ANALISIS KLASIFIKASI GENRE MUSIK MENGGUNAKAN ALGORITMA SUPPORT VECTOR MECHINE (SVM)
Article Sidebar
Read Counter : 2
Download : 5
Main Article Content
Abstract
Music genre classification using 14 parameters, the best model is Support Vector Machine (SVM) with a "poly" kernel. This SVM model managed to achieve high accuracy of around 0.5571 and has a high F1-Score value, making it the main choice in this research. In addition, testing shows that dividing the dataset in a ratio of 60:40 and 70:30 is the most effective in improving model performance. In comparison with the standard algorithm, SVM on a dataset ratio of 70:30 achieved the highest accuracy with a value of 0.5440, F1-Score 0.5396, Recall 0.5440, and Precision 0.5450. This is followed by K-Nearest Neighbors (K-NN) and Decision Tree.
Research results consistently show that SVM with the "poly" kernel provides the best results in music genre classification. Decision Tree with activation criterion "gini" has competitive accuracy, which is around 0.5257. Meanwhile, K-NN with a number of neighbors (k) of around 10 provides an accuracy of around 0.4638, making it a less effective choice in this context. This research provides important insights into the use of music genre classification methods using machine learning algorithms.
Article Details
Section
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Menawarkan akses terbukaReferences
[1] S. Widhyatama, Sejarah musik dan apresiasi seni. PT Balai Pustaka (Persero), 2012.
[2] A. Gabrielsson, Strong Experiences with Music: Music is much more than just music. OUP Oxford, 2011. [Daring]. Tersedia pada: https://books.google.co.id/books?id=qnGqpqoimc4C
[3] M. P. Dewi, “Studi Metaanalisis: Musik untuk menurunkan stres,” Jurnal Psikologi, vol. 36, no. 2, hlm. 106–115, 2009.
[4] P. G. Christenson dan J. B. Peterson, “Genre and gender in the structure of music preferences,” Communic Res, vol. 15, no. 3, hlm. 282–301, 1988.
[5] I. D. Id, Machine Learning: Teori, Studi Kasus dan Implementasi Menggunakan Python, vol. 1. Unri Press, 2021.
[6] E. A. Laksana dan F. Sulianta, “Analisis dan studi komparatif algoritma klasifikasi genre musik,” Semnasteknomedia Online, vol. 5, no. 1, hlm. 1–2, 2017.
[7] S. Walfish, “A review of statistical outlier methods,” Pharmaceutical technology, vol. 30, no. 11, hlm. 82, 2006.
[8] H. Kang, “The prevention and handling of the missing data,” kja, vol. 64, no. 5, hlm. 402–406, Mei 2013, doi: 10.4097/kjae.2013.64.5.402.
[9] M. Montague dan J. A. Aslam, “Relevance score normalization for metasearch,” dalam Proceedings of the tenth international conference on Information and knowledge management, 2001, hlm. 427–433.
[10] M. A. Hearst, S. T. Dumais, E. Osuna, J. Platt, dan B. Scholkopf, “Support vector machines,” IEEE Intelligent Systems and their Applications, vol. 13, no. 4, hlm. 18–28, 1998, doi: 10.1109/5254.708428.
[11] A. Patle dan D. S. Chouhan, “SVM kernel functions for classification,” dalam 2013 International Conference on Advances in Technology and Engineering (ICATE), 2013, hlm. 1–9. doi: 10.1109/ICAdTE.2013.6524743.
[12] S. S. Keerthi dan C. Lin, “Asymptotic Behaviors of Support Vector Machines with Gaussian Kernel,” Neural Comput, vol. 15, no. 7, hlm. 1667–1689, 2003, doi: 10.1162/089976603321891855.
[13] B. Rajagopalan dan U. Lall, “A k‐nearest‐neighbor simulator for daily precipitation and other weather variables,” Water Resour Res, vol. 35, no. 10, hlm. 3089–3101, 1999.
[14] A. J. Myles, R. N. Feudale, Y. Liu, N. A. Woody, dan S. D. Brown, “An introduction to decision tree modeling,” Journal of Chemometrics: A Journal of the Chemometrics Society, vol. 18, no. 6, hlm. 275–285, 2004.
[15] Y.-Y. Song dan L. U. Ying, “Decision tree methods: applications for classification and prediction,” Shanghai Arch Psychiatry, vol. 27, no. 2, hlm. 130, 2015.
[16] R. Susmaga, “Confusion Matrix Visualization,” dalam Intelligent Information Processing and Web Mining, M. A. Kłopotek, S. T. Wierzchoń, dan K. Trojanowski, Ed., Berlin, Heidelberg: Springer Berlin Heidelberg, 2004, hlm. 107–116.
[17] S. A. Livingston dan C. Lewis, “Estimating the consistency and accuracy of classifications based on test scores,” J Educ Meas, vol. 32, no. 2, hlm. 179–197, 1995.
[18] C. Goutte dan E. Gaussier, “A Probabilistic Interpretation of Precision, Recall and F- Score, with Implication for Evaluation,” dalam Advances in Information Retrieval, D. E. Losada dan J. M. Fernández-Luna, Ed., Berlin, Heidelberg: Springer Berlin Heidelberg, 2005, hlm. 345– 359.
[19] I. G. Harsemadi, “Perbandingan Kinerja Algoritma K-NN dan SVM dalam Sistem Klasifikasi Genre Musik Gamelan Bali,” INFORMATICS FOR EDUCATORS AND PROFESSIONAL: Journal of Informatics, vol. 8, no. 1, hlm. 1–10, 2023.
[20] S. Lutfiani, T. H. Saragih, F. Abadi, M. R. Faisal, dan D. Kartini, “Perbandingan Metode Extreme Gradient Boosting Dan Metode Decision Tree Untuk Klasifikasi Genre Musik,” Jurnal Informatika Polinema, vol. 9, no. 4, hlm. 373–382, 2023.