In order to improve the recognition performance and accuracy of traditional object detection and to accelerate the computation speed, a CNN( Convolutional Neural Network) model with more powerful feature learning and representation capabilities and with related deep learning training algorithms is adopted and applied to large-scale recognition tasks in the field of computer vision. The characteristics of traditional object detection algorithms, such as the V-J(Viola-Jones) detector, HOG(Histogram of Oriented Gradients) features combined with SVM( Support Vector Machine) classifier, and DPM ( Deformable Parts Model) detector are analyzed. Subsequently, the deep learning algorithms that emerged after 2013, such as the RCNN ( Region-based Convolutional Neural Networks) algorithm and YOLO(You Only Look Once) algorithm are introduced, and their application status in object detection tasks is analyzed. To detect fallen individuals, the YOLOv5(You Only Look Once version 5) model is used to train the behavior of individuals with different heights and body types. By using evaluation metrics such as IoU(Intersection over Union), Precision, Recall, and PR curves, the YOLOv5 model is analyzed and evaluated for its performance in detecting both standing and fallen activities. In addition, by pre- training and data augmentation, the number of training samples is increased, and the recognition accuracy of the network is improved. The experimental results show that the recognition rate of fallen individuals reaches 86% . The achievements of this study will be applied to the design of disaster detection and rescue robots, assisting in the identification and classification of injured individuals who have fallen, and improving the efficiency of disaster area rescue.

To meet the need of integrating scientific research into teaching of Emerging Engineering Education, a multi-dimensional and hierarchical integrated experimental platform based on Python is designed. Guided by the talent-training plan, hierarchical modules involving image recognition, machine learning and data analysis is designed from scientific research hotspots. Image recognition module starts from character recognition, then face and license plate recognition are realized by several algorithms. In the machine learning module, commonly used machine learning algorithms are studied and corn disease is identified by various methods based on Python. In the data processing and analysis module, Excel data processing experiment based on Python is designed to analyze the data of workload and bioinformatics data. The platform enables students to learn the application of Python in the experiments, and choose different experimental projects according to professional needs and research directions to realize the goal of teaching students in accordance with their aptitude. By applying the experimental platform to teaching practice, it is demonstrated that students have a deeper understanding of Python’s programming implementation in image recognition, machine learning, and data analysis and enhanced research interest. And the goal of integrating scientific research into teaching and improving the quality of undergraduate teaching could be achieved.

Under the current situation of normalized management of epidemic situation, in order to ensure the normal development of computer experiment courses in colleges and universities, a virtual laboratory for computer basic experiments is established based on Docker technology. Students can access the server through a browser to obtain an independent experimental environment. The Docker-Compose tool is used to create, open, stop, delete and other multi-dimensional management of students' experimental environments, and to ensure their performance, which is equivalent to moving the offline laboratories online. This scheme can meet the needs of online computer basic experiments and provide high-quality experimental services for corresponding theoretical teaching.

 In response to the problem of many class hours and many students attending classes in public computer laboratories each semester, a set of public computer laboratory information system has been developed independently. The system consists of three parts: student side, teacher side and server. The student side is a desktop program based on Python. The teacher side and the server are implemented in a web project written by JSP(Java Server Pages). In terms of function, the platform can be divided into three basic modules: student sign in, lost and found, feedback. It integrates other common functions. The application results indicate that this system can utilize information technology to provide convenience for students to learn in the laboratory. It truly implements the teaching concept of “student-oriented”

