Assessment of water resources carrying capacity using chaotic particle swarm genetic algorithm

Abstract

Water resources carrying capacity (WRCC) has been evaluated repeatedly to guide sustainable regional development, with the increasing conflicts over water resources between society and nature. Urban underlying surfaces are constantly changing under the rapid development of urbanization, which has changed the WRCC. The chaotic particle swarm genetic algorithm (CPSGA) is proposed in this study to evaluate the WRCC. It combines the genetic algorithm (GA), chaotic optimization algorithm (COA), and particle swarm optimization (PSO), as well as introduces the chaotic mapping of COA and the velocity position update strategy of PSO into the GA framework to strengthen the population quality and improve the algorithm's efficiency. The effectiveness of CPSGA was demonstrated using three typical functions. Nanjing, China, was used as the study area to evaluate the WRCC from 2015 to 2018. The results showed that the comprehensive evaluation scores of the WRCC of Nanjing from 2015 to 2018 were up to 0.83. In addition, the CPSGA had better astringency and stability than GA, COA, and PSO. The application indicated that the proposed methodology is feasible, providing a reference for conducting WRCC research elsewhere.

Gender-Driven English Speech Emotion Recognition with Genetic Algorithm

“…Metaheuristic algorithms have universal and diverse heuristic strategies [ 10 , 11 ], and they are powerful tools for handling complex optimization problems such as feature selection [ 12 , 13 , 14 ]. A genetic algorithm (GA) mimics the process of natural selection, in which promising individuals are selected for producing the next generation [ 15 , 16 ]. Binary-coded GA can be directly used to solve the selection/non-selection of features, without the need for position transformation [ 17 , 18 ].…”