摘要
针对大气环境的复杂多变性和不确定性,采用太原市2014年至2016年的空气污染物监测数据,分别将改进的粒子群算法(IPSO)和遗传算法(GA)与支持向量机(SVM)相结合,通过参数寻优构建新模型完成对空气质量指数(AQI)的预测.实验结果表明,GA-SVM在预测精度、误差率和可靠性方面均优于IPSO-SVM与SVM.因此GA-SVM模型更适用于AQI的预测,为大气污染防治提供了科学合理的理论依据和新的预测方法.
In view of complexity and uncertainty of the atmospheric environment, in this thesis, through the adoption of the monitoring data of air pollutants in Taiyuan city from 2014 to 2016, the improved particle swarm algorithm (IPSO) and genetic algorithm (GA) are combined with support vector machine (SVM) respectively to predict the air quality index (AQI) by building the model optimization for parameter optimization. The experimental results show that GA-SVM is better than IPSO-SVM and SVM in prediction accuracy, error rate and reliability. Therefore, the GA-SVM model is more suitable for the prediction of AQI, which provides some scientific basis and a new prediction method for the prevention and control of air pollution.
出处
《数学的实践与认识》
北大核心
2017年第12期113-120,共8页
Mathematics in Practice and Theory
基金
国家自然科学基金(61275120)
关键词
粒子群优化算法
遗传算法
支持向量机
信息粒化
空气质量指数预测
particle swarm optimization algorithm
genetic algorithm
support vector ma-chine
information granulation
air quality index prediction