Air Quality Monitoring and Prediction Through IOT Sensor Network data Using Machine Learning and Deep Learning Algorithms

Air pollution, such as the quantity of PM2.5 and PM10, is one of the most significant variables affecting human health. Due to a lack of air pollution measuring stations near the user, it is challenging to obtain accurate information. In order to efficiently measure and forecast air quality using various machine learning and deep learning techniques, our research uses data gathered by both fixed and mobile IOT sensors that are mounted on vehicles patrolling the area. By utilising LSTM, SVM, random Forest Algorithm, Gradient Boosting algorithms for learning and training data, we proposed a method for the prediction of air pollution. The test’s findings demonstrate the performance of the air pollution prediction system and model that proposed deviation.