framework is introduced to deal with task allocation and time scheduling. The experimental results show that GNN-RL has obvious advantages in optimization ability, solution accuracy, and stability, and has great advantages in solving the detection and scheduling problem of energy metering equipment, which significantly improves the efficiency and reliability of problem solving.

Multi source heterogeneous data may contain sensitive and personal privacy information, increasing the risk of data leakage. Therefore, a multi-source heterogeneous data security aggregation algorithm based on kernel extreme learning machine is designed. Partial least squares algorithm is used to extract features from multi-source heterogeneous data, the extreme learning machine is optimized by introducing kernel functions, and the obtained data features inputtied into the kernel extreme learning machine to complete data aggregation by class. Elliptic curve encryption algorithm is used to encrypt the aggregated data, improving data security and achieving the goal of secure aggregation of multi-source heterogeneous data. The experimental results show that the algorithm has high accuracy in multi-source heterogeneous data aggregation and good data encryption performance, and can be widely applied in practice. 

Data may be tampered with by illegal elements during storage, leading to security issues such as data leakage and damage. In order to ensure the security of data and further improve the anti tampering ability of cloud data, an anti tampering storage algorithm for multi blockchain cloud data is proposed. By analyzing the structure of multi blockchain networks, a cloud data distributed storage architecture based on blockchain technology is designed. A cloud data access control model is designed through the data layer, application interaction layer, contract layer, and functional layer to improve the security of distributed cloud data storage. During the data encryption and decryption process, Hash algorithm and asymmetric encryption algorithm are combined to encrypt and decrypt the combined data of “random number+cloud data冶, to avoid the phenomenon of node private key leakage, cloud data being replaced and forged. The experimental results show that the encryption and decryption processing time of the proposed algorithm is maintained within 25 ms, the probability of successful attack is less than 40%, and the data is not easily tampered with during transmission.

In response to the demand for real-time and accurate tracking of multiple surgical instruments in collaborative operations, this study aims to solve the problem of invisible instrument ends caused by light filtering and shielding based on a near-infrared active optical tracking system, and achieve accurate identification and stable tracking of multiple surgical instruments. The problem of surgical instrument tracking based on a near- infrared optical positioning system is explored. In response to the limitations of traditional algorithms in multi- instrument recognition and landmark tracking, a multi-instrument recognition method based on point set matching is proposed. By matching the landmark points in the captured image with the pre-established instrument model, accurate identification and differentiation of multiple surgical instruments are achieved. And a landmark tracking method based on least squares algorithm prediction is proposed. The historical tracking data and the least squares method are used to predict the location of the landmark points, thereby achieving real-time tracking of surgical instruments. Experimental verification shows that the coordinated use of the two methods can achieve accurate identification (first-frame recognition rate 100% ) and stable tracking (overall recognition rate 97. 45%) of multiple surgical instruments, while ensuring tracking accuracy and meeting the real-time requirements of surgery. It can provide surgeons with clear instrument spatial position information and support precise operations. It is of great significance to improving surgical safety and reliability, and can provide technical support for the clinical application of near-infrared optical surgical navigation systems.

Aiming at the nonlinear problem of SMC (Sliding Mode Control) of PMSM (Permanent Magnet Synchronous Motor), on the basis of analyzing the weak connection between the parameters of the sliding mode control at different stages, a fuzzy parameter tuning strategy is proposed to reduce overshoot, chattering and having certain anti-jamming ability. The major functions of various parameters and the relationship between parameters in the process of sliding mode motor control are improved. The fuzzy logic control is combined with the exponential reaching law. The change of sliding mode parameters is adjusted by fuzzy control, and the fuzzy reaching law is derived. The design method simplifies the complexity of sliding mode parameter adjustment and eliminates the constant speed term of exponential approach rate, making the design and regulation more convenient. The conclusions show that compared with the traditional sliding mode control of permanent magnet synchronous motor, the speed loop controller designed by making fuzzy control to adjust the sliding mode parameters can further reduce the overshoot by 21. 86%, reduce the start-up time by 0.038 s, effectively eliminate the buffeting peak wave when reducing the buffeting, and reduce the speed drop by 7. 31% when dealing with the sudden change of load. The adjustment time is reduced by 0. 010 s. The reliability and superiority of the parameters are verified. 

