Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
April 13, 2026Journal of Innovative Science and Engineering (JISE)Open Access

Comparative Analysis of SVM, k-NN and Logistic Regression Methods in Classifying Turkish Music Genres

View Full Paper
Ask AI
Bookmark
Share

Authors

MÖMehmet Cüneyt ÖzbalcıBursa Technical UniversityTBTurgay Tugay BilginBursa Technical University

Discussion

Loading...

Member takes

Implication

Analysis demonstrates music genre classification in Turkish music using various machine learning methods, suggesting SVM's top performance.

Key Points

  • The research aims to compare the effectiveness of SVM, k-NN, and Logistic Regression in classifying Turkish music genres.
  • Derived acoustic characteristics using the librosa library.
  • Curated a dataset of 600 WAV music files across six Turkish music genres.
  • Performed classification using SVM, k-NN, and Logistic Regression algorithms.
  • Conducted experiments varying kernel functions and distance metrics.
  • Achieved accuracy rates were 71.88% for k-NN, 73.44% for Logistic Regression, and 78.65% for SVM.
  • SVM outperformed both k-NN and Logistic Regression in terms of accuracy.

Cite This Study

Özbalcı et al. (2026) studied this question.

synapsesocial.com/papers/69dc88583afacbeac03ea302https://doi.org/10.38088/jise.1809289
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Consideration of Environmental, Economic, and Oil Factors for Unit-based Estimation of Consumed Electrical Energy with ML Algorithms: A Case Study of Çanakkale Region2025 · 1 citations
  2. 2Classification of Musical Instruments using SVM and KNN2020 · 24 citations
  3. 3Feedforward joint phase and timing estimation with OQPSK modulation1999 · 20 citations
  4. 4Mood-Based Music Discovery: A System for Generating Personalized Thai Music Playlists Using Emotion Analysis2025 · 4 citations
  5. 5Musical instrument identification using MFCC2017 · 30 citations