Abstract
This study aims to address the communication hallenges faced by the Indonesian deaf community by developing an automatic classification model for Sistem Bahasa Isyarat Indonesia (SIBI) using data mining techniques. The main objective is to identify a practical algorithm for recognizing SIBI hand gestures to enhance accessibility and inclusiveness in digital communication. A comprehensive dataset consisting of 32,850 gesture samples representing SIBI alphabet signs was collected and processed through feature extraction, data cleaning, and normalization using Z-Transform and Min-Max methods. Two classification algorithms, K-Nearest Neighbor (KNN) and Random Forest, were implemented and evaluated using metrics such as accuracy, precision, recall, and F1-score. Experimental results show that both algorithms achieved high classification performance, with Random Forest obtaining a superior accuracy of 94.33% under Min-Max normalization compared to KNN’s 93.67%. These findings highlight the potential of Random Forest as an effective method for SIBI recognition. The research contributes to the advancement of automatic sign language recognition technology in Indonesia and supports the development of more inclusive communication tools for individuals with hearing impairments.
DOI
https://doi.org/10.17977/um018v8i12025p68-80
First Page
68
Last Page
80
Recommended Citation
Wirawan, Muhammad Zaki; Afif, Achmad; Handayani, Anik Nur; Hitipeuw, Imanuel; and Fukuda, Osamu
(2025)
"Classification of Indonesian Sign Language (SIBI) Using Data Mining Algorithms K-Nearest Neighbor and Random Forest,"
Knowledge Engineering and Data Science: Vol. 8:
No.
1, Article 4.
DOI: https://doi.org/10.17977/um018v8i12025p68-80
Available at:
https://citeus.um.ac.id/keds/vol8/iss1/4