A CRF Based Model for Learning High Level Behaviors of the Elders in Household Environment

Abstract:

A CRF model is proposed to extract the high level behaviors based on the position information of the elders in household environment. Firstly, the slide time window is used to segment the time-order position data which is then transformed into the position-based information including position region No., speed and direction. Then, we take the information as the observation data to construct the CRF model, learn the model parameters, and achieve to extract the high level behavior state sequences which can be applied to detect the abnormality of the elders. The experiment results show that the proposed method can identify the behavior states with a good rate of identification accuracy.

• Periodical: Applied Mechanics and Materials (Volumes 55-57)
• Pages: 1017-1021
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.55-57.1017
• Online since: May 2011
• Authors: Xian Shan Li, Ling Fu Kong
• Keywords: Behavior Learning, CRF Model, Position-Based Information, Slide Time Window

References

[1] X. S. Li, L. F. Kong and F. D. Zhao, A position-based approach of extracting elderly daily behavior habits for service robot. Proc. of 3rd IEEE Conference on Industrial Electronics and Applications. Singapore, (2008).

DOI: 10.1109/iciea.2008.4582741

[2] L. Liao, D. Fox, and H. Kautz, Extracting Places and Activities from GPS Traces Using Hierarchical Conditional Random Fields, The International Journal of Robotics Research, vol. 26, no. 1 (2007), p.119.

DOI: 10.1177/0278364907073775

[3] M. Bennewitz, W. Burgard, and S. Thrun, "Learning Motion Patterns of Persons for Mobile Service Robots, Proc. of the International Conference on Robotics and Automation(ICRA), vol. 4, (2002), pp.3601-3606.

DOI: 10.1109/robot.2002.1014268

[4] V. Guralnik and K. Z. Haigh, Learning Models of Human Behaviour with Sequential Patterns, Proc. of the AAAI-02 Workshoop Autonation as Caregiver, (2002) , pp.24-30.

[5] M. Philipose, K.P. Fishkin, M. Perkowitz, etc, Inferring activities from interactions with objects, Pervasive Computing, (2005), pp.50-56.

DOI: 10.1109/mprv.2004.7

[6] J. Lafferty, A. McCallum and F. Pereira, Conditional random fields: Probabilistic models for segmenting and labeling sequence data. Proc. of the International Conference on Machine Learning, (2001).

DOI: 10.1145/1015330.1015422

[7] A. Quattoni, M. Collins and T. Darrell. Conditional random fields for object recognition. Proc. of the Neural Information Processing Systems, Vancouver , Canada , (2004).

[8] T. Y. Huang, C. D. Shi, F. X. LI and C. Cheng, Discriminative Random Fields for Online Behavior Recognition. Chinese Journal of Computers, vol. 32, no. 2, (2009), pp.275-281.

DOI: 10.3724/sp.j.1016.2009.00275

[9] X. S. Li, F. D. Zhao, L. F. Kon and P. L. Wu, Learning Human Daily Behavior Habit Patterns Using EM Algorithm for Service Robot, IEEE International Conference on Robotics and Biomimetics, Sanya, China, (2007).

DOI: 10.1109/robio.2007.4522167