IoT-Driven Air Quality Monitoring and Predictive Analytics Framework Using Machine Learning for Enhanced Indoor Environmental HealthOpen Access

Abstract

Humans are susceptible to poor indoor air quality, but there are ways to prevent this. This study describes a method for monitoring and detecting indoor air quality to assess many parameters, including carbon dioxide, volatile organic compounds (VOCs), PM2.5, PM10 particulate matter, carbon monoxide, ozone, nitrogen dioxide, sulfur dioxide, temperature, and humidity. The device collects real-time air quality data using microcontrollers and advanced sensor technology. Consolidating all of this data onto a single platform facilitates continuous monitoring and enables rapid response. The primary goal is to maintain air quality standards within safe and optimal limits to improve occupant comfort and health. Preliminary testing in several confined environments has demonstrated its effectiveness in providing accurate and timely air quality information. This modular device will serve as a critical tool for achieving optimal indoor air quality due to its ease of installation and real-time monitoring capabilities. Predictive analytics will be integrated into future developments to facilitate proactive management of anticipated air quality issues.