Taget Detection of Photovoltatic Remote Sensing Based on Improved Yolov5 Model TONG Xifeng, DU Xin, WANG Zhibao (School of Computer and Information Technology, Northeast Petroleum University, Daqing 163318, China) Abstract: Aiming at high-sensing photovoltaic image resolution, high environmental noise, and complex background, an improved Yolov5 model is proposed to achieve positioning of photovoltaic power plants. First of all, the CA(Coordinate Attention) mechanism is added to the compassionate layer of the main feature extraction network to improve the learning ability of the network characteristics; second, the Ghostconv network structure is added to Backbone, useing the Ghostconv network module to replace the Conv network module, designing a new GhostC3 network network instead of the original C3 network module to improve the learning efficiency of the model; finally, the GIoU_Loss function is changed to the SIoU_Loss function. Compared with the original Yolov5 method, the average accuracy of the improved algorithm mAP, accuracy, and recall rate reached 97. 5% , 98. 9% , and 94. 9% , respectively, which have increased by 1. 8% , 1. 7% , and 5. 8% , respectively. The algorithm has a good effect on photovoltaic detection.

In order to reduce the inspection burden of electric power workers and realize intelligent inspection in substation, the algorithm of substation equipment defect detection is studied. Firstly, the data augmentation method is used to expand the initial dataset and various image processing method is used to generate the dataset with complex illumination environment. Then, the adaptive spatial feature fusion method is used to mitigate the inconsistency of different scale features in the feature pyramid, and the loss function of confidence is changed to Focal loss function to mitigate the imbalance between positive and negative samples. Based on the improved YOLOX-s(You Only Look Once X-s) network model, the algorithm of substation defect detection is designed. Finally, the detection effect of the improved YOLOX-s model is compared with that of other deep learning algorithms. Under the designed data set, the experiment shows that the comprehensive detection effect of the improved YOLOX-s network model is good, and the accuracy and real-time performance is satisfied. 

A football competition risk intelligent warning method based on an improved Copula model is proposed to address the issues of large errors between warning values and actual values, and multiple false alarms in football matches. Based on the fuzzy comprehensive evaluation matrix, the evaluation system for football competition risk indicators is determined. The indicator level status is classified, the Copula function is selected, and an improved Copula football competition risk intelligent warning method is constructed to accurately judge football competition risks and reduce risk losses. The experimental results show that the interference suppression of this method is high, maintained above 20 dB, and have high anti-interference ability. It can effectively suppress interference. This method also reduces the error between the warning value and the actual value, reduces the number of false alarms in the warning, and verifies the practicality and feasibility of this method.

To avoid the gradient vanishing or exploding issue in the RNN(Recurrent Neural Network)-based sequential recommenders, a gated recurrent unit based sequential recommender DeepGRU is proposed which introduces the residual connection, layer normalization and feed forward neural network. The proposed algorithm is verified on three public datasets, and the experimental results show that DeepGRU has superior recommendation performance over several state-of-the-art sequential recommenders ( averagely improved by 8. 68% ) over all compared metrics. The ablation study verifies the effectiveness of the introduced residual connection, layer normalization and feedforward layer. It is empirically demonstrated that DeepGRU effectively alleviates the unstable training issue when dealing with long sequences. 

In order to solve the problem that using traditional technologies such as Java and .NET to develop and deploy data services are complex and difficult to integrate with advanced cloud and container technologies, a lightweight 3D visualization data service solution for drilling based on Web is proposed, providing data interface support for front-end visualization applications. Based on NodeJS、 Angular、 TypeScript and other open source lightweight technologies, a lightweight drilling database system is designed, which can be used as an auxiliary tool for front-line technical managers and providing the most concerned data items in the fastest way with high efficiency and practicability. With the data loading tool, drilling technicians can easily load data into the database, including surface and seismic slices, measurements, events and well logs of blocks. And the system provides a comprehensive data security mechanism, including JWT ( JSON Web Token ) based identity authentication and JWE ( JSON Web Encripytion ) based data encryption, to ensure data security. The application results show that this solution can provide efficient data transmission services for drilling 3D visualization systems. 

 To monitor changes of indoor carbon dioxide concentrations in real time, a carbon dioxide alarm based on a gas sensor with a STC89C52 microcontroller as the core is designed. When the CO2 concentration in the air exceeds the preset value, the sound and light alarm function can be activated, and the indoor CO2 concentration value can be displayed in real-time. The hardware system includes a carbon dioxide sensor, signal conditioning circuit, analog-to-digital conversion circuit, STC89C52 microcontroller, and acousto-optic alarm unit. The software system includes data acquisition, data processing, alarm logic, and other functional units. The alarm can be activated in time when indoor CO2 concentration exceeds 1. 5% . 