With the continuous integration of large-scale distributed power sources into distribution networks, distribution networks face many challenges in terms of safety, stability and economy. And the existing deep reinforcement learning methods often exhibit limitations in generalization ability when training agents to cope with changing operating conditions due to insufficient generalization of collected data. Therefore a distribution network regional voltage optimization control strategy based on large language model-assisted deep reinforcement learning is proposed, combining large language model technology with deep reinforcement learning. Secondly, by guiding large language models to generate customized datasets for deep reinforcement learning agent training through prompt engineering, a multi-agent collaborative decision-making framework is constructed. Then, based on distributed partially observable Markov processes, dynamic control problems are modeled to reduce dependence on real-world data while improving agent generalization ability. Finally, the effectiveness of the proposed control strategy is verified on the improved IEEE 33-node system, with voltage deviation and network loss reduced by 60. 82% and 49.91%, respectively, exhibiting strong robustness under various operating conditions.

To improve the efficiency and accuracy of the helmet wearing detection model, the LFE-Y8 (LightConv, Focal Loss and EMA Attention You Only Look Once version 8) model is proposed. This model adopts the Focal Loss function to solve the problem of imbalanced sample categories. The original model is optimized using LightConv lightweight convolution, which improves the feature extraction ability. In order to better focus on small targets, an efficient multi-scale EMA (Efficient Multi Scale Attention) attention mechanism for cross spatial learning is integrated. The experimental results show that the LFE-Y8 model effectively improves the accuracy of helmet wearing detection compared to the improved YOLOv8 model. The improved algorithm has an accuracy increase of 0. 6% and a recall increase of 2. 1%. The mAP@ 50 is improved by 1.2%, and mAP@ 50-95 is improved by 1.5%, demonstrating the effectiveness of the LFE-Y8 model in practical applications. 

In the coal gangue sorting scene, coal and gangue are closely intertwined, making it challenging for the mechanical claw to accurately grasp gangue. To enhance grasping reliability under complex conditions, a multi-objective small-gap coal gangue recognition method based on semantic segmentation is proposed. The FCN (Fully Convolutional Networks) algorithm is improved by integrating the FPN (Feature Pyramid Network) module and replacing the cross-entropy loss with Dice Loss. A total of 1 202 coal gangue images are annotated using Labelme, and enhanced with the CLAHE (Contrast Limited Adaptive Histogram Equalization) algorithm. The performance of various semantic segmentation algorithms and transfer learning strategies are analyzed by comparative experiment. Results show that the FCN-ResNet50-FPN model, with ResNet50 as the feature extractor, achieved a precision of 95. 0%, a recall of 95. 4%, an F1 score of 95. 2%, and a mIoU(mean Intersection over Union) of 90. 9%. Transfer learning further improves recognition, enhances small-gap detection and provides reliable data for precise coal gangue sorting robot operations. 

To ensure the confidentiality and integrity of sensitive data for smart grid end users, a secure aggregation algorithm for smart grid end user sensitive data is proposed. The establishment of a fog computing architecture is prioritized for sensitive data collection, transmission, and processing of smart grid end users. At the smart meter terminal, the collected user sensitive data is encrypted through the formation and distribution of keys. The encrypted data is aggregated through fine-grained aggregation of fog nodes and coarse-grained aggregation of cloud nodes, and the obtained coarse-grained aggregation dataset of cloud nodes is transmitted to the power service institution through secure transmission channels. By parsing all fine-grained aggregated data stored in the cloud, the corresponding aggregated data plaintext can be obtained to achieve secure aggregation of sensitive data for smart grid end users. The experiment shows that the communication overhead of the proposed algorithm for secure aggregation of sensitive data is below 100 kByte, and the aggregation time is short. And the integrity protection for different types of sensitive data is above 0. 8, indicating that the proposed algorithm has high practicality.

