PERBANDINGAN PERFORMA METODE NAIVE BAYES DAN SUPPORT VECTOR MACHINE DALAM KLASIFIKASI GENRE MUSIK BERDASARKAN EKSTRAKSI FITUR SINYAL AUDIO MENGGUNAKAN MEL-FREQUENCY CEPSTRAL COEFFICIENTS (MFCC)

NASERWAN, KEVIN PUTRAYUDHA and Miraswan, Kanda Januar (2024) PERBANDINGAN PERFORMA METODE NAIVE BAYES DAN SUPPORT VECTOR MACHINE DALAM KLASIFIKASI GENRE MUSIK BERDASARKAN EKSTRAKSI FITUR SINYAL AUDIO MENGGUNAKAN MEL-FREQUENCY CEPSTRAL COEFFICIENTS (MFCC). Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021282126083.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021282126083_TURNITIN.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (4MB)
	Text RAMA_55201_09021282126083_0009019002_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_55201_09021282126083_0009019002_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021282126083_0009019002_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (386kB) | Request a copy
	Text RAMA_55201_09021282126083_0009019002_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021282126083_0009019002_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (709kB) | Request a copy
	Text RAMA_55201_09021282126083_0009019002_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (136kB) | Request a copy
	Text RAMA_55201_09021282126083_0009019002_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (106kB) | Request a copy
	Text RAMA_55201_09021282126083_0009019002_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (132kB) | Request a copy

Abstract

Music genre classification has become a research topic that is gaining increasing attention, especially with the emergence of digital music platforms. One of the relevant features extracted from audio signals and capturing important characteristics of sound is MFCC, which is widely recognized as an effective technique. This study applies Naive Bayes and SVM algorithms for classification on a collection of music datasets, with each genre represented by its own MFCC feature. The performance of these methods is evaluated using standard metrics such as accuracy, precision, recall, and F1 score. The results show that SVM shows superior performance in terms of classification accuracy. SVM achieves an accuracy of 95.25%, much better than Naive Bayes which only reaches 50.37%. In addition, the average performance difference between the two models is quite large, with SVM showing more consistent performance across configurations. This study concludes that SVM is better than Naive Bayes in music genre classification with MFCC feature extraction.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Naive Bayes, Support Vector Machine, music genre classification, Mel-Frequency Cepstral Coefficients (MFCC), pemrosesan sinyal audio
Subjects:	T Technology > T Technology (General) > T1-995 Technology (General)
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Kevin Putrayudha Naserwan
Date Deposited:	09 Jan 2025 03:08
Last Modified:	09 Jan 2025 03:08
URI:	http://repository.unsri.ac.id/id/eprint/163270

Actions (login required)

View Item