Aiming at the problem that the traditional named entity recognition method can not fully learn the complex sentence structure information of ancient Chinese and it is easy to cause information loss in the process of long sequence feature extraction, an ancient Chinese fusion of SikuBERT ( Siku Bidirectional Encoder Representation from Transformers) model and MHA (Multi-Head Attention) is proposed. First, the SikuBERT model is used to pre-train the ancient Chinese corpus, the information vector obtained from the training into the BiLSTM (Bidirectional Long Short-Term Memory) network is input to extract features, and then the output features of the BiLSTM layer are assigned different weights through MHA to reduce the information loss problem of long sequences. And finally the predicted sequence labels are obtained through CRF (Conditional Random Field) decoding. Experiments show that compared with commonly used BiLSTM-CRF, BERT-BiLSTM-CRF and other models, the F1 value of this method has been significantly improved, which verifies that this method can effectively improve the effect of ancient Chinese named entity recognition.

 Microseismic inversion is an important way to complete main task of microseismic monitoring by inverting and inferring information such as the location of the epicenter, the time of occurrence of the earthquake, the true magnitude, the initial amplitude of the hypocenter, the focal mechanism and the medium parameters based on the microseismic monitoring data. Through the study of microseismic inversion technology, more accurate microseismic information can be obtained, thereby improving the reliability of reservoir fracture evaluation, reducing development costs and improving oil and gas recovery. We review microseismic inversion from three aspects: microseismic focal location inversion, microseismic focal mechanism inversion, and microseismic multi-parameter joint inversion. The research progress of microseismic inversion technology in recent years is reviewed, and the principle, advantages and disadvantages of various microseismic inversion methods are summarized, the improvement and application of various microseismic inversion techniques are summarized, and the future research ideas and development directions are prospected. It provide reference for further development of microseismic inversion in the future.

Federated learning has become increasingly important for modern machine learning, especially for data privacy sensitive scenarios. It is difficult to carry out secure machine learning between heterogeneous data islands. A federated learning communication mode between heterogeneous data islands is proposed, which realizes the hybrid federated learning communication between horizontal and vertical, and breaks the communication barrier of the disunity of model structure between horizontal and vertical participants in traditional federated learning. Based on the special privacy requirements of the government, banks and other institutions, the third party aggregator is further removed on the basis of the hybrid federated learning model, and the calculation is carried out only among the participants, which greatly improves the privacy security of local data. In view of the computational speed bottleneck caused by vertical homomorphic encryption in the communication process in the above model, by increasing the local iteration round q, the encryption time of vertical federation learning is shortened by more than 10 times, and the computational bottleneck between horizontal and vertical participants is reduced, and the accuracy loss is less than 5% .

The connection between mobile internet devices based on the Android platform and people’s lives is becoming increasingly close, and the security issues of mobile devices have become a major research hotspot. Currently, many visual Android malware detection methods based on convolutional neural networks have been proposed and have shown good performance. In order to better utilize deep learning frameworks to prevent malicious software attacks on the Android platform, a new application visualization method is proposed, which to some extent compensates for the information loss problem caused by traditional sampling methods. In order to obtain more accurate software representation vectors, this study uses the Swin Transformer architecture instead of the traditional CNN(Convolutional Neural Network) architecture as the backbone network for feature extraction. The samples used in the research experiment are from the Drebin and CICCalDroid 2020 datasets. The research experimental results show that the proposed visualization method is superior to traditional visualization methods, and the detection system can achieve an accuracy of 97. 39% , with a high ability to identify malicious software.

