改进的无线传感网混沌Hopfield盲检测算法  

An improved blind detection algorithm of chaos Hopfield neural network for wireless sensor networks

作　　者：张昀[1] 于舒娟[1] 刘欢[1] 

机构地区：[1]南京邮电大学电子科学与工程学院,江苏南京210003

出　　处：《电子技术应用》2014年第11期95-97,101,共4页Application of Electronic Technique

基　　金：国家自然科学基金项目(61302155);校引进人才项目(NY212022)

摘　　要：在密集部署的无线传感器网络中,相邻传感器的信号可能高度相关。在无线传感网传输模型分簇的基础上,针对Hopfield神经网络极易陷入局部最优解、收敛速度慢等缺陷,利用混沌序列的遍历性和类随机性,提出一种改进的混沌Hopfield盲检测算法解决无线传感网簇内传感器信号盲检测问题。算法的思想是:利用混沌映射产生初始发送序列,并且在算法出现早熟收敛时进行小幅度的混沌扰动,借此降低算法的误码率。仿真结果表明,改进的混沌Hopfield神经网络算法所需数据量极短,从而成功实现簇内簇首传感器信号盲检测。In densely deployed wireless sensor networks,signals of adjacent sensors can be highly cross-correlated.An improved algorithm of chaos Hopfield neural network is proposed to blind detection inter-cluster signals of wireless sensor networks.In order to overcome premature convergence and slow convergence speed of Hopfield neutral network,the novel algorithm takes advantages of the stochastic and ergodic properties of chaotic sequence.The initial transmitting sequence is generated by chaotic disturbance and the chaos perturbation is introduced in a small range when the global optimal value is trapped in local minimum.Simulation results show that the algorithm needs shorter received signals and show high speed to blindly detect signals of sensor inter-cluster.

关 键 词：无线传感网 混沌映射 盲检测 HOPFIELD神经网络 

分 类 号：TN929.5[电子电信—通信与信息系统]