Real Time Elderly Activity Monitoring System Based on a Tri-Axial Accelerometer
By Kang, Dong Won; Choi, Jin Seung; Lee, Jeong Whan; Chung, Soon Cheol; Park, Soo Jun; Tack, Gye Rae ; Disability and Rehabilitation: Assistive Technology, Vol. 5, No. 4, pp. 247-253Publication Date: July 2010
Study undertaken for the development of an automatic human movement classification system for the elderly using a single waist mounted tri-axial accelerometer. The real-time system comprises the tri-axial accelerometer, a rechargeable lithium battery, a microcontroller, and a transmitter. Data obtained from the sensors are transmitted to a notebook computer, and a graphical display is available. A real-time movement classification algorithm was developed using a hierarchical binary tree, which can classify activities of daily living into four general states: (1) resting state, such as sitting, lying, and standing; (2) locomotion state, such as walking and running; (3) emergency state, such as a fall; and (4) transition state, including sit to stand, stand to sit, sit to lie, and so on. The proposed algorithm was evaluated with 5 healthy participants with a mean age of about 25 years performing activities such as falls, walking, and running. Results showed that the successful detection rate of the system for all activities was about 96 percent. To evaluate long-term monitoring with the system, a 3 hour experiment in a home environment was performed with one healthy young participant, showing a 98.4 percent total detection rate of 12 movements. Further improvements of the system will include a more detailed classification algorithm to distinguish several daily activities.
Published by: Taylor & Francis, Limited (Website:http://taylorandfrancis.org)
International Society of Physical and Rehabilitation Medicine (Web Site: http://www.isprm.org )
