QoE-Aware Edge-Assisted Machine Learning-Based Fall Detection and Prediction with FBGs

Considering that fall accidents are one of the leading causes of non-natural death of elders, it is crucial to design and to implement home' fall detection systems. Current home monitoring systems are targeting this challenge, pursuing non-invasive, low latency, and simplified fall detection algorithms. Therefore, in this paper, edge-enabled non-wearable and non-invasive fall detection system is proposed. Concretely, outperforming the conventional invasive/privacy-sensitive fall detection technologies, the proposed system comprises four photonic-based accelerometers solely relying on the fiber Bragg grating (FBG) technology, which monitor the vibrations induced by the body impact in the platform by the Bragg wavelength shifts. A newly-developed support vector machine-based multi-class fall detection algorithm is proposed, based on the data collected by the accelerometers. Moreover, feasibility analysis of the proposed fall detection algorithm also reveals the possibility of fall prediction, given the slipping as the pre-falling phenomenon. Experimental results showcase that the proposed fall detection algorithm achieves overall accuracy up to 96.5%, with average processing time achieved as 21.3 ms, indicating the sufficiency to provide high quality of experience (QoE) fall detection services. Besides, fall prediction based on the pre-falling case study of slipping is discussed, revealing that fall can be predicted197.5 ms beforehand, which is sufficient for further fall prevention (e.g., airbag).