Pattern Classification and Prediction of Water Quality by Neural Network with Particle Swarm Optimization

Water pollution has posed a severe problem in modern society. Evaluation of water quality is a meaningful topic today. To identify the specific water category and predict the water quality in the future, a particle swarm optimization (PSO) based artificial neural network (ANN) approach is presented. The data investigated from the Yangtze River are chosen as the original cases to construct the ANN model and testify both the classification and prediction ability of this method. Compared with other classical methods, the proposed one can obtain high quality and efficiency without losing computational expense. Experimental results show PSO is a robust training algorithm and could be extended to other real world pattern classification and prediction applications