基于卷积神经网络的无线传感器网络链路异常检测算法

doi:10.13229/j.cnki.jdxbgxb.20230224

摘要/Abstract

摘要：

为精准检测无线传感器网络异常链路，提出基于CNN的无线传感器网络链路异常检测算法。采用并发多线程技术设计网络链路异常检测功能，利用CNN建立网络链路异常检测训练模型。输入网络链路数据，卷积处理网络链路信息，提取网络链路特征向量，并通过下采函数处理，分析网络链路异常行为，使用向量映射方式表示异常部分向量，经过Softmax函数分类器完成分类检测。实验结果表明：本文方法能有效提升链路异常分类精度和检测精度，且用时较短。

关键词: 无线传感器网络, 卷积神经网络, 卷积运算, 激活函数, 下采样层, 链路特征

Abstract:

To accurately detect abnormal links in wireless sensor networks， a CNN based wireless sensor network link anomaly detection algorithm is proposed. Design network link anomaly detection function using concurrent multithreading technology， and establish a training model for network link anomaly detection using CNN. Input network link data， convolve network link information， extract network link feature vectors， and analyze network link abnormal behavior through down sampling function processing. Use vector mapping to represent the abnormal part vector， and complete classification detection through Softmax function classifier. The experimental results show that the proposed method can effectively improve the accuracy of link anomaly classification and detection， and it takes a short time.

Key words: wireless sensor network, convolution neural network, convolution operation, activation function, lower sampling layer, link characteristics

中图分类号:

TP391

特木尔朝鲁朝鲁,张亚萍. 基于卷积神经网络的无线传感器网络链路异常检测算法[J]. 吉林大学学报(工学版), 2024, 54(8): 2295-2300.

Chao-lu TEMUR,Ya-ping ZHANG. Link anomaly detection algorithm for wireless sensor networks based on convolutional neural networks[J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(8): 2295-2300.

图/表 4

图1

图2

图3

图4

参考文献 20

1	杨亚让, 吴云虎. 基于随机森林的无线传感器通信网络阻塞故障检测[J]. 吉林大学学报:工学版, 2023, 53(5): 1490-1495.
	Yang Ya-rang, Wu Yun-hu. Blockage fault detection of wireless sensor communication network based on random forest[J]. Journal of Jilin University (Engineering and Technology Edition), 2023, 53(5):1490-1495.
2	刘拥民, 杨钰津, 罗皓懿, 等. 基于双向循环生成对抗网络的无线传感网入侵检测方法[J]. 计算机应用, 2023, 43(1):160-168.
	Liu Yong-min, Yang Yu-jin, Luo Hao-yi, et al. Wireless sensor network intrusion detection method based on two-way cyclic generation countermeasures network[J]. Computer Application, 2023,43 (1): 160-168.
3	刘敏. 基于深度学习的光纤网络链路缺陷数据检测及研究[J]. 激光杂志, 2021, 42(8):108-114.
	Liu Min. Data detection and research of optical network link defects based on deep learning[J]. Laser Journal, 2021,42(8): 108-114.
4	郁滨, 熊俊. 基于平衡迭代规约层次聚类的无线传感器网络流量异常检测方案[J]. 电子与信息学报, 2022, 44(1): 305-313.
	Yu Bin, Xiong Jun. A novel wsn traffic anomaly detection scheme based on BIRCH[J]. Journal of Electronics & Information Technology, 2022, 44(1): 305-313.
5	Kumar Gupta S, Kumar S, Tyagi S. Energy efficient and effective node deployment for wireless sensor network[J]. International Journal of Communication Systems, 2022, 35(9): 21535139.
6	Envelope A J. Dynamic coordinator management for balancing data flow in the wireless sensor network[J]. IFAC-PapersOnLine, 2022, 55(4): 115-120.
7	杨彩云, 汪小东, 汪晨, 等. 基于移动Sink的带状无线传感器网络数据汇聚方法研究[J]. 传感技术学报, 2022, 35(4): 550-557.
	Yang Cai-yun, Wang Xiao-dong, Wang Chen, et al. Research on data aggregation method of banded wsn based on mobile sink[J]. Chinese Journal of Sensors and Actuators, 2022,35(4): 550-557.
8	张书毓, 施伟斌, 王文龙, 等. 基于线性回归的无线传感器网络链路质量估计方法研究[J]. 计算机应用研究, 2022, 39(7): 2132-2136, 2155.
	Zhang Shu-yu, Shi Wei-bin, Wang Wen-long, et al. Research on link quality estimation method for wireless sensor networkbased on linear regression[J]. Application Research of Computers, 2022,39(7): 2132-2136, 2155.
9	高文志, 王彦军, 王欣伟, 等. 基于卷积神经网络的柴油机失火故障实时诊断[J]. 吉林大学学报:工学版, 2022, 52(2):417-424.
	Gao Wen-zhi, Wang Yan-jun, Wang Xin-wei, et al. Real-time diagnosis for misfire fault of diesel engine based on convolutional neural network[J]. Journal of Jilin University (Engineering and Technology Edition), 2022, 52(2): 417-424.
10	李红艳, 李春庚, 安居白, 等. 注意力机制改进卷积神经网络的遥感图像目标检测[J]. 中国图象图形学报, 2019, 24(8): 1400-1408.
	Li Hong-yan, Li Chun-geng, An Ju-bai, et al. Attention mechanism improves CNN remote sensing image object detection[J]. Journal of Image and Graphics, 2019, 24(8): 1400-1408.
11	Gan J H, Teh P C. Detection of plant diseases using deep learning based on convolution neural network (CNN)[J]. I-Manager's Journal on Image Processing, 2021, 8(4): 1-8.
12	Bai S, Bao F, Zhao F. On the efficiency of a cfd-based full convolution neural network for the postprocessing of field data[J]. Fluid Dynamics & Materials Processing, 2021, 17(1): 39-47.
13	张志超, 王剑, 章隆兵, 等. 面向目标检测的卷积神经网络优化方法[J]. 高技术通讯, 2022, 32(3):227-238.
	Zhang Zhi-chao, Wang Jian, Zhang Long-bing, et al. Convolutional neural network optimization method for object detection[J]. Chinese High Technology Letters, 2022, 32(3): 227-238.
14	Sinha R, Sur R, Sharma R, et al. Anomaly detection using system logs: a deep learning approach[J]. International Journal of Information Security and Privacy (IJISP), 2022, 16(1): 1-15.
15	王慧珍, 王立德, 杨岳毅, 等. 基于Logistic集成学习的列车MVB网络异常检测方法研究[J]. 机车电传动, 2021(1):138-144.
	Wang Hui-zhen, Wang Li-de, Yang Yue-yi, et al. Anomaly detection for MVB network based on logistic ensemble learning [J]. Electric Drive for Locomotives, 2021 (1): 138-144.
16	Safaei M, Driss M, Boulila W, et al. Global outliers detection in wireless sensor networks: a novel approach integrating time‐series analysis, entropy, and random forest‐based classification[J]. Software: Practice and Experience, 2022, 52(1): 277-295.
17	Alzubi O A. A deep learning-based frechet and dirichlet model for intrusion detection in IWSN[J]. Journal of Intelligent & Fuzzy Systems, 2022, 42(2): 873-883.
18	阮峻, 孙豪, 朱志俊, 等. 直流控保系统光纤链路微弱故障的定位[J]. 中国激光, 2021, 48(20): 113-119.
	Ruan Jun, Sun Hao, Zhu Zhi-jun, et al. Location of weak faults in optical fiber links of direct current control and protection system[J]. Chinese Journal of Lasers, 2021, 48(20): 113-119.
19	Liu C, Su X, Li C. Edge computing for data anomaly detection of multi-sensors in underground mining[J]. Electronics, 2021, 10(3): 302-311.
20	张帆, 黄赟, 方子茁, 等. 卷积神经网络的损失最小训练后参数量化方法[J]. 通信学报, 2022, 43(4):114-122.
	Zhang Fan, Huang Yun, Fang Zi-zhuo, et al. Lost-minimum post-training parameter quantization method for convolutional neural network[J]. Journal on Communications, 2022, 43(4): 114-122.

