Our Blog
Research >> Digital Health – Non-Intrusive Monitoring
Description Remote health and wellness monitoring has been a topic of interest in the field of public healthcare for almost a decade, with advanced diagnostic solutions promising to shape our lifestyle,
but so far falling short of expectations. The rise of health wearable devices has brought a host of privacy challenges. While patients may be willing to subject themselves to the inconvenience of
wearing these technologies at all times, the average users see them as invasive. In the case of fall detection notification, current state-of-the-art requires either the persons actively triggering
the devices to call for help after falls, or using positional sensing in the case of mobile phone based devices to automate signaling for help. Video monitoring is rich in content but may be intrusive.
Regardless of accuracy and level of intrusiveness, all existing fall detection methods are limited to detecting the fall and signalling for help, thereby rendering them simplistic and frequently
inadequate for practical applications in fall detection, and more importantly, post-fall safety and fall prevention. Our proposed research seeks to develop a platform that links a unique non-intrusive
video fall detection scheme with helper notification. Our system will not only work towards predicting fall before it happens and alert for help, identifying the possible origin of fall,
but also associate the video signals with other sensor signals to improve accuracy of prediction. Our project will also address the judicious consideration of what relevant data to capture
and retain in the person’s health record to support wellness-in-home for that individual. This longitudinal tracking will also help to ascertain over time how the individual changes and
how the smart environment should adapt to this change.
The proposed monitoring supports current Canada and BC emphasis on home wellness and presents an ideal Canada-based opportunity to assess its feasibility in synergy with traditional sensing to improve health
care and health outcomes.
Researchers
Selected Publications:
- A. Shojaei-Hashemi, P. Nasiopoulos, J. J. Little and M. T. Pourazad, "Video-based Human Fall Detection in Smart Homes Using Deep Learning," 2018 IEEE International Symposium on Circuits and Systems (ISCAS), Florence, 2018, pp. 1-5.