PI: Assoc. Prof. Dr. SHERZOD TURAEV, College of Information Technology, UAE University
Co-PIs: Prof. Dr. NAZAR ZAKI, College of Information Technology, UAE University Prof. Dr. SAAD HAROUS, College of Computing and Informatics, University of Sharjah Asst. Prof. Dr. MANZOOR KHAN, College of Information Technology, UAE University Prof. Dr. LOO CHU KIONG, Faculty of Computer Science and Information Technology, University of Malaya, Malaysia Asst. Prof. Dr. ALI ABD ALMISREB, Faculty of Engineering and Natural Sciences, International University of Sarajevo, Bosnia and Herzegovina
Body language is a type of nonverbal communication in which physical behaviors – visible bodily actions, instead of words, are used to express or convey the information. Such behaviors can be postures, gestures, stances, and movements of any part of the body or the body as a whole.
According to prominent studies, over 65% of face-to-face communications are done using body language. Understanding body movements, including facial expressions, body poses, tone of voice, and hand gestures, is not only important for communication, where body language assists people in understanding and decoding what other people are expressing, but it is also important for the interpretation of peoples’ health conditions, feelings, and emotional states. The abnormal psychological and physical states of sick people can be read from their body movements, which have been studied by healthcare and AI researchers. Most studies focus on analyzing the body movements of patients with brain disorders and damages as well as measuring pain scales from the body movements of sick people.
The commonality of these studies is that almost every research considered a disease concerning a single type of body movement. We can also hardly ever find studies on comprehensive disease–body language relationships. To overcome these drawbacks, we propose a contextual clustered approach to studying body language, in which all body movements related to the disease are considered together (in a cluster), taking into consideration external factors such as environment, circumstances, and domain (context).
This approach provides more accurate localization of pain and more precise identification of external signs and symptoms, which will help to correctly diagnose diseases and properly monitor patients’ health conditions. We develop novel intelligent clustered deep neural network models for body language analysis of healthcare patients. Smart healthcare systems enhanced with these body language analyzers will “understand” health conditions, feelings, and emotional states of patients through their body language and do make significant improvements in disease prevention and monitoring, diagnosis and treatment, hospital management, health decision-making, medical research and many other critical dimensions, which are very essential for the UAE healthcare systems.