Real-Time Classification Improvement of Indonesian Sign System Letters (SIBI) Using K-Nearest Neighbor Algorithm

Abstract

Indonesian Sign Language (SIBI) is a vital means of communication for individuals with hearing impairments. The automatic translation from spoken language to SIBI presents challenges in accurately predicting sign characters. The information transfer process becomes biased when system predictions are incorrect. The current approach lacks accuracy due to data variations that may lead to character similarities. This research addresses this issue with an improved method incorporating linguistic features and contextual information. A novel approach is introduced to enhance SIBI character predictions using the K-Nearest Neighbor (K-NN) algorithm. The K-NN algorithm is employed to predict the most suitable SIBI character based on the similarity of linguistic features between input speech and existing data. This research compares distance metrics such as Euclidean, Manhattan, and Chebyshev to determine the optimal number of nearest neighbors (K) for achieving the most accurate outcomes. Experimental results employing 200 data points per label yielded satisfactory average predictions for each label. The experiments underscore the effectiveness of the K-NN model utilizing the Chebyshev distance metric with K=7 on the 200 data labels, as it provided excellent probability results for each label.