Adaptive Indoor Air Quality Monitoring System using Iot Sensors And Deep Learning

Air pollution is a major risk to public health and environmental sustainability. This paper introduces an IoT- based air quality monitoring system that uses deep learning to offer real-time pollution evaluation. The system incorporates several gas and particulate matter sensors, such as MQ-7, MQ-135, MQ-4, a PM2.5 dust sensor, and a temperature sensor, to gather environmental information. The ESP32 controller sends the reading from sensors to a cloud portal (Blynk), on which there exists a learned deep learning model with three output classifications: good, moderate, and bad" The determined status is updated on an LCD display screen and gives instantaneous visible feedback together with actionable tips in the form of air is clean!, stay cautious!, or avoid outdoors!. It keeps getting refreshed in real time, keeping up with the real-time pollution measurement. Experimental outcomes prove the efficiency of the model in detecting air quality status, which is an indication of its suitability for wide-scale application. This study advances the construction of low-cost, smart air monitoring systems that can support public awareness and decision-making towards healthier surroundings.