People

Reza Argha

Current role: Performing research in the application of deep learning and AI in the development of smart systems for improving health

Current interests in research and development relevant to the Hub:
I am currently working on the development of an unobtrusive fall detection and prediction system using wearable sensors, mmWave radars, infrared sensors, and deep learning. While fall detection systems can help reduce the consequences of falls, they are not able to stop them from happening. Thus, prediction systems must be developed to identify the risk factors inducing a fall incident. Traditionally, this is carried out by caregivers using questionnaires, diaries or phone calls; but the data collected is usually incomplete and not always reliable. Since falls are rare events, standard supervised AI methods may not be effective to detect them accurately. The overall objective of the research will be to develop next generation fall detector technology by fusing and processing data from wearable sensors mmWave radars used to collect human body’s point cloud using novel semi-supervised generative deep-learning models and evaluate its effectiveness prospectively. This project aims also to develop a robust falls risk assessment system (i.e. fall prediction and prevention), in order to avoid falls and its related long-term disabilities especially among elderly. The proposed system will use real-time vital signs collected through a smart phone app-based telehealth system, motion data (collected via mmWave radar and wearable sensors), falls history and other clinical information.


More people