相关文章 15

[1]	朱圣杰,王宣,徐芳,彭佳琦,王远超. 机载广域遥感图像的尺度归一化目标检测方法[J]. 吉林大学学报(工学版), 2024, 54(8): 2329-2337.
[2]	赵宏伟,武鸿,马克,李海. 基于知识蒸馏的图像分类框架[J]. 吉林大学学报(工学版), 2024, 54(8): 2307-2312.
[3]	张锦洲,姬世青,谭创. 融合卷积神经网络和双边滤波的相贯线焊缝提取算法[J]. 吉林大学学报(工学版), 2024, 54(8): 2313-2318.
[4]	王晓莹,陈小海. 嵌入式无线传感器网络多链路传输随机退避算法[J]. 吉林大学学报(工学版), 2024, 54(7): 2057-2062.
[5]	魏晓辉,王晨洋,吴旗,郑新阳,于洪梅,岳恒山. 面向脉动阵列神经网络加速器的软错误近似容错设计[J]. 吉林大学学报(工学版), 2024, 54(6): 1746-1755.
[6]	孙铭会,薛浩,金玉波,曲卫东,秦贵和. 联合时空注意力的视频显著性预测[J]. 吉林大学学报(工学版), 2024, 54(6): 1767-1776.
[7]	夏超,王梦佳,朱剑月,杨志刚. 基于分层卷积自编码器的钝体湍流流场降阶分析[J]. 吉林大学学报(工学版), 2024, 54(4): 874-882.
[8]	张云佐,郭威,李文博. 遥感图像密集小目标全方位精准检测算法[J]. 吉林大学学报(工学版), 2024, 54(4): 1105-1113.
[9]	段锦,姚安妮,王震,于林韬. 改进的麻雀搜索算法优化无线传感器网络覆盖[J]. 吉林大学学报(工学版), 2024, 54(3): 761-770.
[10]	杨国俊,齐亚辉,石秀名. 基于数字图像技术的桥梁裂缝检测综述[J]. 吉林大学学报(工学版), 2024, 54(2): 313-332.
[11]	车翔玖,徐欢,潘明阳,刘全乐. 生物医学命名实体识别的两阶段学习算法[J]. 吉林大学学报(工学版), 2023, 53(8): 2380-2387.
[12]	张楠,史建华,亿吉,王平. 基于加权质心定位的井下移动目标实时跟踪方法[J]. 吉林大学学报(工学版), 2023, 53(5): 1458-1464.
[13]	张振海,季坤,党建武. 基于桥梁裂缝识别模型的桥梁裂缝病害识别方法[J]. 吉林大学学报(工学版), 2023, 53(5): 1418-1426.
[14]	刘培勇,董洁,谢罗峰,朱杨洋,殷国富. 基于多支路卷积神经网络的磁瓦表面缺陷检测算法[J]. 吉林大学学报(工学版), 2023, 53(5): 1449-1457.
[15]	高海龙,徐一博,侯德藻,王雪松. 基于深度异步残差网络的路网短时交通流预测算法[J]. 吉林大学学报(工学版), 2023, 53(12): 3458-3464.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed