@Article{cmc.2025.068228,
AUTHOR = {Fatima Khan, Amna Khan, Tariq Ali, Tariq Shahzad, Tehseen Mazhar, Sunawar Khan, Muhammad Adnan Khan, Habib Hamam},
TITLE = {IoT-Driven Pollution Detection System for Indoor and Outdoor Environments},
JOURNAL = {Computers, Materials \& Continua},
VOLUME = {86},
YEAR = {2026},
NUMBER = {2},
PAGES = {1--27},
URL = {http://www.techscience.com/cmc/v86n2/64723},
ISSN = {1546-2226},
ABSTRACT = {The rise in noise and air pollution poses severe risks to human health and the environment. Industrial and vehicular emissions release harmful pollutants such as CO<sub>2</sub>, SO<sub>2</sub>, CO, CH<sub>4</sub>, and noise, leading to significant environmental degradation. Monitoring and analyzing pollutant concentrations in real-time is crucial for mitigating these risks. However, existing systems often lack the capacity to monitor both indoor and outdoor environments effectively.This study presents a low-cost, IoT-based pollution detection system that integrates gas sensors (MQ-135 and MQ-4), a noise sensor (LM393), and a humidity sensor (DHT-22), all connected to a Node MCU (ESP8266) microcontroller. The system leverages cloud-based storage and real-time analytics to monitor harmful gas levels and sound pollution. Sensor data is processed using decision tree algorithms for classification, enabling threshold-based detection with environmental context. A Progressive Web Application (PWA) interface provides users with accessible, cross-platform visualizations.Experimental validation demonstrated the system’s ability to detect pollutant concentration variations across both indoor and outdoor settings, with real-time alerts triggered when thresholds were exceeded. The collected data showed consistent classification of normal, warning, and critical states for methane, CO<sub>2</sub>, temperature, humidity, and noise levels. These results confirm the system’s reliability in dynamic environmental conditions.The proposed framework offers a scalable, energy-efficient, and user-friendly solution for pollution detection and public awareness. Future enhancements will focus on extending the sensor suite, improving machine learning accuracy, and integrating meteorological data for predictive pollution modeling.},
DOI = {10.32604/cmc.2025.068228}
}