DETECTION OF AIR POLLUTION USING MACHINE LEARNING ALGORITHMS

Abstract

Air pollution monitoring is crucial for protecting public health and the environment. “Traditional methods that utilize machine learning (ML) and deep learning (DL) techniques—such as Random Forest (RF), Support Vector Machines (SVM), and Long Short-Term Memory Networks (LSTM)”—are commonly used to predict the Air Quality Index (AQI). However, these methods often face challenges such as high computational demands, reliance on large datasets, and limited responsiveness to real-time air quality changes. In response, we introduce the Rule-Based Weighted Air Quality Estimation Model (RWAQEM), an innovative and computationally efficient solution designed for real-time applications. By leveraging weighted pollutant concentration calculations, geographic context adjustments, and the inclusion of Gaussian noise, RWAQEM provides a dynamic AQI assessment. Unlike traditional ML methods, which require substantial resources, RWAQEM operates with constant-time complexity, making it highly suitable for integration into Internet of Things (IoT) frameworks. Extensive evaluations demonstrate that RWAQEM achieves an impressive accuracy rate of 94.8% while computing AQI scores in a rapid 0.0004 seconds, showcasing its advantage over ML models in real-time processing and competitive accuracy.