Application of Random Forest Classifier Algorithm in Indonesian Sign Language System (Sibi) Detection System

Abstract

Sign language is a language that prioritizes body movements and facial expressions as symbols to communicate with each other. Deaf and speech-impaired groups are the main users of sign language. One type of sign language in Indonesia is SIBI (Indonesian Sign Language System). SIBI (Indonesian Sign Language System) is a form of spoken language that is converted into sign language. Sign language is not only used as a means of communication and interaction between deaf and mute people, but also with normal people. However, until now there is still a communication gap between people who are deaf or mute and normal people. Then made a system design that can detect the sign language symbol SIBI (Indonesian Sign Language System). This system is made using the Random Forest Classifier algorithm with the help of MediaPipe Holistic and OpenCV and is made using the Python programming language. In this study, a dataset was created which was limited to 10 (ten) classes of symbols representing words in the SIBI (Indonesian Sign System) with a total of 8734 data lines which were then pre-processed by dividing the dataset into 70% training data and 30% test data. This study contains stages such as making detection, creating datasets, training classification models, and testing. The test is carried out by calculating the accuracy using the Confusion Matrix and then getting the Accuracy rate of 98.6%, Precision of 98.6%, and Recall of 98.66%. With the creation of the SIBI (Indonesian Language Sign System) detection system, it is hoped that it can reduce the gap between people who are deaf or speech impaired and normal people in communicating. Contribute to knowledge about symbol detection in SIBI (Indonesian Sign System) using the Random Forest Classifier algorithm as well as MediaPipe Holistic and OpenCV. As well as preserving and popularizing SIBI (Indonesian Sign System) as a sign language in Indonesia.