Cluster Computing

, Volume 22, Supplement 6, pp 13583–13590 | Cite as

Posture based health monitoring and unusual behavior recognition system for elderly using dynamic Bayesian network

  • G. AnithaEmail author
  • S. Baghavathi Priya


Video surveillance cameras play a vital role in society. Elderly monitoring is one of the major applications of surveillance camera. It is observed that most of the elderly people live alone at homes. They desire aging at homes. Due to aging elderly people may experience some abnormal behaviors like chest pain, headache etc. Since they live alone these abnormal activities are unnoticed. This unnoticed activities cause severe health problems and finally may cause death. So a monitoring system is needed to monitor the behavior and give alerts to the care givers. A computer vision based elderly health care monitoring system using Dynamic Bayesian network (DBN) is developed. Modelling sequential data is an important feature in machine learning domain. The DBN model detects the abnormal activities such as backward fall, chest pain, forward fall, headache, and vomit. Human postures are recognized from silhouettes so that the privacy of the people is preserved and this model is robust to different environmental setup. This DBN model is both generative and discriminative and evaluated with real time video sequences and gives 82% accuracy. This system helps to give immediate attention to the people who are suffering in home alone due to severe health issues.


Dynamic Bayesian network Independent component analysis (ICA) Principal component analysis (PCA) Activity recognition Video surveillance Generative model 


  1. 1.
    Kleinberger, T., Becker, M., Ras, E., Holzinger, A., Müller, P.: Ambient intelligence in assisted living: enable elderly people to handle future interfaces. In: International Conference on Universal Access in Human-Computer Interaction. Springer, Berlin, pp. 103–112CrossRefGoogle Scholar
  2. 2.
    Storf, H., Kleinberger, T., Becker, M., Schmitt, M., Bomarius, F., Prueckner, S.: An eventdriven approach to activity recognition in ambient assisted living. In: European Conference on Ambient Intelligence, Springer, Berlin, 2009Google Scholar
  3. 3.
    Rafael Caba˜nas de Paz, M. Julia Flores, Jes´us Mart´ınez-G´omez, Dynamic Bayesian Network for Gesture Recognition, Xii Workshop De Agentes F´Isicos, Septiembre 2011, AlbaceteGoogle Scholar
  4. 4.
    Edwards, J.: Wireless sensors relay medical insight to patients and caregivers [special reports]. IEEE Signal Process. Mag. 29(3), 8–12 (2012)CrossRefGoogle Scholar
  5. 5.
    Malhi, K., Mukhopadhyay, S.C., Schnepper, J., Haefke, M., Ewald, H.: A Zigbee-based wearable physiological parameters monitoring system. IEEE Sens. J. 12(3), 423–430 (2012)CrossRefGoogle Scholar
  6. 6.
    Mariani, B., Jiménez, M.C., Vingerhoets, F.J.G., Aminian, K.: On-shoe wearable sensors for gait and turning assessment of patients with Parkinson’s disease. IEEE Trans. Biomed. Eng. 60(1), 155–158 (2013)CrossRefGoogle Scholar
  7. 7.
    Chen, B.-R., et al.: A web-based system for home monitoring of patients with Parkinson’s disease using wearable sensors. IEEE Trans. Biomed. Eng. 58(3), 831–836 (2011)CrossRefGoogle Scholar
  8. 8.
    Mihailidis, A., Fernie, G.R., Cleghorn, W.L.: The development of a computerized cueing device to help people with dementia to be more independent. Technol. Disabil. 13(1), 23–40 (2000)CrossRefGoogle Scholar
  9. 9.
    Adlam, D., Gibbs, C., Orpwood, R.: The Gloucester smart house bath monitor for people with dementia. Phys. Med. Congr. Med. Phys. Clin. Eng. 17, 189 (2001)Google Scholar
  10. 10.
    Aziz, O., Robinovitch, S.N.: An analysis of the accuracy of wearable sensors for classifying the causes of falls in humans. IEEE Trans. Neural Syst. Rehabil. Eng. 19(6), 670–676 (2011)CrossRefGoogle Scholar
  11. 11.
    Ranhotigmage, C.: Human activities and posture recognition: innovative algorithm for highly accurate detection rate, 2013.
  12. 12.
    Ma, D., Saxena, N., Xiang, T., Zhu, Y.: Location-aware and safer cards: enhancing RFID security and privacy via location sensing. IEEE Trans. Dependable Secur. Comput. 10(2), 57–69 (2013)CrossRefGoogle Scholar
  13. 13.
    Mukhopadhyay, S.C.: Wearable sensors for human activity monitoring—a review. IEEE Sens. J. 15(3), 1321–1330 (2015)CrossRefGoogle Scholar
  14. 14.
    Collins, R.T., Lipton, A.J., Kanade, T.: Introduction to the special section on video surveillance. IEEE Trans. Pattern Anal. Mach. Intell. 22(8), 745–746 (2000)CrossRefGoogle Scholar
  15. 15.
    Jalal, A., Kamal, S., Kim, D.: A depth video sensor-based life-logging human activity recognition system for elderly care in smart indoor environments. Sensors 14(7), 11735–11759 (2014)CrossRefGoogle Scholar
  16. 16.
    Brulin, D., Benezeth, Y., Courtial, E.: Posture recognition based on fuzzy logic for home monitoring of the elderly. IEEE Trans. Inf. Technol. Biomed. 16(5), 974–982 (2012)CrossRefGoogle Scholar
  17. 17.
    Wang, C.W., Hunter, A., Gravill, N., Matusiewicz, S.: Unconstrained video monitoring of breathing behavior and application to diagnosis of sleep apnea. IEEE Trans. Biomed. Eng. 61(2), 396–404 (2014)CrossRefGoogle Scholar
  18. 18.
    Khan, Z.A., Sohn, W.: Abnormal human activity recognition system based on R-Transform and kernel discriminant technique for elderly home care. IEEE Trans. Consum. Electron. 5(4), 1843–1850 (2011)CrossRefGoogle Scholar
  19. 19.
    Tabbone, S., Wendling, L., Salmon, J.P.: A new shape descriptor defined on the radon transform. Comput. Vis. Image Understand. J. 102(1), 42–51 (2006)CrossRefGoogle Scholar
  20. 20.
    Murphy, K.: Dynamic Bayesian Networks: Representation, Inference and Learning. University of California, Berkeley (2002)Google Scholar
  21. 21.
    Murphy, K.: The bayes net toolbox for matlab. Comput. Sci. Stat. 33(2), 1024–1034 (2001)Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Information TechnologyRajalakshmi Engineering CollegeChennaiIndia

Personalised recommendations