Air quality prediction and analysis using embedded sensors and machine learning

This paper introduces a comprehensive, real-time air quality monitoring and alert system that combines sensor-based hardware with a machine learning model for data classification. The system integrates gas sensors MQ135, MQ2, MQ9, a DHT11 temperature and humidity sensor, and an Arduino Mega 2560 microcontroller. Sensor data is processed using a Python-based Random Forest classifier to predict pollution levels and environmental conditions. Alerts are triggered through buzzers, LCD displays, and GSM-based SMS notifications. Unlike traditional setups requiring Wi-Fi modules, the system transmits data to the ThingSpeak platform using serial communication and Python scripting. This approach offers a scalable and low-cost solution for detecting hazardous gases and abnormal temperatures, making it suitable for residential, industrial, and public safety applications.