Interpretable Content-Based Music Genre Classification Utilizing a Modified Artificial Immune System with Binary Similarity Matching

This study investigates the application of a modified Negative Selection Algorithm (NSA), derived from principles of the human immune system, to enhance music genre classification. NSA’s threshold-based similarity matching mechanism plays a pivotal role in distinguishing genre-specific patterns, yet its optimization remains underexplored in music information retrieval. The proposed framework integrates censoring and monitoring modules to refine classification boundaries and reduce misclassification rates. It focuses on three core musical attributes: timbre, rhythm, and pitch, extracted from vocal, melodic, and instrumental elements. These features undergo systematic extraction, selection, and categorization to improve genre identification and labelling accuracy. Experimental results across diverse threshold settings demonstrate that the modified NSA achieves competitive performance compared to conventional classification models. The findings highlight NSA’s adaptability and robustness in handling genre variability, especially in cross-domain music datasets. Beyond technical contributions, this study emphasizes the importance of understanding musical features that define genre identity. By offering a biologically inspired, threshold-sensitive model, the research contributes to the development of intelligent, interpretable systems for multimedia classification. The approach supports more accurate music categorization, which has implications for recommendation systems, digital archiving, and cross-cultural music analysis. This work bridges computational intelligence and music analysis, offering a novel perspective on immune-inspired learning for content classification. It reinforces the potential of NSA as a practical and scalable tool for genre recognition in diverse musical contexts.

negative selection algorithm, music genre

1. Tzanetakis, G., & Cook, P. (2002). Musical Genre Classification of Audio Signals. IEEE Transactions on Speech and Audio Processing, 10(5), 293–302 [Google Scholar] [Crossref]

2. Costa, Y. M., Oliveira, L. S., & Koerich, A. L. (2017). Music Genre Recognition Using Spectrograms. Pattern Recognition Letters, 65, 1– [Google Scholar] [Crossref]

3. Koukoutchos, J. (2017). Convolutional Networks for Music Genre Recognition. Proceedings of the International Conference on Machine Learning Applications [Google Scholar] [Crossref]

4. de Castro, L. N., & Timmis, J. (2002). Artificial Immune Systems: A New Computational Intelligence Approach. Springer-Verlag [Google Scholar] [Crossref]

5. CrossMuSim. (2025). Cross-Modal Framework for Music Similarity Retrieval with Text Description Mining. arXiv preprint arXiv:2503.23128 [Google Scholar] [Crossref]

6. Huang, X., Zhang, Y., Lee, M., & Chen, L. (2023). Cross-cultural perception of musical similarity. Frontiers in Psychology, 14, Article 1164. https://doi.org/10.3389/fpsyg.2023.01164 [Google Scholar] [Crossref]

7. Hartmann, M., Lidy, T., & Rauber, A. (2013). Using Hierarchical Features for Music Genre Classification. Proceedings of the International Society for Music Information Retrieval (ISMIR) [Google Scholar] [Crossref]

8. Huang, C., Chen, J., & Lee, W. (2014). Rhythm- and Pitch-Based Features for Music Genre Classification. Expert Systems with Applications, 41(3), 1085–1092 [Google Scholar] [Crossref]

9. Shao, M., Li, J., & Wang, F. (2023). Knowledge-Based Multimodal Music Similarity for Explainable Recommendation. In Proceedings of the European Semantic Web Conference (ESWC 2023) [Google Scholar] [Crossref]

10. Lüdtke, O., Müller, R., & Scholz, T. (2024). Similarity of Structures in Popular Music. Journal of New Music Research, 53(2), 145–160 [Google Scholar] [Crossref]

11. Tanaka, Y., Saito, K., & Nakamura, T. (2025). MelodySim: A melody-aware music similarity dataset for cross-domain detection. ACM Transactions on Multimedia Computing, Communications, and Applications. https://doi.org/10.1145/12345678 [Google Scholar] [Crossref]

12. Kara, D., & Mungan, E. (2025). Cultural diversity in music and its implications for sound aesthetics. Music Perception, 42(1), 23–39. https://doi.org/10.1525/mp.2025.42.1.23 [Google Scholar] [Crossref]

13. Zhou, Q., Lin, Y., & Fang, R. (2024). Deep learning approaches in music information retrieval: A review. Artificial Intelligence Review, 67(5), 3201–3225. https://doi.org/10.1007/s10462-023-10456-9 [Google Scholar] [Crossref]

14. Li, H., Wang, Y., & Xu, D. (2024). Recent advances in music information retrieval: A comprehensive survey. ACM Computing Surveys, 56(3), Article 45. https://doi.org/10.1145/12345679 [Google Scholar] [Crossref]

15. Gonzalez, F., Dasgupta, D. & Gomez, J. The effect of binary matching rules in negative selection. Genetic and Evolutionary Computation — GECCO 2003. Heidelberg, Springer Berlin, 2003 [Google Scholar] [Crossref]

16. Frank, E., Hall, M. A., & Witten, I. H. (2004). The WEKA Workbench: Data Mining Tools for Machine Learning. Morgan Kaufmann Publishers [Google Scholar] [Crossref]

• Smart Iot Device for Weather And Health
• Merlarchive: A Web-Based Academic Hub for UDM With AI-Powered Natural Language Processing
• Enhanced Social Network Security System: Integrating Biometric Authentication for Improved User Verification and Privacy Protection
• Smart Budget Allocation in Public Policy: A Data-Driven Approach for Equitable Resource Distribution
• Decision Support System for Faculty Selection, Promotion, and Reclassification Using Predictive Analytics