Bumil Bahagia Smart Home System: Genre-Based Music Recommendations for Postpartum Mothers Using SVM Classification

• Published in: 2024 7th International Conference of Computer and Informatics Engineering (IC2IE) pp. 1 - 7
• Main Authors: Fatichin, Mochammad Rizqul, Aulia Vinarti, Retno, Muklason, Ahmad, Riksakomara, Edwin
• Format: Conference Proceeding
• Language: English
• Published: IEEE 12.09.2024
• Subjects: Accuracy; audio signal processing; Classification algorithms; Kernel; Medical treatment; Multiple signal classification; Music; music recommendation system; postpartum depression; Recommender systems; Signal processing algorithms; support vector machine; Support vector machines; Vectors
• DOI: 10.1109/IC2IE63342.2024.10748191

Postpartum Depression is a mental health disorder in postpartum mothers. Overcoming the anxiety at an early stage are important to prevent and reduce symptoms and their impact on maternal health and child development. Music therapy is one of the treatments that can give soothness and is easy to apply. In providing therapy, the selection of music that can soothe and match with mother's preference is important. This study aims to develop a soothing music recommendations system for mothers at risk of PPD. The recommendations are made based on the similarity of music, considering the music genre classification. The music genre classification was built by utilizing the musical features that generated from audio signal processing and using the Support Vector Machine (SVM) algorithm as a classifier. Five music recommendations were generated based on the similarity between music features which are good for classifying genres. The results of this study show that the genre classification, that is part of the recommendation system, has an accuracy value of 80% with a precision of 82% and a recall of 80%. Removing some redundant and irrelevant features can improve the quality of music genre classification.