基于IPSO-BP神经网络的WSNs数据融合算法

WSNs data fusion algorithm based on IPSO-BP neural network

针对无线传感器网络(WSNs)数据融合算法中反向传播(BP)神经网络存在对初值敏感、收敛速度慢、易陷入局部最优解等问题,提出基于改进粒子群优化BP(IPSO-BP)神经网络的WSNs数据融合算法。首先,用细菌觅食算法的趋化、迁徙算子对粒子群优化(PSO)算法进行改进;然后,用IPSO算法优化BP神经网络的权值和阈值,再引入到WSNs数据融合中,簇成员节点负责采集监测数据,在簇首节点通过优化后的BP神经网络对数据进行特征提取,并将融合结果发送至汇聚节点。仿真结果表明:IPSO-BP算法能有效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。

In order to solve the problems of back propagation(BP)neural network in data fusion algorithm of wireless sensor networks(WSNs),such as sensitive to initial values,slow convergence rate and easy to fall into local optimal solution,a WSNs data fusion algorithm based on improved particle swarm optimization BP(IPSO-BP)neural network is presented.Firstly,the particle swarm optimization(PSO)algorithm is improved by using the chemotaxis and migration operators of the bacterial foraging algorithm.Then,the weight and threshold values of the BP neural network are optimized by IPSO algorithm.Then,it is introduced into WSNs data fusion.Cluster member nodes are responsible for collecting monitoring data.At the first node of the cluster,the optimized BP network is used to extract features of the data.The fusion results are sent to the Sink node.The simulation results show that the IPSO-BP algorithm can effectively improve the fusion precision and convergence speed,reduce redundant data transmission,and extend the network life cycle.