Loading [a11y]/accessibility-menu.js
A fall detection study on the sensors placement location and a rule-based multi-thresholds algorithm using both accelerometer and gyroscopes | IEEE Conference Publication | IEEE Xplore

A fall detection study on the sensors placement location and a rule-based multi-thresholds algorithm using both accelerometer and gyroscopes


Abstract:

Falls are dangerous among the elderly population and are a major health concern. Many investigators have reported the use of accelerometers for fall detection. In additio...Show More

Abstract:

Falls are dangerous among the elderly population and are a major health concern. Many investigators have reported the use of accelerometers for fall detection. In addition, the use of miniature gyroscopes has also been reported to be able to detect falls, but the effects of sensor placement on the back of a person have not been studied thoroughly. In this paper we present a simple solution for effective fall detection using both an accelerometer and two gyroscopes placed, as a single unit, on three different positions along the thoracic vertebrae (i.e., T-4, T-7, and T-10). Results indicated that T-10 was not a good location for the gyroscope placement for fall detection. However, both T-4 and T-7 were suitable, with the results for T-4 being slightly better. Using a simple rule-based multi-thresholds algorithm that utilizes the recorded resultant gravitational acceleration, angular change, angular velocity, and angular acceleration, we were able to successfully detect all 60 falls and differentiate between falls and activities of daily living (ADL) with no false positives on young volunteers. More testing data is needed, especially for backward falls, to test the robustness of our simple algorithm and to improve the sensor portability for future trial studies on geriatric populations.
Date of Conference: 27-30 June 2011
Date Added to IEEE Xplore: 01 September 2011
ISBN Information:

ISSN Information:

Conference Location: Taipei, Taiwan

Contact IEEE to Subscribe

References

References is not available for this document.