Computer Engineering and Applications ›› 2009, Vol. 45 ›› Issue (21): 218-221.DOI: 10.3778/j.issn.1002-8331.2009.21.063

• 工程与应用 • Previous Articles     Next Articles

Model and application research on parallel hybrid neural network

CAO Yun-zhong   

  1. Information & Engineering Technology Institute,Sichuan Agricultural University,Yaan,Sichuan 625014,China
  • Received:2009-02-10 Revised:2009-04-17 Online:2009-07-21 Published:2009-07-21
  • Contact: CAO Yun-zhong



  1. 四川农业大学 信息与工程技术学院,四川 雅安 625014
  • 通讯作者: 曹云忠

Abstract: Single neural network is difficult in performing accurate predictions for complex model.A hybrid model,which involves a radial basis function network,a multi-layer perception network with back-propagation and a control module,is proposed and used for forecasting complex system.The control module serves as a linear mapping network which combines the outputs of two neural networks to gain the final output value.The prediction methods of the hybrid model are mainly discussed:Firstly,the improved algorithm is taken to train two networks respectively and the output values are obtained;Secondly,the linear mapping network is optimized by self-adaptive genetic algorithm to gain higher prediction accuracy;Finally,this paper has carried out two experiments to compare the prediction performance of a single network and the proposed model.The experimental results show that the proposed hybrid neural network provides a superior performance in prediction accuracy than other methods and offers a common tool for complex prediction.

Key words: radial basis function, Back Propagation(BP) neural network, hybrid network model, data prediction, linear mapping

摘要: 单一神经网络难以对复杂模型做出准确的预测,提出了一种并联型混合神经网络模型用于对复杂的系统进行预测,该模型由径向基函数网络、BP网络和控制模块组成。控制模块用于线性映射层,将两种单一神经网络的输出结合并得到最终的输出结果。详细地给出了混合模型的预测方法:首先,利用改进算法分别训练径向基函数网络和BP网络;其次,采用自适应遗传算法优化线性映射层以获得更好的预测精度;最后,利用两个实例比较单一神经网络和提出的混合网络的预测性能。实验表明,混合神经网络在预测精度上比单一网络具有更优的性能,同时,该混合模型为复杂系统提供了一种通用的预测工具。

关键词: 径向基函数, BP神经网络, 混合网络模型, 数据预测, 线性映射