To reduce the influence of complex and changeable electromagnetic environment on vehicles, the cable model is built in the engine compartment by using the three-dimensional electromagnetic field simulation software CST(Computer Simulation Technology) to study the influence of different factors on the electromagnetic coupling effect of vehicles. Through simulation, the peak relationship curves between induced voltage and induced current in the cable are drawn when the parameters such as cable length, cable height from the bottom of the car, cable relative distance, cable terminal resistance, conductor radius, and insulation layer thickness change. These conclusions can provide theoretical guidance for the design of vehicle wire harnesses, and provide a basis for the conductor radius selection, cable relative distance, height from the ground, and cable length in electromagnetic protection design. 

In order to solve the problems of management, coordination and association of cross regional scientific and technological resource sharing and collaborative innovation, practical application and theoretical research of scientific and technological resource platform are carried out to build an ecological digital display system of scientific and technological innovation. First, the definition, composition and index system of scientific and technological innovation elements are constructed, and innovation map, innovation ability, innovation subject, innovation carrier are proposed. The digital display system with innovation resources and innovation environment is the core. Taking Jilin Province as an example, the index method is used to monitor the level of regional scientific and technological innovation, the text mining method is used to analyze the hot spots of scientific and technological policies, and the system architecture and function design are carried out based on the Vue + Django + MySQL technology architecture. Finally, the ecological digital display of scientific and technological data innovation in the region is realized, so that the system has data sharing, data association and intelligent service functions such as decision support. The application practice shows that the system enriches the visualization of scientific and technological data resources, improves the visualization of scientific and technological innovation ecology, and improves the expansibility, efficiency and performance of the system.

As one of the important components of the detection system, the performance of photoelectric detector is directly related to the quality of system data acquisition. In order not to affect the final detection result, it is essential to ensure the detector performance. The performance of high performance PtS₂ / MoTe₂ heterojunction infrared photodetector is studied. First, the materials, reagents and equipment are prepared to make PtS₂ / MoTe₂ heterojunction infrared photodetectors. The detector performance test environment, the four indicators of light response, detection rate, response time and photoconductivity gain are set up, and the detector performance is analyzed. The results show that the optical responsivity of PtS₂ / MoTe₂ heterojunction infrared photodetector is always above the 5 A/ W limit with the passage of test time. The detection rate of the detector is greater than 10 cm·Hz1 / 2 W ^-1 regardless of the infrared light reflected from any material. Whether the photocurrent is in the rising time or the falling time, its response time is always below the limit of 150 μs; The photoconductivity gain value has been kept above 80% . 

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.

 In response to the chattering phenomenon that traditional SMO(Sliding Mode Observer) faces during switching functions, novel sliding mode observer using saturation function instead of switching function is proposed to weaken chattering. In the process of extracting position information, a phase-locked loop is selected to replace the traditional arctangent method, there by improving the observation accuracy of PMSM(Permanent Magnet Synchronous Motor) rotor position. In the Matlab environment, by comparing traditional SMO and new SMO, it can be observed that the speed error of the rotor has increased by about 14 r/ min, and the position error of the rotor has increased by about 0. 03 rad.

The obstacle avoidance control problem of UAVs( Unmanned Aerial Vehicles) and UGVs ( Unmanned Ground Vehicles) named heterogeneous unmanned swarm system is studied using a game-theoretic approach combined with the artificial potential field method. Unlike most multi-agent formation control schemes that only consider the group formation objective, we allow each agent to have individual objectives, such as individual tracking and obstacle avoidance. Specifically, when the heterogeneous unmanned swarm system completes the cooperative formation, each agent needs to track the target point and avoid obstacles in real-time according to its own interests. The heterogeneous unmanned swarm system formation problem is transformed into a non- cooperative game problem between agents because there may be conflicts between the individual and group objectives of the agents. Real-time obstacle avoidance is realized by adding an obstacle avoidance term based on the artificial potential field function into the cost function. And the controller is designed based on the Nash equilibrium seeking strategy to achieve a balanced formation mode of individual and group objectives. Finally, the correctness of the theoretical results is verified through simulation experiments. The proposed method can enable heterogeneous unmanned swarm system to achieve formation motion and real-time obstacle avoidance.

