无线传感器网络中基于粒子群优化的目标识别方法

Target classification algorithm based on particle swarm optimization in wireless sensor networks

针对无线传感器网络在地面目标声振信号识别方面的应用需求,在分析现有算法缺点的基础上,提出了基于粒子群优化(particle swarm optimization,PSO)方法的目标识别算法。利用粒子群算法优化基于模糊逻辑规则的分类器(fuzzy logic rule based classifier,FLRBC),分析了算法中各个参数的设置对算法性能的影响。基于实地采集到的信号的仿真实验表明,该方法在一定程度上提高了目标识别的正确率和稳定性,平衡了分类性能,改善了收敛性质。

To satisfy the requirement of application on classification of acoustic-seismic signals of ground targets in wireless sensor networks,a target classification algorithm based on particle swarm optimization（PSO）,which is used to train the fuzzy logic rule based classifier（FLRBC）,is proposed after analyzing the shortages of existing algorithms,and effects of parameters on performance are analyzed.Experiments based on real signals indicate that this method can improve the classification rate and stability to a certain extent,balance the classification performance and enhance the convergence quality.