针对无线传感器网络（WSN）数据融合算法中传统反向传播（BP）神经网络收敛速度慢、对初值敏感和易陷入局部最优解的问题，提出基于改进粒子群的BP神经网络WSN数据融合算法（BSO-BP）。用天牛须搜索（BAS）算法对粒子群算法进行改进，利用改进后的粒子群算法优化BP神经网络权值和阈值，引入WSN数据融合中，簇首节点通过优化训练后的BP神经网络对采集数据进行特征提取，将融合后的数据发送至汇聚节点。仿真实验表明，BSO-BP算法能有效地提高融合精度和收敛速度，减少冗余数据传输，延长网络生命周期。相较于传统BP数据融合算法和PSO-BP算法，BSO-BP算法减少了至少11%的平均相对误差和13.89%的均方根误差。
Back-propagation (BP) neural network has low convergence speed, is sensitive to the initial value, and easily falls into the local optimal solution in data fusion algorithms in wireless sensor network (WSN). To solve these problems, a data fusion algorithm based on improved particle swarm optimization BP neural network in WSN (BSO-BP) is proposed. The beetle antennae search(BAS) algorithm is used to improve the particle swarm optimization. Then the imporved particle swarm optimization is used to optimize the BP neural network weights and thresholds, which are applied to WSN data fusion. The cluster head nodes extract the feature of the collected data by optimizing the trained BP neural network, and send the merged data to the sink node. Simulation results show that BSO-BP algorithm effectively improves the fusion accuracy and convergence speed, decreases the redundant data communication and prolongs network lifetime. BSO-BP algorithm reduces the relative error by 12.4% and the root-mean-square error by 11%, compared to BP and PSO-BP algorithms.
[1] Lin D, Wang Q, Lin D, et al. An energy-efficient clustering routing protocol based on evolutionary game theory in wireless sensor networks[J]. International Journal of Distributed Sensor Networks, 2015,2015:1-12.
[2] Heinzelman W R, Chandrakasan A, Balakrishnan H. Energy-efficient communication protocol for wireless microsensor networks[C]//Proceedings of the 33rd Annual Hawaii International Conference on System Sciences. Hawaii:IEEE, 2000:1-10.
[3] 孙凌逸, 黄先祥, 蔡伟, 等.基于神经网络的无线传感器网络数据融合算法[J].传感技术学报,2011,24(1):122-127.
[4] Boyinbode O, Le H, Mbogho A, et al. A survey on clustering algorithms for wireless sensor networks[C]//2010 IEEE 13th International Conference on Network-based Information Systems. Takayama:IEEE, 2010:358-364.
[5] 成瑜娟, 张敏洪. 感应半径可调的无线传感器网络生命周期的研究[J].中国科学院研究生院学报, 2011, 28(6):768-775.
[6] 李兆祥. 无线传感器网络数据融合的算法研究[D]. 武汉:武汉理工大学, 2011.
[7] 赵亚光. 基于蚁群算法和BP神经网络的WSN数据融合算法研究[D]. 昆明:云南大学, 2013.
[8] 陈秋红, 郭猛. 基于PSO-BP的无线传感器网络数据融合算法研究[J]. 计算机测量与控制, 2014, 22(4):1212-1214.
[9] Kennedy J, Eberhart R. Particle swarm optimization[C]//Proceedings of ICNN'95-International Conference on Neural Networks. Perth:IEEE, 1995:1942-1948.
[10] Wang T, Yang L, Liu Q. Beetle swarm optimization algorithm:theory and application[J]. arXiv preprint arXiv:1808.00206, 2018.
[11] 胡强, 王海涛, 底楠, 等. 无线传感网中一种智能数据融合算法的实现及仿真分析[J]. 传感技术学报,2018, 31(2):283-288.
[12] Jiang X Y, Li S. BAS:beetle antennae search algorithm for optimization problems[J/OL]. International Journal of Robotics and Control, 2018[2019-03-05]. https://arxiv.org/pdf/1710.10724.pdf.
[13] 刘杨, 田学锋, 詹志辉. 粒子群优化算法惯量权重控制方法的研究[J]. 南京大学学报(自然科学版),2011,47(4):364-371.
[14] 张震, 魏鹏, 李玉峰,等. 改进粒子群联合禁忌搜索的特征选择算法[J]. 通信学报, 2018,39(12):60-68.
[15] 焦李成, 杨淑媛, 刘芳, 等. 神经网络七十年:回顾与展望[J]. 计算机学报, 2016, 39(8):1697-1716.
[16] 段大高, 谢永恒, 盖新新, 等. 基于神经网络的微博虚假信息识别模型[J]. 信息网络安全, 2017, 17(9):134-137
[17] 胡向东, 李秋实. 基于人工鱼群算法优化神经网络的WSN数据融合[J]. 重庆邮电大学学报(自然科学版), 2018, 30(5):614-619.
[18] Ishizuka M, Aida M. Performance study of node placement in sensor network[C]//24th International Conference on Distributed Computing Systems. Hachioji:IEEE, 2004:598-603.
[19] Guidoni D L,Boukerche A, Villas L A,et al. A tree-based approach to design heterogeneous sensor networks based on small world concepts[C]//2011 IEEE 36th Conference on Local Computer Networks. Bonn:IEEE, 2011:666-672.
