Design and Implementation of an Air Quality Monitoring System Based on TurMass Technology

Air quality is crucial to the health of Zhoushan residents as well as the development of its fisheries and tourism. However, conventional monitoring methods are limited in real-time performance, data transmission, and scalability, making them inadequate to meet the demands of smart city initiatives that require high spatiotemporal resolution data and effective early-warning capabilities. To address these challenges, this paper presents an air quality monitoring system based on TurMass wireless communication technology, which achieves real-time collection and reporting of gaseous pollutant concentrations. The proposed system not only provides long transmission distances and high reliability but also demonstrates low power consumption and stable data transmission in edge computing scenarios. In addition, a deep learning prediction model integrating CNN, LSTM, and a self-developed attention mechanism is constructed to efficiently extract spatiotemporal features and capture dynamic changes at key time steps, thereby achieving excellent prediction accuracy in experiments. Through seamless integration with SpringBoot and Echarts for data visualization, the system supports comprehensive monitoring and visualization functions, offering strong technical support for the smart city development of Zhoushan.