Paper Title
Smart Indoor Air Quality Monitoring and Control Using Sensor Networks and Machine Learning

Abstract
Indoor air quality is a serious concern in recent times. People spend most of their time indoors like homes, offices and closed buildings etc. Accessing the air quality of the indoor environment is crucial as pollutants such as particulate matter(PM 2.5 and PM10), volatile organic compounds(VOCs), and Carbon Di-oxide(CO2) can lead to various health problems. Coupled with the threats posed by gas leaks, it presents both serious health implications and property damage if left unnoticed. To address these challenges, we propose a system that will monitor and control air quality. The IoT enabled network of sensors and devices captures real-time data from the subject, which applies Long Short-Term Memory models for predictive analysis and uses Random Forest algorithms for precise classification and anomaly detection. This not only provides real-time analysis through an easy-to-use app, but also allows us to automatically change things based on this information in order to maintain a good air quality level. This solution utilizes sensor networks and robust machine learning techniques that will contribute to improving the management of the indoor environment, addressing issues that are related to health and improving their lifestyle. Keywords - IAQ (Indoor Air Quality), LSTM, Random Forest, IOT, Air Quality Sensors, Carbon Dioxide (CO₂), Particulate Matter (PM2.5, PM10)