Performance Comparison of KNN and CNN in Classifying Balinese Gangsa Instrument Tones

Balinese traditional music, particularly the Gamelan Gangsa, represents a unique aspect of Indonesia’s cultural heritage. Despite its cultural significance, the study and teaching of this instrument face challenges, particularly in tone standardization and the availability of effective learning tools. This research addresses these challenges by exploring the application of Artificial Intelligence (AI) technologies specifically K-Nearest Neighbors (KNN) and Convolutional Neural Networks (CNN) in the identification and classification of Gamelan Gangsa tones. The study involved the creation of a dataset comprising audio recordings of the instrument, followed by the development and evaluation of KNN and CNN models. The results indicate that KNN, with an accuracy of 90%, outperformed CNN, which achieved an accuracy of 85%. The findings suggest that KNN is particularly effective in distinguishing subtle tonal differences, making it a valuable tool for supporting traditional music education. This research not only contributes to the technical understanding of Gamelan Gangsa’s acoustic characteristics but also underscores the potential of AI in cultural preservation. The development of AI-based tone identification systems can facilitate the teaching and learning of traditional music, ensuring its transmission to future generations. The study serves as a foundation for further exploration into the integration of AI technologies with cultural heritage, demonstrating how modern innovations can enhance the appreciation and understanding of traditional arts.