Activity Recognition by Fuzzy Logic System in Wireless Sensor Network for Physical Therapy

  • Shu-Yin Chiang
  • Yao-Chiang Kan
  • Ying-Ching Tu
  • Hsueh-Chun Lin
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 16)


The physical therapy for geriatrics training or stroke patients requires incessant and routine rehabilitation during the cure period. The physiatrists hereby refer feedback from clinical records to offer necessary assistant programs. The ubiquitous health care (UHC or u-healthcare) becomes the most concern of the successful treatment that needs to ensure patients following the therapeutic assignment continuously. This study proposes a facile activity recognition procedure to interact patients and computation for measuring essential movements of human body with privacy concern through wireless sensor network (WSN) body motion sensors that involves the accelerometer and gyroscope. At this initial stage, sensor data of static postures and dynamic motions are recognized by the fuzzy algorithm. According to the proposed process, the fuzzy parameters are calibrated by the adoptive feature sets and are verified by a blind test. The overall recognition accuracy for regularly steady activities achieves over 96%. Two simple rehab postures of physical therapy were discussed and the recognition rate can imply the threshold of specific rehab activity. The approach may support the interface to monitor privately remedy process for patients with non-imaged and non-invasive u-healthcare of physical therapy.


Accelerometer Gyroscope Fuzzy Logic Activity Recognition Ubiquitous Health Care WSN 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Medjahed, H., Istrate, D., Boudy, J., Dorizzi, B.: Human Activities of Daily Living Recognition Using Fuzzy Logic for Elderly Home Monitoring. In: Proc. of IEEE on Fuzzy System, pp. 2001–2006 (2009)Google Scholar
  2. 2.
    Wren, C.R., Azarbayejani, A., Darrell, T., Pentland, A.P.: Real-Time Tracking of the Human Body. IEEE Trans. Pattern Analysis and Machine Intelligence 19(7), 780–785 (1997)CrossRefGoogle Scholar
  3. 3.
    Hwang, J.Y., Kang, J.M., Jang, Y.W., Kim, H.C.: Development of Novel Algorithm and Real-time Monitoring Ambulatory System Using Bluetooth Module for Fall Detection in the Elderly. In: Proc. of the IEEE on Engineering in Medicine and Biology Society, pp. 2204–2207 (2004)Google Scholar
  4. 4.
    Jones, V., Bults, R., Konstantas, D., Vierhout, P.A.M.: Healthcare PANs: Personal Area Networks for trauma care and home care. In: Proc. 4th Wireless Personal Multimedia Communications, pp. 1369–1374 (2001)Google Scholar
  5. 5.
    Zhao, Z., Cui, L.: EasiMed: A remote health care solution. In: Proc. 27th Conf. of the Engineering in Medicine and Biology Society, pp. 2145–2148 (2005)Google Scholar
  6. 6.
    Jovanov, E., Milenkovic, A., Otto, C., de Groen, P.C.: A Wireless Body Area Network of Intelligent Motion Sensors for Computer Assisted Physical Rehabilitation. J. of Neuro Engineering and Rehabilitation 2(6) (2005), doi:10.1186/1743-0003-2-6.Google Scholar
  7. 7.
    Lisetti, C., Nasoza, F., LeRougeb, C., Ozyera, O., Alvarez, K.: Developing Multimodal Intelligent Affective Interfaces for Tele-home Health Care. Int’l J. of Human-Computer Studies 59(1-2), 245–255 (2003)CrossRefGoogle Scholar
  8. 8.
    Akyildiz, I.F., Su, W., Sankarasubramaniam, Y., Cayirci, E.: Wireless Sensor Networks: a Survey. Computer Networks 38(4), 393–422 (2002)CrossRefGoogle Scholar
  9. 9.
    Ghasemzadeh, H., Jafari, R.: Coordination Analysis of Human Movements with Body Sensor Networks: A Signal Processing Model to Evaluate Baseball Swings. IEEE Sensors Journal 11(3), 603–610 (2011)CrossRefGoogle Scholar
  10. 10.
    Lind, L., Sundvall, E., Karlsson, D., Shahsavar, N., Åhlfeldt, H.: Requirements and Prototyping of a Home Health Care Application Based on Emerging JAVA Technology. Int’l J. of Medical Informatics 68(1-3), 129–139 (2002)CrossRefGoogle Scholar
  11. 11.
    Ahmad, S., Eskicioglu, R., Graham, P.: Design and Implementation of a Sensor Network Based Location Determination Service for use in Home Networks. In: Proc. of IEEE on Mobile Adhoc and Sensor Systems, pp. 622–626 (2006)Google Scholar
  12. 12.
    Kan, Y.-C., Chen, C.K.: A Wearable Inertial Sensor Node for Body Motion Analysis. IEEE Sensors Journal, (in Press) doi:10.1109/JSEN.2011.2148708Google Scholar
  13. 13.
    TinyOS Community Forum,
  14. 14.
    Chiang, S.-Y., Kan, Y.-C., Tu, Y.-C., Lin, H.-C.: A Preliminary Activity Recognition of WSN Data on Ubiquitous Health Care for Physical Therapy. In: 2011 International Conference on Data Engineering and Internet Technology, pp. 517–520 (2011)Google Scholar
  15. 15.
    Jeong, D.-U., Do, K.-H., Chung, W.-Y.: Implementation of the Wireless Activity Monitoring System Using Accelerometer and Fuzzy Classifier. The International Journal of Information Systems for Logistics and Management, 617–716 (2008)Google Scholar
  16. 16.
    Alvarez-Alvarez, A., Alonso, J.M., Trivino, G., Llamazares, A., Ocaña, M.: Human Activity Recognition Applying Computational Intelligence Techniques for Fusing Information Related to WiFi Position and Body Posture. In: Proc. of IEEE on Fuzzy Systems, pp. 1–8 (2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Shu-Yin Chiang
    • 1
  • Yao-Chiang Kan
    • 2
  • Ying-Ching Tu
    • 1
  • Hsueh-Chun Lin
    • 3
  1. 1.Department of Information and Telecommunications EngineeringMing Chuan UniversityGwei-ShanTaiwan
  2. 2.Department of Communications EngineeringYuan Ze UniversityChung-LiTaiwan
  3. 3.Department of Health Risk ManagementChina Medical UniversityTaichungTaiwan

Personalised recommendations