Computation offloading strategy in mobile edge computing can help users decide how to execute tasks, which is related to user experience, and has become a research hotspot in mobile edge computing. At present, most computation offloading strategies are carried out under the condition of overall task offloading, and only consider a single indicator of delay or energy consumption, and do not combine the two for optimization. To solve this problem, this paper takes the weighted sum of task processing delay and energy consumption as the optimization goal, and proposes a partial offloading algorithm based on reinforcement learning. We divide the processing of a single task into local computing and partial offloading computing, and introduce a variable to determine the offloading weight in partial offloading. Finally, we use reinforcement learning Q-learning to complete the computation offloading and resource allocation of all tasks. Experimental results show that the proposed algorithm can effectively reduce the delay and energy consumption of task processing.

 The current learner model lacks exploration of this dimension of cognitive load, which, as a load generated by the cognitive system during the learning process, has a significant impact on the learning state of learners. Based on the CELTS-11(China E-Learning Technology Standardization-11) proposed by the China E-Learning Technology Standardization Committee, cognitive load is integrated into the learner model as a dimension, and an LMICL ( Learner Model Incorporating Cognitive Load) combining static and dynamic information is constructed. Afterwards, relying on an adaptive learning system, the data of the unmixed cognitive load learner model and the LMICL data were used as the basis for recommending learning resources, resulting in two different learning resource recommendation results. Two classes of learners were randomly selected to learn system, and then their academic performance. The results of cognitive load and satisfaction were used to validate the effectiveness of LMICL , and it was found that the recommendation learning effect based on LMICL was better than that of the learner model without integrating cognitive load.

 In order to improve the invulnerability and working ability of the satellite constellation network after being attacked, a simulated annealing wolf pack algorithm is proposed. We use the subjective and objective weight method combined with the TOPSIS( Technique for Order Preference by Similarity) to Ideal Solution to evaluate the importance of nodes in the network, and attack the network according to the order of node importance. The network connection efficiency is the optimization goal, and the satellite constellation network communication limitation is the constraint condition. The idea of motion operator is adopted to realize the walking, summoning and sieging of wolves with adaptive step size. The network structure is optimized using the edge-adding scheme obtained through optimization. Experiments show that compared with other optimization algorithms, this algorithm has superiority. It solves the problem that the satellite constellation network爷s working ability declines after being attacked, and improves its invulnerability after being attacked. Key words: satellite network; invulnerability optimization; simulated annealing algorithm; improved wolf colony algorithm

 In order to explore the ability of imaging to diagnose benign and malignant breast lesions, and compare the value of MR(Magnetic Resonance) radiomics and traditional MRI(Magnetic Resonance Imaging) in diagnosing breast diseases, a total of 190 cases with benign or malignant breast lesions confirmed by pathological findings are collected from patients who underwent MR Plain and enhanced examination in the Department of Radiology in First Hospital of Jilin University from January 2019 to January 2022. MR radiomics is performed by building logistic regression model. The traditional MR Diagnosis is performed by a radiologist with an associate senior title. The results show that the sensitivity, specificity and AUC (Area Under Curve) of the MR radiomics test set are 0. 92, 0. 83 and 0. 92 respectively. The above values are higher than the corresponding values of traditional MR diagnosis, and the differences are statistically significant ( P = 0. 00 ). The method of MR radiomics can assist in the diagnosis of benign and malignant breast lesions, and the diagnostic ability is better than the traditional MR diagnostic mode.

To solve the problem that Q function overestimation may cause SAC ( Soft Actor Critic) algorithm trapped in local optimal solution, SCSAC ( Stable Constrained Soft Actor Critic) algorithm is proposed for perfectly resolving the above weakness hidden in maximum entropy objective function improving the stability of Stable Constrained Soft Actor Critic algorithm in trailing process. The result of evaluating Stable Constrained Soft Actor Critic algorithm on the suite of OpenAI Gym Mujoco environments shows less Q value overestimation appearance and more stable results in trailing process comparing with SAC algorithm.