In low light images, the effective signal and random noise exhibit a similar sparse distribution in the transform domain. The denoised image is prone to staircase effects or pseudo edges, which can lead to noise artifacts and reduce the quality of the image. Therefore, an online dictionary learning algorithm is proposed to smooth and denoise low light images, and to improve the visual effect of the images. The grayscale transformation on low light images is Implemented to reduce random noise in the images. An adaptive low light image block partitioning strategy is designed which dynamically adjusts the size of image blocks based on local brightness information and texture features after grayscale transformation, to obtain image details and structural information. An online dictionary learning model is created. It sparsely represents partitioned image blocks, dynamically captures the time-varying characteristics of noise and detail features through real-time dictionary updates, adaptively separates effective signals and noise, suppresses noise artifacts while preserving signal structure, solves the problems of staircase effect and pseudo edges caused by similar sparse distribution in low light images, and achieves smooth denoising of low light images. The experimental results show that the proposed method has strong robustness and can effectively suppress low light image noise. The peak signal-to-noise ratio and structural similarity of the image are significantly improved. 

SLAM(Simultaneous Localization and Mapping) technology is a camera pose estimation based on static scene features. It is susceptible to dynamic objects in the process of feature calculation and matching at its front end. Therefore a method of instance segmentation combined with multi-view geometric constraints is proposed to improve the front-end feature processing of visual SLAM and eliminate the interference of dynamic information. Specifically, in the front end of the ORB-SLAM3(Oriented FAST and Rotated BRIEF-Simultaneous Localization and Mapping3) framework, the YOLACT + + (You Only Look At CoefficienTs + +) instance segmentation thread is paralleled, and the segmented results are used to supplement the multi-view geometric constraint method testing the dynamic consistency of feature points. The EfficientNetV2 network is used to replace the original backbone network of YOLACT + +, and the TensorRT is used to quantify the instance segmentation model to reduce the front-end computing pressure of the algorithm. The test of TUM data set shows that the positioning accuracy of the proposed algorithm in high dynamic environment is 80. 6% higher than that of ORB-SLAM3 algorithm. 

In response to the demand for higher precision and higher resolution magnetic measurement technology, especially for the improvement of the performance index of weak magnetic measurement technology, based on the principle of magnetic induction electromagnetic, using integrated fluxgate chip, a sensor component structure which can be used in weak magnetic three-dimensional vector field is designed. The influence of coil current, temperature and environment circuit of generating device of weak magnetic field is studied. The three- dimensional distribution characteristics of the magnetic field coil are analyzed and calculated by Ansys simulation software, and the magnetic field intensity and direction of the random space test point are determined. The heat dissipation of coil current is analyzed by COMSOL physical field calculation software. The experimental results show that the test data is basically consistent with the simulation results, so the excitation current condition of the weak magnetic field generator is determined. The system accurately measures the distribution and change of magnetic field vector of geomagnetic field with different latitudes and longitudes. The magnetic vector integral of 20 000 space points for the vector of any closed curve are realized, the curl theorem of static magnetic field is verified experimentally. 

To enhance the security and confidentiality of patients’ medical privacy information, a secure encryption method based on chaotic mapping and the RC5(Rivest Cipher 5) algorithm is proposed. Firstly, the PCA(Principal Component Analysis) method is used to perform data dimension specification processing on medical privacy information data, completing dimensionality reduction of medical privacy information data. Then, using the RC5 block cipher algorithm, the key is initialized, transformed, and mixed to achieve secure encryption of medical privacy information. Finally, the dual chaotic system encryption algorithm ( EDC: Enhanced Dual Chaos) is used, combined with the high-quality performance of one-dimensional logistic mapping and two-dimensional Henon mapping, to achieve secondary encryption of medical privacy information. The experimental results show that the proposed method has high encryption efficiency, low information leakage rate, and strong anti attack performance.

Text classification of transmedia knowledge involves many types of data, such as text, image, video, etc. The heterogeneity and heterogeneity of data increase the complexity of classification. Aiming at the problem that it is difficult to find accurate data in a large number of cross-media knowledge texts, an algorithm of cross- media knowledge text classification based on multi-modal information is proposed. The TF-IDF(Term Frequency- Inverse Document Frequency) algorithm is used to filter the stop words in the processing text, extract the text features, and integrate them with the image text features. By using naive Bayes classifier, the classification of cross-media knowledge text is determined and realized. Experimental analysis shows that the proposed text classification algorithm significantly improves the performance and efficiency of cross-media knowledge text classification, and makes the classification results more accurate, with the accuracy rate up to 95. 12% and the missing rate remaining below 10%.

