Developing Frugal Internet of Things From Artificial Neural Network to Predict Student Mindfulness Concentration and Relaxation Levels

Indoor environmental quality significantly impacts student learning performance and efficiency. Studies indicate that indoor lighting highly affects student learning performance. Electroencephalography (EEG) is used to analyze the influence of correlated color temperature (CCT) on student learning performance. We developed a frugal Internet of Things (IoT) system to monitor student mindfulness concentration and relaxation levels at different CCTs. The proposed IoT system includes a DHT11 sensor for detecting indoor temperature and humidity, a WS2812B sensor for CCT controlling, a galvanic skin response (GSR) sensor for measuring student stress levels, and a TGAM brainwave module measuring real-time concentration and relaxation levels. An artificial neural network (ANN) model was built using data from multiple sensors to predict student mindfulness levels.