Sistem Klasifikasi Emosi Kucing Menggunakan SVM dan Strategi Augmentasi Data
DOI:
https://doi.org/10.29407/2706f967Keywords:
Kucing, Emosi, Klasifikasi, SVM, AugmentasiAbstract
Komunikasi yang baik dengan hewan peliharaan sering kali terganggu karena manusia kurang memahami suara-suara yang dikeluarkan kucing. Penelitian ini bertujuan membuat sistem yang bisa mengklasifikasikan perasaan kucing secara akurat, agar bisa lebih memahami apa yang mereka rasakan. Masalah utama yang dihadapi adalah ketidakseimbangan jumlah data dalam kategori perasaan yang jarang muncul. Untuk mengatasinya, penelitian ini menggunakan algoritma SVM dengan pendekatan augmentasi data berbasis pemrosesan di memori. Metode ini bisa mengubah dan menyeimbangkan data suara dengan efisien, tanpa membebani penyimpanan fisik. Hasil evaluasi menunjukkan model ini mampu mencapai akurasi sebesar 92,94%. Lebih khusus lagi, kategori perasaan yang melalui proses augmentasi berhasil mencapai skor F1 sebesar 1.00, yang membuktikan bahwa metode ini sangat efektif dalam menangani data yang tidak seimbang. Selain itu, sistem juga terbukti tahan terhadap gangguan suara dari lingkungan sekitar. Kesimpulan penelitian ini menyatakan bahwa penggabungan teknik augmentasi sinyal dengan algoritma SVM mampu menghasilkan sistem yang akurat, efisien, dan responsif terhadap berbagai jenis masukan.
Downloads
References
[1] B. Nussberger dkk., “A common statement on anthropogenic hybridization of the European wildcat (Felis silvestris),” Front Ecol Evol, vol. Volume 11-2023, 2023, doi: 10.3389/fevo.2023.1156387.
[2] S. Dwi Permana Putra, F. Fikri, dan O. Tivani Kiki, “Identifikasi Jenis Kucing Berdasarkan Pola Citra Menggunakan Convolutional Neural Network,” Seminar Nasional Teknologi & Sains, vol. 4, no. 1, hlm. 765–770, 2025.
[3] Ú. Morales-Rodríguez, J. Carbajal-Hernández, B. Luna-Benoso, G. De Jesús Rodríguez-Jordán, dan J. C. M. Perales, “Recognition of domestic Felis Catus vocalisations using a computational associative model,” Journal of Animal Behaviour and Biometeorology, hlm., 2024, doi: 10.31893/jabb.2024020.
[4] L. R. Kogan, J. Currin-Mcculloch, C. Bussolari, dan W. Packman, “Cat owners’ disenfranchised guilt and its predictive value on owners’ depression and anxiety,” Human-Animal Interactions, vol. 2023, Jan 2023, doi: 10.1079/HAI.2023.0044;ISSUE:ISSUE:DOI.
[5] S. Schötz, J. van de Weijer, dan R. Eklund, “Context effects on duration, fundamental frequency, and intonation in human-directed domestic cat meows,” Appl Anim Behav Sci, vol. 270, hlm. 106146, 2024, doi: https://doi.org/10.1016/j.applanim.2023.106146.
[6] C. de Mouzon, R. Di-Stasi, dan G. Leboucher, “Human perception of cats’ communicative cues: human‐cat communication goes multimodal,” Appl Anim Behav Sci, vol. 270, hlm. 106137, 2024, doi: https://doi.org/10.1016/j.applanim.2023.106137.
[7] D. de S. Machado, R. R. Vicentini, L. da S. Gonçalves, S. Luchesi, E. Otta, dan A. C. Sant’Anna, “Unraveling Feline Myths: A Review About Misperceptions and Beliefs Surrounding Domestic Cat Behavior,” dalam Pets, MDPI, 2025, hlm. 32.
[8] E. Prato-Previde dkk., “What’s in a Meow? A Study on Human Classification and Interpretation of Domestic Cat Vocalizations,” Animals (Basel), vol. 10, no. 12, hlm. 1–18, Des 2020, doi: 10.3390/ANI10122390.
[9] P. Wei, F. He, L. Li, dan J. Li, “Research on sound classification based on SVM,” Neural Comput Appl, vol. 32, no. 6, hlm. 1593–1607, 2020, doi: 10.1007/s00521-019-04182-0.
[10] S. Kavitha dan J. Manikandan, “Improved methodology of svm to classify acoustic signal by spectral centroid,” Journal of Trends in Computer Science and Smart Technology, vol. 3, no. 4, hlm. 294–304, 2022.
[11] T. Liu, D. Yan, R. Wang, N. Yan, dan G. Chen, “Identification of Fake Stereo Audio Using SVM and CNN,” Information, vol. 12, no. 7, hlm. 263, Jun 2021, doi: 10.3390/info12070263.
[12] Md. R. Ansari, S. A. Tumpa, J. A. F. Raya, dan M. N. Murshed, “Comparison between Support Vector Machine and Random Forest for Audio Classification,” dalam 2021 International Conference on Electronics, Communications and Information Technology (ICECIT), IEEE, Sep 2021, hlm. 1–4. doi: 10.1109/ICECIT54077.2021.9641152.
[13] R. A. A., M. Nasrun, dan C. Setianingsih, “Human Emotion Detection with Speech Recognition Using Mel-frequency Cepstral Coefficient and Support Vector Machine,” dalam 2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS), IEEE, Apr 2021, hlm. 1–6. doi: 10.1109/AIMS52415.2021.9466077.
[14] “Cat Meow Classification.” Diakses: 7 Desember 2025. [Daring]. Tersedia pada: https://www.kaggle.com/datasets/andrewmvd/cat-meow-classification
[15] “Cat Sound Classification Dataset.” Diakses: 7 Desember 2025. [Daring]. Tersedia pada: https://www.kaggle.com/datasets/yagtapandeya/cat-sound-classification-dataset
[16] P. Singh, N. Singh, K. K. Singh, dan A. Singh, “Chapter 5 - Diagnosing of disease using machine learning,” dalam Machine Learning and the Internet of Medical Things in Healthcare, K. K. Singh, M. Elhoseny, A. Singh, dan A. A. Elngar, Ed., Academic Press, 2021, hlm. 89–111. doi: https://doi.org/10.1016/B978-0-12-821229-5.00003-3.
[17] C. Miller, T. Portlock, D. M. Nyaga, dan J. M. O’Sullivan, “A review of model evaluation metrics for machine learning in genetics and genomics,” Frontiers in Bioinformatics, vol. 4, hlm. 1457619, Sep 2024, doi: 10.3389/FBINF.2024.1457619/FULL.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Rizky Ananda Putra, Alif Rama Nugroho
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work’s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
