基于自适应小波过程神经元网络的人口预测研究  

Research of Population Forecast Based on the Model of Adaptive Wavelet PNN

作　　者：刘金月[1] 许少华[1] 

机构地区：[1]大庆石油学院计算机与信息技术学院,黑龙江大庆163318

出　　处：《长江大学学报（自科版）（上旬）》2008年第4期236-237,240,共3页JOURNAL OF YANGTZE UNIVERSITY (NATURAL SCIENCE EDITION) SCI ＆ ENG

摘　　要：针对复杂非线性系统建模、时变过程信号处理的问题,提出了一种基于小波变换和过程神经元网络的自适应小波过程神经元网络模型。模型为3层结构,输入层完成连续信号的输入,隐层由过程神经元结点组成,采用小波基函数作为激励函数,用于完成输入信号的空间聚合和向输出层的映射功能,输出层完成隐层输出信号的时、空聚合运算和系统输出。给出了学习算法,并以人口预测为例验证了模型和算法的有效性。In view of complex nonlinear system modeling and time-varying process signal processing problem,this paper proposed an adaptive wavelet PNN model based on wavelet transform and process neural network.The model had three layers,the input layer accomplished continuous signal input,The hidden layer was composed of procedure neurons,used wavelet function as incentive function,and accomplishes input signal aggregation in space and transfered the input signals to the output layer.The output layer accomplishes output signal aggregation in both space and time,and fulfills system output.The learning algorithm is given,and the effectiveness of the model and algorithm is proved by population forecast as an example.

关 键 词：小波交换 过程神经元网络 小波神经网络 学习算法 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]