IAES International Journal of Artificial Intelligence (IJ-AI) Vol. 12, No. 4, December 2023, pp. 1666~1676 ISSN: 2252-8938, DOI: 10.11591/ijai.v12.i4.pp1666-1676  1666 Journal homepage: http://ijai.iaescore.com Glove based wearable devices for sign language-GloSign Soly Mathew Biju, Obada Al-Khatib, Hashir Zahid Sheikh, Farhad Oroumchian Faculty of Engineering and Information Sciences, University of Wollongong in Dubai, Dubai, UAE Article Info ABSTRACT Article history: Received Jun 5, 2022 Revised Feb 21, 2023 Accepted Mar 11, 2023 Loss of the capability to talk or hear has psychological and social effects on the affected individuals due to the absence of appropriate interaction. Sign Language is used by such individuals to assist them in communicating with each other. This paper proposes a glove called GloSign that can convert American sign language to characters. This glove consists of flex and inertial measurement unit (IMU) sensors to identify gestures. The data from glove is uploaded on IoT platform, which makes the glove portable and wireless. The data from gloves is passed through a k-nearest neighbors (KNN) Algorithm machine learning algorithm to improve the accuracy of the system. The system was able to achieve an accuracy of 96.8%. The glove can also be used to form sentences. The output is displayed on the screen or is converted to speech. This glove can be used in communicating with people who don’t know sign language. Keywords: Glove Pattern recognition gesture recognition Sign language sensor This is an open access article under the CC BY-SA license. Corresponding Author: Soly Mathew Biju Associate Professor, Faculty of Engineering and Information Sciences, University of Wollongong in Dubai Office 201, Block 15, Knowledge Park, PO Box 20183, Dubai, UAE Email: solymathewbiju@uowdubai.ac.ae. 1. INTRODUCTION Loss of the ability to communicate with others can have devastating effects. Sign language is a way for communication to overcome this problem. Sign language involves gestures made by hands and facial expressions. It is a very effective and interactive way of communicating [1]. The problem that arises from sign language is that not everyone is familiar with the gestures. It would be challenging for people with disability to communicate with people who don’t know this language. Furthermore, it can’t be used to communicate digitally. Another issue with the sign language is that there is no universal sign language. Every country has their own sign language with gestures that have different meaning than the sign language of other countries. To overcome the issue of communication, a glove has been proposed in this study called GloSign. The major focus is to translate the sign language into English language. This paper focuses on American sign language, as it is the most common sign language. American sign language is mostly used in America and some parts of Canada. American sign language was devised in the 19 th century by the American school of deaf. Like any other language, sign language has formal and informal parts. This paper covers the formal part of the communication. The formal part of the American sign language consists of 26 alphabets. These alphabets can be used to form words and sentences. The gestures associated with these letters are defined by four components. These are the shape of the hand, position in relation to the body, hand movements and alignment of the palm. Few of the gestures are dynamic. These gestures require the movement of the hand. Figure 1 shows the basic gestures for the English alphabets in American sign language. This glove consists of flex sensor, accelerometer, and gyroscope to aid in recognizing gestures made. This wireless glove uses an IoT platform for uploading the data. This data is analyzed to understand the gesture made using the glove. Then it will be used to form words and sentences. The sentences will then be displayed on the screen running the gesture recognition software, along with conversion of the sentence to speech.