AI-Based PM2.5 Classification for Health Monitoring
Ajay Vishwakarma
, Amit Kumar Pandey , Santosh Singh , Vishal Singh
PM2.5 Prediction, Classification Models, Air Quality Monitoring, Environmental Health
This research delves into the predictive modeling of PM2.5 concentrations in India, employing advanced machine learning techniques to tackle the pressing issue of air quality, which poses significant threats to both public health and the environment. Utilizing a comprehensive dataset that includes timestamps, PM2.5 readings, and key temporal features—such as year, month, day, and hour—this study formulates a binary classification target variable to identify instances where PM2.5 levels exceed a predefined threshold. A range of classification algorithms, including Decision Trees, Random Forest, Gradient Boosting, AdaBoost, and a Voting Classifier, were deployed to assess their predictive efficacy in forecasting elevated PM2.5 concentrations. The models were rigorously trained and evaluated through an 80-20 data split, with performance metrics—such as accuracy, precision, and recall—highlighting the superior performance of both the Random Forest and Voting Classifier models. Additionally, visualizations, including scatter plots and time-series graphs, were employed to reveal underlying patterns and trends in PM2.5 levels throughout the day. This study offers invaluable insights into the dynamics of air quality in India and underscores the transformative potential of machine learning in environmental monitoring and informed public health policymaking.
"AI-Based PM2.5 Classification for Health Monitoring", IJSDR - International Journal of Scientific Development and Research (www.IJSDR.org), ISSN:2455-2631, Vol.10, Issue 3, page no.b411-b417, March-2025, Available :https://ijsdr.org/papers/IJSDR2503150.pdf
Volume 10
Issue 3,
March-2025
Pages : b411-b417
Paper Reg. ID: IJSDR_301092
Published Paper Id: IJSDR2503150
Downloads: 000140
Research Area: Science and Technology
Country: Mumbai, Maharastra, India
ISSN: 2455-2631 | IMPACT FACTOR: 9.15 Calculated By Google Scholar | ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 9.15 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publisher: IJSDR(IJ Publication) Janvi Wave
