Accelerometer-based fall detection sensor system for the elderly

The considerable risk of falls and the substantial increase in the elderly population make the automatic fall detection system become very important. Existing fall detection systems using accelerometer as the detector are often designed based on an empirical acceleration threshold to differentiate falls from normal activities. In this paper, we design the detection method under the Neyman-Pearson detection framework. An optimal detection threshold can be obtained which meets the specified false alarm rate while maximizing the detection probability. We use TelosW mote with accelerometer as the detector, which is attached to the waist of the old people to capture the movement data. Extensive experiments are conducted to evaluate the effectiveness of our method and the accuracy of the detection system.