Abstract

Air quality prediction is considered one of complex problems. This is due to volatility, dynamic nature, and high variability in space and time of particulates and pollutants. Meanwhile, designing an automated model for monitoring and predicting air quality becomes more and more relevant, particularly in urban regions. Air pollution can significantly affect the environment and eventually citizens’ health. In this paper, one of the popular machine learning algorithms, the neural network algorithm, is employed to classify different species of air pollutants. To boost the performance of the traditional neural network, the war strategy optimization algorithm tunes the neural network’s parameters. The experimental results demonstrate that the proposed optimized neural network based on the war strategy algorithm can accurately classify air pollutant species.

中文翻译：

---

基于战争策略优化算法的优化神经网络空气污染物分类

摘要

空气质量预测被认为是复杂的问题之一。这是由于颗粒物和污染物的波动性、动态性以及空间和时间的高度可变性。与此同时，设计用于监测和预测空气质量的自动化模型变得越来越重要，特别是在城市地区。空气污染会严重影响环境并最终影响公民的健康。本文采用流行的机器学习算法之一——神经网络算法来对不同种类的空气污染物进行分类。为了提高传统神经网络的性能，战争策略优化算法调整神经网络的参数。实验结果表明，所提出的基于战争策略算法的优化神经网络能够准确地对空气污染物种类进行分类。