To inherit and protect the traditional blue calico patterns, it is necessary and challenging to protect blue calico in a digital manner. Due to the lack of blue calico pattern datasets with original manual characteristics, which limits the application of powerful deep learning technology on pattern recognition field like the recognition of Blue Calico patters, therefore a large-scale dataset called Blue-Calico pattern dataset is provided, which is the first publicly available benchmark for blue calico pattern recognition. This dataset contains about 50 216 blue calico patterns, covering 85 pattern classes, such as animals, plants, myths and legends. The construction of this dataset will concern the digital construction of blue calico, such as calico image retrieval and caption, and enable researchers to design and validate data-driven algorithms. On the basis of the new dataset, the experimental results of four state-of-the-art networks are provided as a baseline for future work.

fMRI ( functional Magnetic Resonance imaging) is an efficient research method for brain imaging technique. In order to reduce the redundancy of the fMRI data and transform the fMRI data to the constructed features with more classification potential, a feature construction method based on the siamese network named as SANet(Siamese Network) is proposed. It engineered the brain regions features under multiple scanning points of an fMRI image. The improved AlexNet is used for feature engineering, and the incremental feature selection strategy is used to find the best feature subset for the encephalopathy prediction task. The effects of three different network structures and four classifiers on the SANet model are evaluated for their prediction efficiencies, and the ablation experiment is conducted to verify the classification effect of the incremental feature selection algorithm on the SANet features. The experimental data shows that the SANet model can construct features from the fMRI data effectively, and improve the classification performance of original features.

Fault identification plays an important role in geological exploration, reservoir description, structural trap and well placement. Aiming at the problem that traditional coherence attribute and machine learning are poor in complex fault recognition, a fault recognition method based on UNet++ convolutional neural network is proposed. The weighted cross entropy loss function is used as the objective function to avoid the problem of data sample imbalance in the training process of the network model. Attention mechanism and dense convolution blocks are introduced, and more jump connections are introduced to better realize the feature fusion between the semantic information of deep faults and the spatial information of shallow faults. Furthermore, the UNet ++ network model can realize fault identification better. The experimental results show that the F1 value increased to 92. 38% and the loss decreased to 0. 012 0, which can better learn fault characteristic information. The model is applied to the identification of the XiNanZhuang fault. The results show that this method can accurately predict the fault location and improve the fault continuity. It is proved that the UNet ++ network model has certain research value in fault identification. 

The complex anatomical structure of the human body and significant individual differences, the limited two-dimensional anatomical images in textbooks often make it difficult for students to understand, and there are problems such as unclear learning objectives, unscientific learning methods, low learning efficiency, and poor learning outcomes during the learning process. To address a clinical anatomy teaching model based on image 3D visualization technology is proposed. The clinical teaching achievements based on 3D visualization technology in recent years are summarized, and the feasibility and superiority of 3D visualization technology in clinical teaching mode pointed out. Finally, the expansion content and development ideas of the visualization clinical teaching mode are discussed, and the possibility of applying the construction of clinical anatomy case library based on image visualization technology to the visualization teaching mode is prospected. 

The improvement of consensus mechanism is a key research content in the development process of blockchain technology. In the traditional consensus mechanism, all endorsement nodes participate in endorsement, which consumes a lot of time, and has the possibility of forging and manipulating the consensus process with low security. Based on the verifiable random function, the endorsement nodes in the candidate set of endorsement nodes for trading and any endorsement node for endorsement operation are randomly selected which can effectively improve the processing efficiency and reduce the processing time of the consensus mechanism. Based on theoretical analysis and experimental verification of Hyperledger fabric model, the results show that the optimized consensus mechanism has faster transaction processing speed, lower delay time and higher security.

