Matching pursuit-based compressive sensing in a wearable biomedical accelerometer fall diagnosis device

There is a significant high fall risk population, where individuals are susceptible to frequent falls and obtaining significant injury, where quick medical response and fall information are critical to providing efficient aid. This article presents an evaluation of compressive sensing techniques in an accelerometer-based intelligent fall detection system modelled on a wearable Shimmer biomedical embedded computing device with Matlab. The presented fall detection system utilises a database of fall and activities of daily living signals evaluated with discrete wavelet transforms and principal component analysis to obtain binary tree classifiers for fall evaluation. 14 test subjects undertook various fall and activities of daily living experiments with a Shimmer device to generate data for principal component analysis-based fall classifiers and evaluate the proposed fall analysis system. The presented system obtains highly accurate fall detection results, demonstrating significant advantages in comparison with the thresholding method presented. Additionally, the presented approach offers advantageous fall diagnostic information. Furthermore, transmitted data accounts for over 80% battery current usage of the Shimmer device, hence it is critical the acceleration data is reduced to increase transmission efficiency and in-turn improve battery usage performance. Various Matching pursuit-based compressive sensing techniques have been utilised to significantly reduce acceleration information required for transmission.