Fall Detection Algorithm Based on Triaxial Accelerometer and Magnetometer

Fall is a precipitous drop from a height, or from a higher position, which may be accompanied by injuries. This is one of the most dangerous and fearful situation in the elderly living. This is the reason, fast and early detection of the fall is very important to save and rescue the people and avoid the badly prognosis. In this article we are presenting a thresholdbased fall detection algorithm that processes data from common sensors in modern smart phones, such as triaxial accelerometer and magnetometer in order to detect falls. The algorithm uses Signal Vector Magnitude (SVM) peak value, base length and post-impact velocity to distinguish falls from most of daily activities. However, the SVM curve in a period produced by running is similar to a fall (a running curve can be regarded as the combination of multiple fall curves). Accordingly, residual movement is taken into account to identify running and fall. In addition, the vertical acceleration is observed to increase detection accuracy. In the experiments, the data are collected by simulating fall in four directions: forward, backward, left and right. The simulations are conducted by young people. The final experiment includes data from 120 simulated falls and 150 daily activities. Compared with previous methods, the proposed method achieves higher sensitivity and specificity.