Assessing Real-Time Health Impacts of outdoor Air Pollution through IoT Integration

Abstract

Air pollution constitutes a significant global challenge in both public health and the environment, particularly for countries undergoing industrialization and transitioning from low- to middle-income economies. This study aims to investigate the feasibility and effectiveness of a real-time air quality prediction system based on data collected from Internet of Things (IoT) sensors to help people and public institutions track and manage atmospheric pollution. The primary objective of this study was to investigate whether an IoT-based approach can provide accurate and continuous real-time air quality forecasting. The standard dataset provided by the Indian government was analyzed using regression, traditional Long-Short-Term Memory (LTSM), and bidirectional LSTM (BLSTM) models to evaluate their performance on multivariate air quality features. The results show that the proposed BLSTM model outperformed the other models in minimizing RMSE errors and avoiding overfitting.