A wearable pre-impact fall detector using feature selection and Support Vector Machine
- 1 October 2010
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1686-1689
- https://doi.org/10.1109/icosp.2010.5656840
Abstract
Falls and the resulting injuries in the elderly are a major public health problem, thus the early detection of falls is of great significance. The purpose of this study was to investigate the feasibility of a novel pre-impact fall detector prototype capable of detecting impending falls in their descending phase before the body hits the ground. A wearable tri-axial MEMS accelerometer was used for data collection of human motion information and a pair of wireless transceivers was used to transmit acceleration data to a PC for data analysis. Feature vector derived from time-domain characteristics was generated and feature selection was then performed to obtain the features with the most discrimination power. Fall detection algorithm using Support Vector Machine was developed and evaluated. The overall system was tested and results showed that all falls could be detected with an average lead-time of 203ms before impact, and no false alarm occurred. The proposed system will lead to potential applications for preventing or reducing fall-related injuries.Keywords
This publication has 14 references indexed in Scilit:
- A wearable system for pre-impact fall detectionJournal of Biomechanics, 2008
- The identification of vertical velocity profiles using an inertial sensor to investigate pre-impact detection of fallsMedical Engineering & Physics, 2008
- Portable Preimpact Fall Detector With Inertial SensorsIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2008
- Distinguishing fall activities from normal activities by angular rate characteristics and high-speed camera characterizationMedical Engineering & Physics, 2006
- The acute medical care costs of fall-related injuries among the U.S. older adultsInjury, 2005
- Evaluation of a fall detector based on accelerometers: A pilot studyMedical & Biological Engineering & Computing, 2005
- Population based study of hospitalised fall related injuries in older peopleInjury Prevention, 2002
- Feature selection with neural networksPattern Recognition Letters, 2002
- Distinguishing fall activities from normal activities by velocity characteristicsJournal of Biomechanics, 2000
- The Nature of Statistical Learning TheoryPublished by Springer Science and Business Media LLC ,2000