Indoor air quality (IAQ) has a significant impact on human health and comfort, especially in environments where people spend a majority of their time indoors. This paper presents an intelligent indoor air quality monitoring and forecasting system based on Internet of Things (IoT) and machine learning techniques. The proposed system integrates multiple sensors, including DHT11 for temperature and humidity measurement, MQ-135 for gas and carbon dioxide (CO₂) detection, and a particulate matter sensor (PMS) for monitoring PM1, PM2.5, and PM10 levels. The collected environmental data is processed using a Raspberry Pi and transmitted to the cloud platform for real-time visualization. A Random Forest algorithm is employed to analyze historical data and predict future air quality conditions, enabling proactive decision-making. Additionally, an alert mechanism using a buzzer and GSM module is implemented to notify users through SMS when pollutant levels exceed predefined safety thresholds. Experimental results obtained from real-time sensor data and ThingSpeak visualization demonstrate the effectiveness of the system in monitoring environmental parameters and detecting hazardous conditions. The proposed system is cost-effective, scalable, and suitable for applications in smart homes, offices, and industrial environments
Rohini et al. (Thu,) studied this question.