A Combined Deep Learning Model Using Selected Important Features And Swarm-Based Optimization To Accurately Predict Air Quality Index

Abstract

Air pollution is a serious problem that affects health and the environment. To help manage this, we developed a deep learning model that combines important input features with a swarm optimization technique to predict the Air Quality Index (AQI) more accurately. Feature selection is used to remove unnecessary data, and swarm optimization helps to choose the best model settings. We tested the model using real air quality data and compared it with other methods. Our approach showed better performance in terms of accuracy, precision, recall, and F1-score, proving that it gives more reliable AQI predictions.