论文信息 - An Improved BP Neural Network based on IPSO and Its Application

An Improved BP Neural Network based on IPSO and Its Application

Considering the fact that BP Neural Network has the defects of being easily falling into partial extreme value, to avoid the limitation of particle swarm algorithm we come up with an improved BP Neural Network applied in Neural Network training. This method means using nonlinear decreasing weight factor to change the fundamental ways of PSO first, and then using the developed PSO ways to optimize the original weight and threshold value of Neural Network. This method strengthens the ability of BP algorithm to solve the nonlinear problems and improve rapidity of convergence and the ability to search optimal value. We apply the improved particle swarm algorithm to agricultural land classification. Compared with BP method,this kind of algorithm can minimize errors and improve rapidity of convergence at the same time.

Zheng Xie | Lianguang Mo

[1] Junying Chen,et al. A PSO-based subtractive clustering technique for designing RBF neural networks , 2008, 2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence).

[2] Liu Xing. Application of PSO-BP Model in Short-Term Prediction of Urban Water Consumption , 2007 .

[3] Wang Hai-feng. Application in long-term load power forecasting based on modified principal component analysis for radial basic function of neural network , 2007 .

[4] Riccardo Poli,et al. Particle swarm optimization , 1995, Swarm Intelligence.

[5] Zhang Jun. Faster particle swarm optimization with random inertia weight , 2009 .

[6] Wei Zhenchun,et al. Adaptive Particle Swarm Optimization Algorithm and Simulation , 2006 .

[7] R. P. Shimpi,et al. Modified Particle Swarm Optimization , 2009 .

[8] Xu Yu-liang. Speed Control System of Motors Based on Artificial Neural Network Method , 2006 .

[9] Zhang Guo. Optimization model for discharge distribution of irrigation channels based on particle swarm optimizer , 2006 .

[10] Yan Wang,et al. A Modified Particle Swarm Optimization and Radial Basis Function Neural Network Hybrid Algorithm Model and Its Application , 2009, 2009 WRI Global Congress on Intelligent Systems.