A Fall Detection Method Based on Acceleration Data and Hidden Markov Model

Falls have been a major health risk that diminishes the quality of life among the elderly. In this paper, we propose a new method using acceleration data and hidden Markov model (HMM) to detect fall events. A wearable device integrating a tri-axial accelerometer was used to collect acceleration data of human chest. Feature sequences (FSs) were extracted from the acceleration data and used as sequence of observations to train an HMM of fall detection. The probability of the input FS generated by the model was calculated as the detection standard. Experimental results showed that the accuracy of the proposed method was 97.2%, the sensitivity was 91.7%, and the specificity was 100%, demonstrating desired performance of our method in detecting fall events.