 Due to the dense traffic flow and stochastic uncertainty of vehicle behaviors, the scenario of unsignalized intersection poses significant challenges for autonomous driving. An innovative approach for autonomous driving decision-making at unsignalized intersections is proposed based on the MAPPO(Multi-Agent Proximal Policy Optimization) algorithm. Applying the MetaDrive simulation platform to construct a multi-agent simulation environment, we design a reward function that comprehensively considers traffic regulations, safety including arriving safely and occurring collisions, and traffic efficiency considering the maximum and minimum speeds of vehicles at intersections, aiming to achieve safe and efficient autonomous driving decisions. Simulation experiments demonstrate that the proposed decision-making approach exhibits superior stability and convergence during training compared to other algorithms, showcasing higher success rates and safety levels across varying traffic densities. These findings underscore the significant potential of the autonomous driving decision-making solution for addressing challenges in unsignalized intersection environments, thereby advancing research in autonomous driving decision-making under complex road conditions.自动驾驶;智能决策;无信号灯交叉口;MAPPO算法 

An improved artificial potential field method is proposed to solve the problems of local minimum and unable to reach the target in the path planning of mobile robots. Firstly, in order for the robot to reach the target point when there are obstacles near the target point due to the large repulsive force, a safe distance factor is introduced into the potential field, and this parameter is optimized, so that the robot can maintain a proper distance from the obstacles and reach the target point smoothly. Secondly, in order to solve the local minimum problem, the local minimum discriminant condition is introduced, and the local minimum region is circum- navigated when the condition is triggered, so that the robot can reach the target point smoothly. The simulation results show that the improved algorithm has strong robustness when operating in the map environment with different number of obstacles. The proposed algorithm can make the robot bypass the local minimum area in the U-shaped obstacle environment, and successfully solve the local minimum problem in the mobile robot path planning.

Considering that the randomness of the new power load is enhanced, the traditional accurate forecasting methods can not meet the requirements, an EMD-BiLSTM-ANFIS (Empirical Mode Decomposition Bi-directional Long Short Term Memory Adaptive Network is proposed based Fuzzy Inference System) quantile method to predict the load probability density. It replaces the accurate value of point prediction with the load prediction interval, which can provide more data for power System analysis and decision-making, The reliability of prediction is enhanced. First, the original load sequence is decomposed into several components by EMD, and then divided into three types of components by calculating the sample entropy. Then, the reconstructed three types of components and the characteristics of external factors screened by correlation. And they are used together with the Bilstm and ANFIS models for prediction training and QR(Quantile Regression), and accumulate the results of the prediction interval of the components to obtain the prediction interval of the final load. Finally, the kernel density estimation is used to output the user load probability density prediction results at any time. The validity of this method is proved by comparing the point prediction and interval prediction results with CNN- BiLSTM(Convolutional Neural Network-Bidirectional Long Short-Term Memory) and LSTM ( Long Short-Term Memory)models. 

The rock image recognition algorithm model based on traditional deep learning is cumbersome and requires certain computing power when it is applied to mobile terminals, so it is difficult to realize real-time and accurate identification of rock types. Based on the ShuffleNetV2 network, we insert the ECA (Efficient Channel Attention) module of the channel connection attention mechanism, use the Mish activation function to replace the ReLU activation function, and introduce the depthwise separable convolution in the lightweight network components. Experiments are performed on rock images with this method. Experiments show that the recognition accuracy of the algorithm reaches 94. 74% . The improved algorithm structure is not complex and maintains the characteristics of lightweight, which lays a foundation for its application in limited resource environments such as mobile terminals.

To address the problem that traditional language models can not solve the problem of deep bidirectional representation and the problem that classification models can not adequately capture salient features of text, a text classification model based on BERT-BiGRU-CNN ( Bidirectional Encoder Representation from Transformers-Bidirectional Gating Recurrent Unit-Convolutional Neural Networks) is proposed. Firstly, the BERT pre-training model is used for text representation; secondly, the output data of BERT is input into BiGRU to capture the global semantic information of text. The results of BiGRU layer again are input into CNN to capture the local semantic features of text. Finally, the feature vectors are input into Softmax layer to obtain the classification results. The Chinese news text headlines dataset is used, and the experimental results show that the BERT-BiGRU-CNN based text classification model achieves an F1 value of 0. 948 5 on the dataset, which is better than other baseline models, proving that the BERT-BiGRU-CNN model can improve theshort text classification performance. 

