Implementasi SuperTML Untuk Klasifikasi Genre Musik Indonesia
DOI:
https://doi.org/10.59581/harmoni-widyakarya.v1i4.1516Keywords:
SuperTML, Densenet, Genre, MusikAbstract
Music genres are becoming increasingly diverse, and many people listen to music because it has benefits such as refreshing, motivating or therapeutic. However, with the increasing number of genres, some listeners have a tendency towards the type of genre they like. In Indonesia itself, there are several popular music genres such as pop, folk, rock, indie and dangdut. Classification of music genres is an interesting topic when looking at this behaviour. Several approaches to classify popular music genres include audio and tabular data approaches. In this research, classifying music genres using an image approach by implementing SuperTML to change the form of tabular data into image form, which is then trained using a pre-trained CNN Densenet, succeeded in achieving an accuracy of 67%.
References
Arjaya, D. (2016). Dangdut dan Rezim Orde Baru: Wacana Nasionalisasi Musik Dangdut Tahun 1990-an. Universitas Gajah Mada, 12.
Ayu, G., & Giri, V. M. (2017). KLASIFIKASI DAN RETRIEVAL MUSIK BERDASARKAN GENRE (SEBUAH STUDI PUSTAKA). In Jurnal Ilmiah ILMU KOMPUTER Universitas Udayana: Vol. X (Issue 1). www.allmusic.com
Lidinillah Alfath, N., Emanuela, O., & Alya Fatma, dan. (2022). PENGARUH MUSIK POPULER DALAM MEMBANTU TINGKAT PEMAHAMAN PEMBELAJARAN MATEMATIKA TERHADAP SISWA SMA (Vol. 2, Issue 1).
Phung, V. H., & Rhee, E. J. (2019). A High-accuracy model average ensemble of convolutional neural networks for classification of cloud image patches on small datasets. Applied Sciences (Switzerland), 9(21). https://doi.org/10.3390/app9214500
West, Jeremy; Ventura, Dan; Warnick, Sean (2007). "Spring Research Presentation: A Theoretical Foundation for Inductive Transfer". Brigham Young University, College of Physical and Mathematical Sciences. Archived from the original on 2007-08-01. Retrieved 2007-08-05.
B. Sun et al., “SuperTML: Two-dimensional word embedding for the precognition on structured tabular data,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW), Jun. 2019, pp. 1–9
G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 4700–4708
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 Joni Bastian, Made Hanindia Prami Swari, Andreas Nugroho Sihanto
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