The sources of regional economic data are diverse, including statistical departments, enterprise reports, sensor data, et al. There are significant differences in data format, structure, and semantics, making it difficult to process them uniformly. This leads to difficulties in accurately extracting data features, which in turn results in inaccurate data classification results for methods. To address this issue, a regional economic big data integrated classification method based on parallel clustering algorithm is proposed. Based on the characteristics of regional economic big data, calculate the purity and neighborhood radius of the data, determine the missing values of regional economic big data, and correct and fill them in. Based on the filled data, parallel clustering algorithm is used to randomly divide it into multiple subsets of data. The parallel clustering algorithm utilizes multi node parallel processing to significantly improve computational efficiency and meet the requirements of large-scale data processing. Extract the feature quantities of each data subset and design a big data base classifier accordingly. Under the premise of considering the internal data density of the base classifiers, determine the weight values of each base classifier, combine the classification results of each base classifier, and output the final data ensemble classification result. The experimental results show that the designed classification method has a DBI (Davies-Bouldin Index) index of 0.31 in practical applications, which can achieve accurate classification of regional economic big data.

 In order to quickly extract key information from massive library knowledge graphs, an entity relationship extraction algorithm for academic text keyword library knowledge graphs is proposed. OCS-FCM (Optimization of Complete Strategy Fuzzy C-Means) and Elastic E-t-SNE(Embedding t-Distributed Stochastic Neighbor Embedding ) algorithms are used to perform missing value filling and dimensionality reduction on key words in the library. And using entities in the academic text keyword library as vertices, a knowledge graph is established. Based on the part of speech and other features of keywords, a SelfATT BLSTM(Self Attention Bidirectional Long Short Term Memory) model is constructed using a self attention mechanism algorithm to extract entity relationships from the knowledge graph and obtain the extracted results. Experimental results have shown that the collection accuracy of proposed algorithm is more than 0. 8, with an ACC(Accuracy) value over 30% and a extraction time less than 1.5 s, demonstrating excellent ability to extract entity relationships. 

Considering the large-scale and high-dimensional features of remote sensing images, the complex remote sensing application process requires appropriate feature extraction and selection, while further distinguishing different subcategories of similar targets. Therefore, an improved ResNet(Residual Network) algorithm is proposed for fine-grained recognition of complex remote sensing background targets. Non mean filtering algorithm is used to label the coordinate domain of noisy remote sensing images, calculate the similarity between pixels, and denoise complex remote sensing images. Based on the denoising results, global and local feature points of the image are extracted, and global and local feature maps are obtained through feature point fusion results. An improved residual network algorithm is introduced to analyze the fine-grained pixel size of each background image block area. After residual learning, combined with the image pixel position and loss function, a classifier is used twice to determine the fine-grained pixel features and complete the fine-grained recognition of background targets. The experimental results show that the image clarity is high, and as the number of images to be recognized continues to increase, F1 -Score and global recall rates have been improved to various degrees, with lower gain errors. 

In order to study the conjecture of neighbor sum distinguishing total chromatic number, the structure of minimal counter example graphs is analyzed using the Combinatorial Nullstellensatz and proved that the neighbor sum distinguishing total chromatic number of IC-planar graphs with the maximum degree Δ>=8 without intersecting triangles does not exceed Δ+3 by the discharging method. The research results indicate that the conjecture of neighbor sum distinguishing total chromatic number holds on this class graphs.

Due to the poor defogging effect of remote sensing image clustering, the clustering accuracy and Kappa coefficient of image clustering are low and the time is long. In order to solve these problems, a new clustering optimization method remote sensing image based on adaptive K-means algorithm is proposed. Firstly, dark channel prior estimation and color line prior estimation are used to de-fog remote sensing images. Secondly, the gray co-occurrence matrix of the remote sensing image after fog removal is calculated, and the texture features are obtained. Finally, the colony algorithm is used to optimize the K-means algorithm, and the optimized adaptive K-means algorithm is used to realize the clustering optimization of remote sensing images according to texture features. The experimental results show that the proposed method can effectively eliminate cloud and fog in remote sensing images, and the image details are clearly displayed. The proposed method has good performance in terms of clustering accuracy, Kappa coefficient and clustering time. The clustering accuracy reaches 94. 9%, the Kappa coefficient is 0. 97, and the clustering time is 0.36 s. This method has certain validity. 

