Independent Research Presentation

Title: Transfer Learning for Improved Fall Detection


Student: Nader Maray


Advisor: Dr. Anne Hee Hiong Ngu


Date: 12.08.2022


Time: 11:00 AM



Meeting ID: 791 080 6695



Falls in the elderly are associated with significant morbidity and mortality. While numerous fall detection devices incorporating AI and machine learning algorithms have been developed, no known smartwatch-based system has been used successfully in real-time to detect falls for elderly persons. We have developed and deployed a personalized SmartFall system on a commodity-based smartwatch which has been trialled by nine elderly participants. The system, while being usable and welcomed by the participants in our trial, has two serious limitations. The first limitation is the inability to collect a large amount of personalized data for training. When the fall detection model which is trained with insufficient data is used in the real world, it generates a large number of false positives. The second limitation is that an accurate model trained using data collected with a specific device performs sub-par when used in another device in real-time. This paper aims to first explore the use of transfer learning to overcome the small dataset training problem for fall detection. We also demonstrated the use of transfer learning to bridge the gap in performance between the heterogeneous devices. Our preliminary experiments demonstrate the effectiveness of transfer learning for improved fall detection.

Deadline: Dec. 15, 2022, midnight