论文部分内容阅读
针对目前较严重的雾霾污染,雾霾天气预报显得十分重要,通过将改进人工鱼群算法和分形学习相结合,提出了基于人工鱼群和分形学习的雾藕天气预报方法.首先对人工鱼群算法离散化改进,结合分形学习理论降维雾霾数据;其次运用支持向量机和5-折交叉验证技术分类分布可能不平坦的数据集;最后建立雾霾天气预报模型.实验结果表明,数据降维后更有利于提高分类器性能,与传统预报方法相比,预报性能更优,具有较高的稳定性和可信性.
In view of the more serious haze pollution, it is very important to forecast the hazy weather. By combining the improved artificial fish swarm algorithm and fractal learning, a method of forecasting the fog lotus root based on artificial fish swarm and fractal learning is proposed.First, artificial fish Based on the theory of fractal learning, the data of fog smog is reduced. Secondly, the data set which may be unevenly distributed by using support vector machine and 5-fold cross validation is established. Finally, the haze weather forecast model is established. The experimental results show that the data After dimension reduction, it is more beneficial to improve the performance of classifier. Compared with the traditional prediction methods, the prediction performance is better and has higher stability and credibility.