An improved cohesive hierarchical clustering for indoor air quality monitoring in smart gymnasium with healthy sport areas

Abstract

With the rise of healthy lifestyles, sports arenas have become important exercise venues for people. However, indoor air quality issues are becoming increasingly prominent, posing a potential threat to the health of athletes. Traditional indoor air quality monitoring systems often suffer from problems such as unreasonable layout of monitoring points and inaccurate data processing, making it difficult to effectively cope with complex indoor environments. This article proposes an intelligent monitoring system for indoor air quality in sports venues based on an improved cohesive hierarchical clustering algorithm to address these issues. The system optimizes the layout of monitoring points, combines real-time data collection on the Android platform, and accurately processes non smooth data using an improved cohesive hierarchical clustering algorithm based on BiLSTM. The experimental results show that the algorithm not only improves the accuracy of monitoring point selection, but also optimizes the number of monitoring points and effectively supplements missing data. In addition, the algorithm significantly reduces computational complexity and improves computational efficiency while ensuring clustering quality. Application testing shows that the indoor air environment monitoring system constructed in this article can obtain and analyze data in real time, effectively control the concentration of key pollutants such as PM2.5 and carbon dioxide, and create a healthier sports environment for sports venues. This study provides new ideas and methods for indoor air quality monitoring, which has important practical application value.