Abstract
Smart environment is one of the important research issues in the area of ambient intelligence and pervasive computing. The high accurate activity recognition is the basis of supporting high-quality service for users in smart environments. In practical applications, the detected signals of monitoring smart space generally come from multiple heterogeneous sensors. Since the streaming data generated by multi-sensor are real time, continuous and noisy, recognizing activities accurately in daily living space is a difficult task. This paper proposed a novel activity recognition scheme for multi-sensor streaming data based on discriminant sequence patterns and activity transition patterns. The efficient pattern mining methods and effective activity predicting algorithms are developed for activity recognition. The experiments apply two well-known datasets, WSU and Kasteren datasets, to verify the performance of the proposed methods. The results show that the models based on the proposed discriminant sequence patterns gain effective recognition rates in both metrics of time-slide activity accuracy and class activity accuracy in comparison with HMM on incremental learning of on-line recognition paradigm.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hsu, K.C., Chiang, Y.T., Lin, G.Y., Lu, C.H., Hsu, J.Y.J., Fu, L.C.: Strategies for inference mechanism of conditional random fields for multiple-resident activity recognition in a smart home. In: The 23th International Conference on Industrial, Engineering & Other Applications of Applied Intelligent Systems, pp. 417–426 (2010)
Kasteren, T.V., Noulas, A., Englebienne, G., Kröse, B.: Accurate activity recognition in a home setting. In: The 10th International Conference on Ubiquitous Computing, pp. 1–9 (2008)
Singla, G., Cook, D.J., Schmitter-Edgecombe, M.: Recognizing independent and joint activities among multiple residents in smart environments. J. Ambient Intell. Humaniz. Comput. 1(1), 57–63 (2010)
Yakhnenko, O., Sillvescu, A., Honavar, V.: Discriminatively trained markov model for sequence classification. In: The 5th IEEE International Conference on Data Mining, Houston, pp. 498–505 (2005)
WSU Datasets. http://ailab.wsu.edu/casas/datasets/index.html
Xing, Z., Pei, J., Keogh, E.: A brief survey on sequence classification. ACM SIGKDD Explor. Newsl. 12(1), 40–48 (2010)
Lewis, D.D.: Naïve Bayes at forty: the independence assumption in information retrieval. In: Nédellec, C., Rouveirol, C. (eds.) ECML 1998. LNCS, vol. 1398, pp. 4–15. Springer, Heidelberg (1998)
Chuzhanova, N.A., Jones, A.J., Margetts, S.: Feature selection for genetic sequence classification. Bioinformatics 14(2), 139–143 (1998)
Lesh, N., Zaki, M.J., Ogihara, M.: Mining features for sequence classification. In: The 5th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 342–346 (1999)
Littlestone, N.: Learning quickly when irrelevant attributes abound: a new linear-threshold algorithm. Mach. Learn. 2(8), 285–318 (1988)
Huang, R.S., Chien, B.C.: Activity recognition on multi-sensor data streams using distinguishing sequential patterns. In: The 27th Annual Conference of the Japanese Society for Artificial Intelligence, 2A1-IOS-3b-1 (2013)
Ji, X., Bailey, J., Dong, G.: Mining minimal distinguishing subsequence patterns with gap constraints. In: The 5th IEEE International Conference on Data Mining, pp. 194–201 (2005)
Keogh, E., Pazzani, M.J.: Scaling up dynamic time warping for data mining applications. In: The Sixth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 285–289 (2000)
Kaján, L., Kertést-Farkas, A., Franklin, D., Ivanova, N., Kocsor, A., Pongor, S.: Application of a simple likelihood ratio approximant to protein sequence classification. Bioinformatics 22(23), 2865–2869 (2006)
Lin, Y.X., Chien, B.C.: A discriminant based document analysis for text classification. In: The 2010 International Computer Symposium, Workshop of Artificial Intelligence, Knowledge Discovery, and Fuzzy Systems, pp. 594–599 (2010)
Acknowledgment
This research was supported in part by the National Science Council of Taiwan, R. O. C. under contracts NSC100-2221-E-024-021 and NSC101-2221-E-024-026.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Chien, BC., Huang, RS. (2014). Activity Recognition Using Discriminant Sequence Patterns in Smart Environments. In: Peng, WC., et al. Trends and Applications in Knowledge Discovery and Data Mining. PAKDD 2014. Lecture Notes in Computer Science(), vol 8643. Springer, Cham. https://doi.org/10.1007/978-3-319-13186-3_31
Download citation
DOI: https://doi.org/10.1007/978-3-319-13186-3_31
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-13185-6
Online ISBN: 978-3-319-13186-3
eBook Packages: Computer ScienceComputer Science (R0)