Aiming at the problems of difficult modeling and low calculation efficiency of equivalent harness method, the effect of electromagnetic pulse radiation on the vehicle harness is studied using CST ( Computer Simulation Technology). The influence of the number of vehicle cables on the electromagnetic coupling effect of the harness is analyzed. By controlling the variables, we changed the number of cables in the harness and observed the maximum value of the coupling voltage in the harness. We also studied the maximum coupling voltage and current in the harness by varying the cable size and load resistance. The simulation results show that the peak value of the coupling voltage decreases linearly with an increase in the number of cables and increases linearly with an increase in cable size. The peak value of the coupling current decreases with an increase in load resistance, which follows a power series relationship. Finally, we combined the simulation results and fitted the maximum coupling voltage and current under different parameters, drawing a conclusion about the relationship between them, which provides a reference for the electromagnetic protection of vehicle wiring harnesses. 

In order to better protect the ecological environment and increase the economic value of recyclable waste, to solve the problems faced by the existing garbage identification methods, such as the complex classification background and the variety of garbage target forms, a residual semantic enhancement network for garbage image classification is proposed, which can strip foreground semantic objects from complex backgrounds. Based on the backbone residual network, the network uses visual concept sampling, inference and modulation modules to achieve visual semantic extraction, and eliminates the gap between semantic level and spatial resolution and visual concept features through the attention module, so as to be more robust to the morphological changes of garbage targets. Through experiments on the Kaggle open source 12 classified garbage dataset and TrashNet dataset, the results show that compared with the backbone network ResNeXt-50 and some other deep networks, the proposed algorithms have improved performance and have good performance in garbage image classification. 

 To address the issue of the lack of interoperability and data sharing among different information and application systems on campus, we aim to leverage data integration technology to merge diverse educational data sources. We intend to establish a multi-source, heterogeneous education big data mining and application platform. The platform system will utilize the output of artificial intelligence models and the input from a multi- source, heterogeneous education big data mining engine. It will be based on big data mining techniques to analyze and process multiple data sources, including student records, teaching resources, and social behavior information. This will enable functionalities such as educational sign diagnosis, intelligent learning state comparison, analysis of teaching impact factors, identification of potential issues, and prediction of teaching quality trends. Our goal is to scientifically enhance the quality of personalized campus teaching services, objectively assess the teaching proficiency of individuals and teaching teams, assist in analyzing the strengths and weaknesses of teaching individuals and teams, and provide robust support to decision-makers in managing the education system. 

Aiming at the problem of information loss, such as details of remote sensing images reconstructed by a super-resolution algorithm, in order to ensure that remote sensor reconstruction images contain more texture and high-frequency information, a remote-sensitive image super resolution network is proposed based on a pyramid- based attention mechanism and the generation of confrontational networks. Firstly, a new pyramidal dual attention module is designed, including channel attention network and spatial attention network. Pyramid pooling is used instead of average pooling and maximum pooling in the channel attention network structure to enhance the feature representation capability from the perspective of global and local information. The spatial attention network structure adopts large scale convolution to expand the integration capability of local information, which can effectively extract texture, high frequency and other information. Secondly, the dense multi-scale feature module is designed to extract feature information at different scales using asymmetric convolution, and the extraction accuracy of texture, high frequency and other information is enhanced by fusing multi-level scale features through dense connection. Experimental validation is performed on the publicly available NWPU- RESISC45 dataset, and the experimental analysis shows that the algorithm outperforms the comparison methods in both subjective visual effect and objective evaluation metrics, and the reconstruction performance is relatively good. 

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.