Abstract: In day today’s World pollution is major issue in the country and also whole world. This paper presents a machine learning (ML)- based approach for forecasting air quality. Governments primarily employ air quality monitoring systems to regulate the release of harmful substances into the atmosphere. In addition to ensuring the population's general welfare and quality of life, this also helps to support the agricultural and industrial sectors. Based on the amount of PM2.5 in the gathered dataset, air quality Predicted.ML techniques such as Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), and Neural Network (NN) are examined. A model is built using training data, and its performance is assessed using test data. Precision, recall, F1 score, and support are utilized as performance evaluation metrics. In places with a high population density, such major cities, air pollution is a serious issue. A range of emissions caused by human activities have an impact on the quality of the air, including driving, using electricity, and burning fuel. All businesses, from early-stage startups to major platform providers, have made machine learning and its components one of their main areas of Concentration. In the realm of machine learning, an artificial intelligence device gathers sensor data and learns how to behave.

Keywords: Air Quality Index, Machine Learning, Regression, Random Forest, Particulate Matter.

PDF | DOI: 10.17148/IJARCCE.2023.12319

Open chat
Chat with IJARCCE