IoT-Driven classroom air quality management with deep hierarchical cluster analysis

Poor classroom air quality and high levels of dust have a detrimental impact on student health, comfort, and productivity. To address this issue, we propose an IoT enabled system for monitoring and predicting classroom air quality and dust levels. The system employs multiple sensors placed inside the classroom to collect air quality data. Deep hierarchical cluster analysis is utilized to group the data at different levels of granularity, enabling the extraction of meaningful insights from large volumes of data and revealing trends and patterns that may be challenging to identify using conventional techniques. The work aims to comprehend the factors influencing classroom air quality and dust levels and develop an accurate prediction model. We leverage machine learning algorithms, specifically deep hierarchical cluster analysis, to uncover hidden patterns and relationships within the data. By applying deep hierarchical cluster analysis, we categorize the air quality and dust levels of a classroom into distinct clusters or groups based on data point similarity. Subsequently, a Long Short-Term Memory (LSTM) model is developed based on the cluster analysis results to predict air quality and dust levels. The results showed that the system is suitable for real-time implementation, indicating its potential to be used in practical applications.