粒子群神经网络混合模型在农用地分等中的应用

Application of Particle Swarm Optimization & Neural Network in Agricultural Land Classification

针对常规农用地分等模型因子权重计算存在人为干扰和神经网络模型自身优化过程中易陷入局部最优的情况,该文综合了BP神经网络非线性权重数据挖掘特性和粒子群的全局优化能力,建立了农用地分等计算的粒子群神经网络混合模型(PSO-BP网络模型),并应用于广东省揭西县农用地分等计算中,发现PSO-BP网络模型能避免定级因子权重确定的人为干扰,同时具有较高的优化效率,应用效果较好。

A PSO-BP network model was designed to solve the problem of weight determining affected by human when using conventional agricultural land classification model and the traditional neural network is easy to fall into local optimum situation in the self-optimization process.This model combines the nonlinear data mining features of the neural network and the global optimization capacity of the particle swarm optimization and it was applied in Jiexi County of Guangdong Province for grading calculation of the agricultural land quality practically.As well as the results showed that the PSO-BP network model can avoid weight factor determining disturbed by human and with high classification efficiency.