Research on Marine Water Quality Evaluation Model Based on Improved Harmony Search Algorithm by Gaussian Disturbance to Optimize Takagi-Sugeno Fuzzy Neural Network

Abstract

Shen, G., 2020. Research on marine water quality evaluation model based on improved harmony search algorithm by Gaussian disturbance to optimize Takagi-Sugeno fuzzy neural network. In: Liu, X. and Zhao, L. (eds.), Today's Modern Coastal Society: Technical and Sociological Aspects of Coastal Research. Journal of Coastal Research, Special Issue No. 111, pp. 283–287. Coconut Creek (Florida), ISSN 0749-0208.Marine water quality is affected by many factors and is difficult to evaluate accurately. An improved harmony search algorithm based on Gaussian disturbance (GDHS) is proposed to optimize the Takagi-Sugeno (T-S) fuzzy neural network (TSFNN) model of marine water quality evaluation. First, the basic harmony search algorithm is improved by the Gaussian disturbance global optimal harmony strategy and dynamic adjustment parameters. Second, the parameters of the T-S fuzzy neural network are optimized by GDHS to improve the stability and global convergence speed of the TSFNN. Finally, China's marine water quality standards and the actual conditions of the marine area to which the experimental data belong are considered, five indicators are selected to construct a neural network, and the water quality evaluation results of the data of 10 monitoring stations in the eastern waters of Qingdao show that the smaller the evaluation error of the GDHS-TSFNN model, the higher the accuracy.