INTELLIGENT AIR QUALITY DETECTION DEVICE BASED ON EDGE COMPUTING

Abstract

Air pollution has become a major environmental and public health concern due to rapid industrialization, urbanization, and increased vehicular emissions. Traditional air quality monitoring systems rely on centralized cloud processing, which leads to delays, higher bandwidth consumption, and limited real-time response. To overcome these challenges, this project presents an intelligent air quality detection device based on edge computing for efficient and real-time environmental monitoring. The system integrates multiple gas sensors such as MQ135, MQ7, and MQ2 to detect harmful gases including carbon monoxide, carbon dioxide, ammonia, and smoke, along with a DHT11 sensor for temperature and humidity measurement. These sensors are interfaced with a Raspberry Pi Pico microcontroller, which processes the collected data locally at the edge, reducing latency and dependency on cloud infrastructure. A multilayer Long Short-Term Memory (LSTM) model is implemented for accurate air quality prediction and classification. The system also features an OLED display for real-time visualization and a buzzer alert mechanism when pollution levels exceed safe limits. Wireless communication enables remote monitoring and data transmission. Experimental results show that the system achieves an accuracy of 91.6%, outperforming traditional models such as Multilayer Perceptron (MLP) and Recurrent Neural Network (RNN). The proposed solution is cost-effective, energy-efficient, and suitable for smart city applications, providing a reliable approach for continuous air quality monitoring and environmental protection.