Aiming at the high energy consumption problem that exists in multiple-input multiple-output C-IoT (Cognitive Internet of Things) systems, a joint beamforming optimization algorithm based on IRS(Intelligent Reflecting Surface) assistance is proposed. Taking the signal-to-interference-to-noise ratio at the secondary user and the discrete phase shift at the IRS as constraints, a new optimization criterion is constructed to maximize the energy efficiency of system by jointly optimizing the active beamforming matrix at the secondary transmitter and the passive beamforming matrix at the IRS. After decomposing the complex non-convex optimization problem into sub-problems, the fixed-point iteration method and the successive refinement method are used to process the sub- problems respectively. The simulation results show that the proposed algorithm has good convergence in multi- antenna scenarios. Compared to the baseline scheme, the proposed algorithm effectively improves the energy efficiency of the system in multi-user situations.

With the rapid development of information technology, traditional library information management systems are no longer able to meet the needs of modern users for efficient, convenient, and personalized services. We aim to design and implement an artificial intelligence based library information management system to improve the management efficiency and service quality of the library. The system adopts a layered architecture design, including front-end user interface layer, back-end business logic layer, and data storage layer, to ensure high performance, high availability, and high scalability of the system. The functional modules cover user management, book management, intelligent retrieval, and data analysis, to meet the diverse needs of users. By integrating artificial intelligence technologies such as natural language processing, machine learning, and image recognition, the system has achieved functions such as semantic retrieval, personalized recommendation, and multimodal retrieval, significantly enhancing the user experience. During the development process, the agile development process is followed and technology stacks such as Python, Django, MySQL, etc. are used to ensure efficient development and stable operation of the system. The test results show that the system response time can be maintained within 2 seconds under high concurrency conditions, and user satisfaction reaches 85% . This study provides new perspectives and methods for research in the field of library information management, and provides strong technical support for the digital transformation and intelligent upgrading of libraries, which has important theoretical and practical significance.

The diversity and complexity of video content make video label classification difficult. Different videos may have similar features but belong to different categories, or videos of the same category may have significant differences in presentation. To effectively improve the accuracy of video label classification results, a video label classification algorithm combining CNN(Convolutional Neural Network) and rotated forest is proposed. Classify film and video tags into two stages. In the first stage, the rotation forest algorithm is used to segment the sample set of film and television video labels. Through feature transformation, each subset of samples is transformed into a completely new feature space, and multiple new sample subsets with significant differences are obtained. The AdaBoost algorithm is used to iterate multiple times in the sample set and construct multiple AdaBoost classifiers.The probability averaging method is introduced to fuse the classification results and obtain preliminary label classification results. In the second stage, the film and television video features captured by the quaternion Gabor filtering convolution algorithm and the preliminary classification results of the labels obtained in the first stage are used as inputs for the CNN. L1 regularization is introduced in the fully connected layer to constrain the complexity of the model and prevent overfitting. The film and television video label classification is completed through multiple rounds of iterative training. The test results show that the proposed algorithm has good performance in film and television video label classification and can effectively meet the personalized needs of users.

To address the limitations of existing course evaluation models-specifically their insufficient sensitivity to cross-sentence context and inadequate extraction of semantic importance-this paper proposes a multi-granularity semantic analysis-based model that more accurately captures students' true intentions within textual feedback and supports downstream tasks such as sentiment classification and knowledge extraction. The model integrates pre-trained models and deep neural networks to extract word-level, sentence-level, and part-of-speech-level text feature vectors for semantic analysis and processing. Using course evaluation texts as an example, we conduct experiments and analyses. The model employs both precise and fuzzy matching evaluation methods and incorporates Dropout and the ReLU ( Rectified Linear Unit) activation function to enhance its generalization capability. In the experiments, we improved the model's classification performance by adopting various text preprocessing strategies, including stopwords removal and key term selection. The results indicate that the proposed model excels in sentiment analysis for course evaluations, achieving an accuracy of 92. 53% ,particularly when dealing with ambiguous sentiment boundaries. For course evaluations, the proposed semantic analysis model effectively captures detailed feedback from students, providing an efficient automated evaluation tool for the education sector and optimizing teaching quality.