Smart Cities-Based Improving Atmospheric Particulate Matters Prediction Using Chi-Square Feature Selection Methods by Employing Machine Learning Techniques

Particulate matter is emitted from diverse sources and affect the human health very badly. Dust particles exposure stated environment can our heart lungs The particle pollution creates a variety of problems including nonfatal attacks, premature deaths in people with lung or disease, asthma, difficulty breathing, etc. In this article, we developed an automated tool by computing multimodal features to capture dynamics ambient particulate then applied Chi-square feature selection method acquire most relevant features. We also optimized parameters robust machine learning algorithms further improve prediction performance such as Decision Tree, SVM Linear Regression, Naïve Bayes (NB), Random Forest (RF), Ensemble Classifier, K-Nearest Neighbor, XGBoost for classification. classification results without methods yielded highest detection random forest, GBM 100% accuracy AUC. revealed that proposed methodology more provide efficient system will detect matters automatically help individuals their lifestyle comfort. concerned department monitor individual’s healthcare services reduce mortality risk.