Perancangan Algoritma SVM untuk Pengembangan Model Pendeteksi Bahasa Isyarat Berbasis Landmark
DOI:
https://doi.org/10.29407/9esmzh27Abstract
Penelitian ini mengembangkan sistem pengenalan alfabet Bahasa Isyarat Indonesia (SIBI/BISINDO) berbasis MediaPipe Hands untuk mendukung komunikasi inklusif. Sistem ini membandingkan kinerja empat algoritma klasifikasi Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), Convolutional Neural Network (CNN), dan Random Forest (RF)—pada dataset yang terdiri dari 1.000 citra tangan mewakili 26 huruf. Ekstraksi 21 titik landmark menghasilkan vektor fitur berdimensi 42, kemudian dinormalisasi menggunakan skala min-max dan dibagi menjadi 80% data pelatihan dan 20% data pengujian. Hasil evaluasi menunjukkan bahwa CNN mencapai akurasi tertinggi sebesar 98,2% meski memerlukan waktu pelatihan terlama. Sementara itu, RF menawarkan keseimbangan antara akurasi (96,5%) dan efisiensi komputasi. SVM dan MLP mencapai akurasi 95,1% dan 97,3%. Alur terintegrasi menyoroti trade-off antara akurasi dan kecepatan pemrosesan, krusial untuk perangkat terbatas. Temuan ini menjadi dasar pengembangan teknologi asistif bahasa isyarat dan memperluas akses komunikasi inklusif bagi penyandang tunarungu dan tunawicara.
Keywords:
Bahasa Isyarat, Algortima SVM, landmark tangan##plugins.themes.default.displayStats.downloads##
References
[1] D. Fan, M. Yi, W. Kang, Y. Wang, and C. Lv, “Continuous sign language recognition algorithm based on object detection and variable-length coding sequence,” Sci Rep, vol. 14, no. 1, p. 27592, Dec. 2024, doi: 10.1038/s41598-024-78319-0.
[2] M. Farid Naufal, S. Ferdiana Kusuma, and P. Korespondensi, “ANALISIS PERBANDINGAN ALGORITMA MACHINE LEARNING DAN DEEP LEARNING UNTUK KLASIFIKASI CITRA SISTEM ISYARAT BAHASA INDONESIA (SIBI)”, doi: 10.25126/jtiik.2023106828.
[3] H. ZainEldin et al., “Active convolutional neural networks sign language (ActiveCNN-SL) framework: a paradigm shift in deaf-mute communication,” Artif Intell Rev, vol. 57, no. 6, Jun. 2024, doi: 10.1007/s10462-024-10792-5.
[4] T. W. Chong and B. G. Lee, “American sign language recognition using leap motion controller with machine learning approach,” Sensors (Switzerland), vol. 18, no. 10, Oct. 2018, doi: 10.3390/s18103554.
[5] A. M. Ambarak and A. Z. Falani, “PENGEMBANGAN APLIKASI BAHASA ISYARAT INDONESIA BERBASIS REALTIME VIDEO MENGGUNAKAN MODEL MACHINE LEARNING,” JIKA (Jurnal Informatika), vol. 7, no. 1, p. 89, Feb. 2023, doi: 10.31000/jika.v7i1.7277.
[6] M. Kakizaki, A. S. M. Miah, K. Hirooka, and J. Shin, “Dynamic Japanese Sign Language Recognition Throw Hand Pose Estimation Using Effective Feature Extraction and Classification Approach,” Sensors, vol. 24, no. 3, Feb. 2024, doi: 10.3390/s24030826.
[7] D. S. Ariansyah and D. S. Ariansyah, “PENDETEKSI KATA DALAM BAHASA ISYARAT MENGGUNAKAN ALGORITMA YOLO VERSI 8,” Jurnal Informatika dan Teknik Elektro Terapan, vol. 12, no. 3, Aug. 2024, doi: 10.23960/jitet.v12i3.4904.
[8] B. Alabduallah, R. Al Dayil, A. Alkharashi, and A. A. Alneil, “Innovative hand pose based sign language recognition using hybrid metaheuristic optimization algorithms with deep learning model for hearing impaired persons,” Sci Rep, vol. 15, no. 1, Dec. 2025, doi: 10.1038/s41598-025-93559-4.
[9] D. S. Ariansyah and D. S. Ariansyah, “PENDETEKSI KATA DALAM BAHASA ISYARAT MENGGUNAKAN ALGORITMA YOLO VERSI 8,” Jurnal Informatika dan Teknik Elektro Terapan, vol. 12, no. 3, Aug. 2024, doi: 10.23960/jitet.v12i3.4904.
[10] P. Mandarani and Y. Putra, “APLIKASI BAHASA ISYARAT UNTUK TUNA RUNGU MENGGUNAKAN PLATFORM ANDROID,” Jurnal Teknoif Teknik Informatika Institut Teknologi Padang, vol. 8, no. 1, pp. 47–52, Apr. 2020, doi: 10.21063/jtif.2020.v8.1.47-52.
[11] A. F. Deleviar, Intan Oktaviani, and Hanifah Permatasari, “Pengembangan Website Speech To Video Bahasa Isyarat Indonesia (Bisindo) Berbasis Algoritma Long Shot Term Memory,” Infotek: Jurnal Informatika dan Teknologi, vol. 8, no. 1, pp. 23–33, Jan. 2025, doi: 10.29408/jit.v8i1.26117.
[12] F. Zhang et al., “MediaPipe Hands: On-device Real-time Hand Tracking,” Jun. 2020, [Online]. Available: http://arxiv.org/abs/2006.10214
[13] F. N. Rahmah, “PROBLEMATIKA ANAK TUNARUNGU DAN CARA MENGATASINYA,” QUALITY, vol. 6, no. 1, p. 1, Jun. 2018, doi: 10.21043/quality.v6i1.5744.
[14] A. Sultan, W. Makram, M. Kayed, and A. A. Ali, “Sign language identification and recognition: A comparative study,” Jan. 01, 2022, Walter de Gruyter GmbH. doi: 10.1515/comp-2022-0240.
[15] A. D. Goenawan and S. Hartati, “The Comparison of K-Nearest Neighbors and Random Forest Algorithm to Recognize Indonesian Sign Language in a Real-Time,” Scientific Journal of Informatics, vol. 11, no. 1, pp. 237–244, Feb. 2024, doi: 10.15294/sji.v11i1.48475.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 ALDESTRA BAGAS WARDANA, JODI ARMYANTO, ERNA DANIATI
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
