A multi-scale analysis and compressive sensing based energy aware fall detection system

In this paper, an energy aware real-time wireless fall detection system based on the multi-scale analysis is proposed. Furthermore, an efficient feature extraction and compression algorithm for high accuracy fall recognition is presented. The proposed algorithm is carried out on the low-power Shimmer sensing platform. The developed method aims to reduce the amount of 3D acceleration data for energy efficiency improvement of the energy-hungry wireless links. Interestingly, our results show an average power consumption of less than 60% on the Shimmer Bluetooth link. In addition, the average of the 3D acceleration data rate savings is about 87.5%. Moreover, the proposed energy-aware fall detection system has been proven to distinguish among falls and activities of daily living, and the accuracy has been evaluated in terms of specificity and sensitivity and has shown excellent results. The sparsity degree for an efficient representation of 3D acceleration signal and high fall detection accuracy rate is also studied. The percent error between the original and reconstruted 3D acceleration signal of 7% after applying compressive sensing would yield a space savings of 56%, for a sparsity S=77 and signal length N=512.