A bio-inspired three-dimensional fall detection system

With the advancements in contemporary medicine and the improved standards o f living, people are living longer than ever before. Yet, this growing demographic is facing a challenge that consistently threatens their well-being. Falls account for the main cause of fatal/nonfatal injuries among older adults. Once a fall occurs, immediate medical attention is needed to minimize long term effects and mitigate the health condition. The severity of a fail, in fact, heavily depends on the rescue time. Although falling cannot be completely prevented, their damage can be minimized by taking appropriate precautions and by shortening the rescue time. This research project attempts to investigate the feasibility of using floor vibration captured by accelerometers to detect fall location and estimate its severity as part o f a three-dimensional fall detection system to overcome the drawbacks of the current stateof- the-art fall detection system. The performance of the proposed system is investigated in a controlled lab-scale testbed and the results from this study confirmed the feasibility of the proposed system and showed its great potential of using the system to accurately detect falls in real-time.