The Application of Rough Set Neural Networks of GSS-PSO in the Risk Evaluation of Collapse and Rockfall Disasters

摘要

In this paper, an intelligent prediction approach based on the neural networks rough set of a Genetic Selection Strategy Particle Swarm Optimization Algorithm (GSS-PSO) is proposed to measure the risky area caused by slope. With this approach, the attribute reduction method based on neighborhood rough set is adopted to conduct the attribute reduction, then the genetic strategy is used to reform the particle swarm optimization (PSO), and the reformed method will replace the traditional BP algorithm to train the weight and threshold value of the neural networks. Finally the well-trained neural networks will be used to evaluate the risk of collapse and rockfall. The result of simulation indicates that this new approach reduce the complexity of neural networks, save the training and enhances the precision of prediction.