Search

Unique features of body segment kinematics in falls and activities of daily living (ADL) are applied to make automatic detection of a fall in its descending phase, prior to impact, possible. Fall-related injuries can thus be prevented or reduced by deploying fall impact reduction systems, such as an inflatable airbag for hip protection, before the impact. In this application, the authors propose the following hypothesis: "Thigh segments normally do not exceed a certain threshold angle to the side and forward directions in ADL, whereas this abnormal behavior occurs during a fall activity". Torso and thigh wearable inertial sensors (3D accelerometer and 2D gyroscope) are used and the whole system is based on a body area network (BAN) for the comfort of the wearer during a long term application. The hypothesis was validated in an experiment with 21 young healthy volunteers performing both normal ADL and fall activities. Results show that falls could be detected with an average lead-time of 700 ms before the impact occurs, with no false alarms (100% specificity), a sensitivity of 95.2%. This is the longest lead-time achieved so far in pre-impact fall detection.

A new method of physical activity monitoring that is able to detect posture transitions using two acceleration signals attached on the shoulder part of a garment is presented. Posture transition activities in continuous accelerometer records were classified into two steps. In the first step, wavelet-reconstructed antero-posterior acceleration signal was applied to extract the transition segments from the continuous accelerometer record. When compared with the reference system in segment extraction, averaged absolute error 0.21 s for sit–stand posture transitions and 0.26 s for stand–sit posture transitions were achieved. The overall sensitivity and specificity of sit–stand posture transitions were 90.852% and 98.98% and those of stand–sit posture transitions were 91.367% and 98.55%. In the second step, wavelet coefficients of extracted segments of vertical acceleration signals were used as features in classification. The classification rate (segments that are extracted and classified correctly/total number of segments) of sit–stand and stand–sit activities are 93.65% and 95.24%, respectively. Our results proved a reliable technique of detecting posture transition activities in physical activity monitoring. [ABSTRACT FROM AUTHOR]