Rancangan Machine Learning untuk Mendeteksi Lagu Plagiat

  • Dominggo Pratama Sidauruk Udayana University
  • I Gusti Ngurah Anom Cahyadi Putra Universitas Udayana

Abstract

Plagiarism in the music industry is a serious issue that requires advanced solutions. This research proposes a Machine Learning-based system for detecting song plagiarism by combining Convolutional Neural Network (CNN) and Dynamic Time Warping (DTW). CNN is used to extract features from the visual representation of music notations, while DTW measures the temporal distance between two sequences of notations. Experimental results show that this system provides a more accurate solution with an accuracy of 92.71%, with a dataset of 4800 data points.


Keywords: Music plagiarism, Convolutional Neural Network (CNN), Dynamic Time Warping (DTW), plagiarism detection, music notation, machine learning

Published
2024-05-01
How to Cite
SIDAURUK, Dominggo Pratama; ANOM CAHYADI PUTRA, I Gusti Ngurah. Rancangan Machine Learning untuk Mendeteksi Lagu Plagiat. Jurnal Nasional Teknologi Informasi dan Aplikasnya, [S.l.], v. 2, n. 3, p. 545-554, may 2024. ISSN 3032-1948. Available at: <https://ojs.unud.ac.id/index.php/jnatia/article/view/116053>. Date accessed: 14 dec. 2024. doi: https://doi.org/10.24843/JNATIA.2024.v02.i03.p13.

Most read articles by the same author(s)

Obs.: This plugin requires at least one statistics/report plugin to be enabled. If your statistics plugins provide more than one metric then please also select a main metric on the admin's site settings page and/or on the journal manager's settings pages.