Activity recognition using conditional random field

ABSTRACT

Activity Recognition is an integral component of ubiquitous computing. Recognizing an activity is a challenging task since activities can be concurrent, interleaved or ambiguous and can consist of multiple actors (which would require parallel activity recognition). This paper investigates how the discriminative nature of Conditional Random Fields (CRF) can be exploited to enhance the accuracy of recognizing activities when compared to that achieved using generative models. It aims to apply CRF to recognize complex activities, analyze the model trained by CRF and evaluate the performance of CRF against existing models using Stochastic Gradient Descent (which is suitable for online learning).

References

1. Qing-Bin Gao, and Shi-Liang Sun. 2012. "Trajectory-Based Human Activity Recognition Using Hidden Conditional Random Fields". In Proceedings of the 2012 International Conference on Machine Learning and Cybernetics, Xian, 15--17 July, 2012. IEEE Xplore. DOI=10.1109/ICMLC.2012.6359507
2. Eunju Kim, Sumi Helal, and Diane Cook. 2010. "Human Activity Recognition and Pattern Discovery". IEEE Pervasive Computing 9, 1 (January 2010), 48--53. DOI=10.1109/MPRV.2010.7.
3. Machine Learning: Generative and Discriminative Models. 2010. "Machine Learning: Generative and Discriminative Models". Machine Learning Course, http://www.cedar.buffalo.edu/~srihari/CSE574/Discriminative-Generative.pdf
4. Hongqing Fang, Raghavendiran Srinivasan and Diane J. Cook, 2012, "Feature selections for human activity recognition in smart home environments". In proceedings of International Journal of Innovative Computing, Information and Control, May 2012.
5. Sutton, Charles and Mccallum, Andrew. 2006. "Introduction to Conditional Random Fields for Relational Learning". Getoor, Lise and Taskar, Ben, eds. Introduction to Statistical Relational Learning, MIT Press.
6. Charles Elkan. 2012. "Log Linear Models and Conditional Random Fields". University of San Diego, http://cseweb.ucsd.edu/users/elkan/250Bwinter2012/loglinear- CRFs.pdf.
7. Douglas L. Vail, Manuela M. Veloso, and John D. Lafferty.2007. "Feature Selection in Conditional Random Fields for Activity Recognition". In Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems, San Diego, CA, 2007. IROS 2007. IEEE Xplore, San Diego, CA, pp 3379--3384, DOI=10.1109/IROS.2007.4399441.
8. Douglas L. Vail. 2008. "Conditional Random Fields for Activity Recognition". PhD Thesis, Carnegie Mellon University, United States of America, CMU-CS-08-119, April, 2008.
9. "Center for Advanced Studies in Adaptive Systems (CASAS)", Washington State University Smart Home Project, Aruba Dataset, 2010--2011, Tulum Dataset, 2009--2010, Two-R (Summer and Spring) Dataset 2009, Kyoto (ADL Normal and ADL Error Dataset). Available at CASAS, WSU website: http://wsucasas.wordpress.com/datasets/
10. Naoaki Okazaki, 2007, "CRFsuite: a fast implementation of Conditional Random Fields (CRFs)", http://www.chokkan.org/software/crfsuite
11. Megha Agarwal, 2014, "MSc Thesis on Activity Recognition Using Conditional Random Fields", University Of Bristol, Bristol, United Kingdom

Index Terms

• Computing methodologies

  • Artificial intelligence