AI-Powered Smart Glove for Stroke Rehabilitation and Hand Movement Assessment
Supervisor Name
Areej Jaber
Supervisor Email
a.jabir@ptuk.edu.ps
University
Palestine technical university - Kadoorie
Research field
Computer Science
Bio
Dr. Areej Jaber is Head of the Artificial Intelligence and Applied Computing Departments and an Assistant Professor in the Department of Computer Science at the College of Information Technology and Artificial Intelligence, Palestine Technical University – Kadoorie (PTUK). She earned her Ph.D. in Computer Science and Technology from Universidad Carlos III de Madrid (UC3M), Spain, in 2022, and her M.Sc. in Computer Science from Al-Quds University. Her research focuses on Natural Language Processing (NLP), a major branch of Artificial Intelligence, and she has published several distinguished works in areas such as: Clinical Abbreviation Disambiguation, Propaganda Detection, Sentiment Analysis, and Arabic Linguistic Resource Development Dr. Jaber has participated in regional and international conferences and has published in peer-reviewed journals indexed in Scopus and JCR. She also serves as a reviewer and a member of scientific and program committees for several local and international conferences. In addition to her research activities, Dr. Jaber supervises numerous master’s theses in the Computer Science and Cybercrime programs, covering advanced topics such as Arabic Hate Speech Detection, Machine Translation, and Sentiment Analysis, using machine learning, deep learning, and large language model (LLM) methodologies.
Description
Stroke is one of the leading causes of long-term disability, and many survivors lose part of their ability to use their hands. Rehabilitation therapists often assess hand movement by observation, which can be subjective and makes it hard to measure small improvements over time. This project aims to improve an existing IoT smart glove by adding artificial intelligence that helps assess and track the recovery of stroke patients' hand movements. The glove uses wearable sensors to record hand and finger movements during rehabilitation exercises. Over four months, our team will prepare a suitable dataset of hand movement sensor data, then train and compare AI models that recognize the patient's movements and give a movement quality score. We will also build a backend system that stores patient sessions and runs the AI model, and a web dashboard where rehabilitation specialists can view results, follow each patient's progress over time, and choose suitable exercises. If time and budget allow, we will also build a physical glove prototype and connect it to the system. The system is designed to support therapists in making more accurate and objective decisions, not to replace their clinical judgment.