Impact of Music Teaching on Student Mental Health Using IoT, Recurrent Neural Networks, and Big Data Analytics

In recent years, technological improvements have provided remarkable possibilities for examining the association between education and mental health. However, an in-depth analysis is still needed to assess the impact of specific educational interventions on students. This paper proposes a new approach to measure music education’s positive impact on students by utilizing the desirable features of Big Data and the Internet of Things (IoT). Dependent on data collection, feature extraction, and predictive modeling with built-in Recurrent Neural Networks (RNNs) for LSTM layers, the proposed approach correlates and gives insights into the link between musical education and mental health. The framework forms the basis for thorough analysis by utilizing sensors to monitor physiological parameters such as heart rate and other relevant parameters concerning environment monitoring. The proposed model offers descriptive, diagnostic, predictive, and prescriptive insights using RNNs to predict data patterns, predict mental health trends, and utilize big data analytics to pinpoint influential factors. The study improves students’ mental health during music lessons by enabling the training of RNN models on the captured data, which revealed notable correlations between musical engagements. Furthermore, predictive analytics recommend personalized interventions to boost mental health benefits. The experimental results highlight the efficacy of technology-enhanced music education, with the proposed model showcasing superior performance metrics: accuracy (0.886), sensitivity (0.823), specificity (0.901), F1 score (0.841), MCC (0.724), MSE (0.106), MAE (0.261), and RMSE (0.321). The proposed model’s superiority validates comparative analysis with various learning algorithms, including Logistic Regression, Decision Tree, Random Forest, Gradient Boosting, K-Nearest Neighbors, Support Vector Machine, and Neural Network.