MUSIC RECOMMENDATION SYSTEM BASED ON COSINE SIMILARITY AND SUPERVISED GENRE CLASSIFICATION

  • Jamie Mayliana Alyza (1) Universitas AMIKOM Purwokerto
  • Fandy Setyo Utomo (2*) Universitas AMIKOM Purwokerto http://orcid.org/0000-0001-6347-6514
  • Yuli Purwati (3) Universitas AMIKOM Purwokerto
  • Bagus Adhi Kusuma (4) Universitas AMIKOM Purwokerto
  • Mohd Sanusi Azmi (5) Universiti Teknikal Malaysia Melaka http://orcid.org/0000-0002-4355-3938

  • (*) Corresponding Author
Keywords: K-Nearest Neighbors, Support Vector Machine, Music, Genre, Classification

Abstract

Categorizing musical styles can be useful in solving various practical problems, such as establishing musical relationships between songs, similar songs, and finding communities that share an interest in a particular genre. Our goal in this research is to determine the most effective machine learning technique to accurately predict song genres using the K-Nearest Neighbors (K-NN) and Support Vector Machine (SVM) algorithms. In addition, this article offers a contrastive examination of the K-Nearest Neighbors (K-NN) and Support Vector Machine (SVM) when dimensioning is considered and without using Principal Component Analysis (PCA) for dimension reduction. MFCC is used to collect data from datasets. In addition, each track uses the MFCC feature. The results reveal that the K-Nearest Neighbors and Support Vector Machine offer more precise results without reducing dimensions than PCA results. The accuracy of using the PCA method is 58% and has the potential to decrease. In this music genre classification, K-Nearest Neighbors (K-NN) and Support Vector Machine (SVM) are proven to be more efficient classifiers. K-Nearest Neighbors accuracy is 64,9%, and Support Vector Machine (SVM) accuracy is 77%. Not only that, but we also created a recommender system using cosine similarity to provide recommendations for songs that have relatively the same genre. From one sample of the songs tested, five songs were obtained that had the same genre with an average accuracy of 80%.

Downloads

Download data is not yet available.

Author Biographies

Jamie Mayliana Alyza, Universitas AMIKOM Purwokerto

Informatics Department, Faculty of Computer Science, Universitas AMIKOM Purwokerto

Fandy Setyo Utomo, Universitas AMIKOM Purwokerto

Informatics Department, Faculty of Computer Science, Universitas AMIKOM Purwokerto.

SCOPUS ID: https://www.scopus.com/authid/detail.uri?authorId=56523214300

SINTA ID: https://sinta.kemdikbud.go.id/authors/profile/256978

Yuli Purwati, Universitas AMIKOM Purwokerto

Informatics Department, Faculty of Computer Science, Universitas AMIKOM Purwokerto.

Scopus ID: https://www.scopus.com/authid/detail.uri?authorId=56523317600

SINTA ID: https://sinta.kemdikbud.go.id/authors/profile/6003052

Bagus Adhi Kusuma, Universitas AMIKOM Purwokerto

Informatics Department, Faculty of Computer Science, Universitas AMIKOM Purwokerto.

Scopus ID: https://www.scopus.com/authid/detail.uri?authorId=57193876167

SINTA ID: https://sinta.kemdikbud.go.id/authors/profile/5986871

Mohd Sanusi Azmi, Universiti Teknikal Malaysia Melaka

ASSOC. PROF DR. MOHD SANUSI AZMI.

Faculty of Information and Communication Technology (FTMK), Universiti Teknikal Malaysia Melaka (UTeM).

Scopus ID: https://www.scopus.com/authid/detail.uri?authorId=57198002453 

References

A. C. M. da Silva, M. A. N. Coelho, and R. F. Neto, “A Music Classification model based on metric learning applied to MP3 audio files,” Expert Syst Appl, vol. 144, pp. 3–35, Apr. 2020.

H. C. Ceylan, N. Hardalaç, A. C. Kara, and F. Hardalaç, “Automatic Music Genre Classification and Its Relation with Music Education,” World Journal of Education, vol. 11, no. 2, p. 36, Apr. 2021.

A. Viloria, O. B. P. Lezama, and D. Cabrera, “Segmentation process and spectral characteristics in the determination of musical genres,” Procedia Comput Sci, vol. 175, pp. 96–101, Aug. 2020.

B. R. Ismanto, T. M. Kusuma, and D. Anggraini, “Indonesian Music Classification on Folk and Dangdut Genre Based on Rolloff Spectral Feature Using Support Vector Machine (SVM) Algorithm,” IJCCS (Indonesian Journal of Computing and Cybernetics Systems), vol. 15, no. 1, p. 11, Jan. 2021.

Sarofi Muhammad Abid As, Irhamah, and Mukarromah Adatul, “Identifikasi Genre Musik dengan Menggunakan Metode Random Forest,” Jurnal Sains dan Seni ITS, vol. 9, no. 1, pp. 1–8, Jun. 2020.

V. Fauziah Ramadhani, B. Hidayat, and Azizah, “STEGANALISIS UNTUK FILE AUDIO BERFORMAT MP3 DENGAN METODE LEAST SIGNIFICANT BIT (LSB) PADA KLASIFIKASI PRINCIPAL COMPONENT ANALYSIS (PCA),” ITN Malang, vol. 3, no. 1, pp. 1–6, 2017.

