A Modified Model with Genetic Optimization Algorithm for Land Evaluation

Abstract

Trained speed of model based on traditional BP neural network was slowly and produced emanative result. A novel land evaluation model based on neural network with genetic optimization algorithm was presented in this paper. The neural network of model is front-network which comprised with five layers architecture which composed of dynamic inference with fuzzy rules where the consequent sub-models are implemented by recurrent neural networks. The recurrent neural networks with internal feedback paths and dynamic neuron synapses. In order to optimized the parameter structure and link weight between layers, the author adopted genetic algorithm into model. Experiment results demonstrated that the novel model exhibit superior performance such as enhanced representation power, calculation speed and veracity of result than traditional BP neural network and the other land evaluation models.