R. Mayapada, G. M. Tinungki, and N. Sunusi, “Penerapan Sparse Principal Component Analysis dalam Menghasilkan Matriks Loading yang Sparse,” Jurnal Matematika Statistika & Komputasi, vol. 15, no. 2, pp. 44–54, Jan. 2019.

Doshi Sanket, “Music Feature Extraction in Python,” Towards Data Science, Dec. 30, 2018. https://towardsdatascience.com/extract-features-of-music-75a3f9bc265d#:~:text=MFCC%20%E2%80%94%20Mel%2DFrequency%20Cepstral%20Coefficients&text=%3D’time’)-,.,a%20number%20of%20frames%20available. (accessed Jul. 19, 2023).

S. Kumar, “EVALUATING THE EFFECTIVENESS OF MUSIC RECOMMENDATIONS USING COSINE SIMILARITIES OF VARIOUS COMBINED FEATURE SETS CONSISTING OF METADATA AND USER GENERATED TAGS,” North Dakota State University of Agriculture and Applied Science, 2022.

F. S. Utomo, N. Suryana, and M. S. Azmi, “Stemming impact analysis on Indonesian Quran translation and their exegesis classification for ontology instances,” IIUM Engineering Journal, vol. 21, no. 1, pp. 33–50, Jan. 2020.

J. Ho Kin Pou, H. Keshav Rao, G. Bhambhani, J. Joseph, and S. J. Prakash Asst, Music Genre Classification using Machine Learning. Bengaluru: River Publishers, 2020.

Kartik Chaudhary, “Understanding Audio data, Fourier Transform, FFT and Spectrogram features for a Speech Recognition System,” Towards Data Science, Jan. 19, 2020. https://towardsdatascience.com/understanding-audio-data-fourier-transform-fft-spectrogram-and-speech-recognition-a4072d228520 (accessed Jul. 19, 2023).

D. Lionel, R. Adipranata, and E. Setyati, “Klasifikasi Genre Musik Menggunakan Metode Deep Learning Convolutional Neural Network dan Mel-Spektrogram,” Universitas Kristen Petra, vol. 7, no. 1, pp. 1–5, 2020.

U. Ayvaz, H. Gürüler, F. Khan, N. Ahmed, T. Whangbo, and A. A. Bobomirzaevich, “Automatic Speaker Recognition Using Mel-Frequency Cepstral Coefficients Through Machine Learning,” Computers, Materials and Continua, vol. 71, no. 2, pp. 5511–5521, Nov. 2022.

S. Uddin, I. Haque, H. Lu, M. A. Moni, and E. Gide, “Comparative performance analysis of K-nearest neighbour (KNN) algorithm and its different variants for disease prediction,” Sci Rep, vol. 12, no. 1, Dec. 2022.

X. Mu, “Implementation of Music Genre Classifier Using KNN Algorithm,” Highlights in Science, Engineering and Technology CSIC, vol. 34, pp. 149–153, Feb. 2023.

Indrianti Ismayani, “Klasifikasi dengan KNN (K-Nearest Neighbors) menggunakan Python,” Jun. 2019. https://medium.com/@16611086/klasifikasi-dengan-knn-k-nearest-neighbors-menggunakan-python-bf772e8d4ef5 (accessed Jul. 19, 2023).

S. Y. Yehezkiel and Y. Suyanto, “Music Genre Identification Using SVM and MFCC Feature Extraction,” IJEIS (Indonesian Journal of Electronics and Instrumentation Systems), vol. 12, no. 2, p. 115, Oct. 2022.

KANTINIT, “Confusion Matrix: Pengertian, Cara Kerja dan Contoh Soal,” Kantinit, Jan. 09, 2023. https://kantinit.com/kecerdasan-buatan/confusion-matrix-pengertian-cara-kerja-dan-contoh-soal/ (accessed Jul. 19, 2023).

Trivusi, “Metriks Evaluasi Sistem Menggunakan Confusion Matrix,” Trivusi, Jul. 16, 2022. https://www.trivusi.web.id/2022/04/evaluasi-sistem-dengan-confusion-matrix.html (accessed Jul. 20, 2023).

M. Ludewig, I. Kamehkhosh, N. Landia, and D. Jannach, Effective nearest-neighbor music recommendations. Vancouver: Association for Computing Machinery, 2018.

H. Abdulbar, P. P. Adikara, and S. Adinugroho, “Klasifikasi Genre Lagu dengan Fitur Akustik Menggunakan Metode K-Nearest Neighbor,” Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, vol. 3, no. 8, pp. 8259–8268, Aug. 2019.

Published
2023-08-07
How to Cite
[1]
J. Alyza, F. Utomo, Y. Purwati, B. Kusuma, and M. Azmi, “MUSIC RECOMMENDATION SYSTEM BASED ON COSINE SIMILARITY AND SUPERVISED GENRE CLASSIFICATION”, jitk, vol. 9, no. 1, pp. 77 - 80, Aug. 2023.
Article Metrics

Abstract viewed = 321 times
PDF downloaded = 275 times