ABSTRACT
Recently, human activity recognition and prediction have become important functionalities in ambient-assisted living. Activity inference algorithms detect what task a human undertakes, by analyzing the data stream pattern generated from various Internet of Things (IoT) devices. However, determining how the data stream should be segmented in real-time, referred to as data segmentation, remains as one of the most difficult challenges. In this paper, we propose an automatic data segmentation approach for real-time activity prediction by employing the Jaro-Winkler Distance measurement. Our approach selects a breakpoint of a stream by comparing the Jaro-Winkler distance between the training dataset and the data stream and finding a peak among the variations. The resultant segment also becomes new training data after being tagged; this removes the need to segment the stream data manually for humans. From the experiment based on MIT's smart home dataset collected from a real living environment, our approach shows reasonable performance of 76% accuracy even though the dataset size is relatively diminutive.
- J. A. Stankovic, Research directions for the Internet of Things, IEEE Internet Things J., vol. 1, no. 1, pp. 3--9, Feb. 2014.Google ScholarCross Ref
- L. Chen, J. Hoey, C. D. Nugent, D. J. Cook, and Z. Yu, Sensor-based activity recognition. Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on, 42(6), pp. 790--808, 2012. Google ScholarDigital Library
- L. Bao, and S. S. Intille, Activity recognition from user-annotated acceleration data, In Pervasive computing, Springer Berlin Heidelberg, pp. 1--17, 2004.Google Scholar
- P., Palmes, H. K., Pung, T. Gu, W. Xue, and S. Chen, Object relevance weight pattern mining for activity recognition and segmentation, Pervasive and Mobile Computing, 6(1), pp. 43--57. 2010. Google ScholarDigital Library
- D. J. Cook, and N. Krishnan, Mining the home environment. Journal of intelligent information systems, 43(3), pp. 503--519, 2014. Google ScholarDigital Library
- E. Kim, and S. Helal, Modeling human activity semantics for improved recognition performance. In Ubiquitous Intelligence and Computing, Springer Berlin Heidelberg, pp. 514--528, 2011. Google ScholarDigital Library
- B. Kim, T. Kim, H. G. Ko, D. Lee, S. J. Hyun, and I. Y. Ko, Personal genie: a distributed framework for spontaneous interaction support with smart objects in a place. In Proceedings of the 7th International Conference on Ubiquitous Information Management and Communication, ACM, pp. 97. Jan. 2013. Google ScholarDigital Library
- I. H., Bae, An ontology-based approach to ADL recognition in smart homes. Future Generation Computer Systems, 33, pp. 32--41, 2014. Google ScholarDigital Library
- Jaro-Winkler distance, {Online} available: http://en.wikipedia.org/wiki/Jaro%E2%80%93Winkler_distanceGoogle Scholar
- G. Okeyo, L. Chen, H. Wang, and R. Sterritt, Dynamic sensor data segmentation for real-time knowledge-driven activity recognition. Pervasive and Mobile Computing, pp. 155--172, 2012. Google ScholarDigital Library
- T. V. Kasteren, A. Noulas, G. Englebienne, and B. Kröse, Accurate activity recognition in a home setting. In Proceedings of the 10th international conference on Ubiquitous computing, ACM, pp. 1--9, Sep. 2008. Google ScholarDigital Library
- E. M. Tapia, S. S. Intille, and K. Larson, Activity recognition in the home using simple and ubiquitous sensors, Springer Berlin Heidelberg, pp. 158--175., 2014.Google Scholar
- J. O. Laguna, A. G. Olaya, and D. Borrajo, A dynamic sliding window approach for activity recognition. In User Modeling, Adaption and Personalization, Springer Berlin Heidelberg, pp. 219--230, 2011. Google Scholar
- D. J. Cook, N. C. Krishnan, and P. Rashidi, Activity discovery and activity recognition: A new partnership. Cybernetics, IEEE Transactions on, 43(3), pp. 820--828, 2013.Google Scholar
- J. Wan, M. J. O'Grady, and G. M. O'Hare, Dynamic sensor event segmentation for real-time activity recognition in a smart home context. Personal and Ubiquitous Computing, pp. 1--15, 2014. Google ScholarDigital Library
- X. Hong, and C. D. Nugent, Partitioning time series sensor data for activity recognition. In Information Technology and Applications in Biomedicine, ITAB 2009, 9th International Conference, IEEE, pp. 1--4, Nov. 2009.Google ScholarCross Ref
- M. S. Ryoo, Human activity prediction: Early recognition of ongoing activities from streaming videos. In Computer Vision (ICCV), 2011 IEEE International Conference, IEEE, pp. 1036--1043, Nov. 2011. Google ScholarDigital Library
- K. Li, J. Hu, and Y. Fu, Modeling complex temporary composition of actionlets for activity prediction. In Computer Vision-ECCV 2012, Springer Berlin Heidelberg, pp. 286--299, 2012. Google ScholarDigital Library
- M. S. Ryoo, T. J. Fuchs, L. Xia, J. K. Aggarwal, and L. Matthies, Robot-Centric Activity Prediction from First-Person Videos: What Will They Do To Me? HRI' 15, PortLand, USA, Mar. 2015, Google ScholarDigital Library
- E. M. Tapia, S. S. Intille, and K. Larson, Activity recognition in the home setting using simple and ubiquitous sensors, in Proceedings of PERVASIVE 2004, vol. LNCS 3001, A. Ferscha and F. Mattern, Eds. Berlin Heidelberg: Springer-Verlag, pp. 158--175, 2004.Google Scholar
- X. Zhu, C. Vondrick, D. Ramanan, and C. Fowlkes, Do We Need More Training Data or Better Models for Object Detection?, In BMVC, Vol. 3, p. 5, Sep. 2012.Google ScholarCross Ref
- K. S. Gayathri, S. Elias, and S. Shivashankar, An Ontology and Pattern Clustering Approach for Activity Recognition in Smart Environments. In Proceedings of the Third International Conference on Soft Computing for Problem Solving, Springer India, pp. 833--843, Jan. 2014.Google ScholarCross Ref
Index Terms
- Automatic Sensor Data Stream Segmentation for Real-time Activity Prediction in Smart Spaces
Recommendations
Annotating smart environment sensor data for activity learning
Smart Environments: Technology to Support HealthcareThe pervasive sensing technologies found in smart homes offer unprecedented opportunities for providing health monitoring and assistance to individuals experiencing difficulties living independently at home. In order to monitor the functional health of ...
Semantic segmentation of real-time sensor data stream for complex activity recognition
Data segmentation plays a critical role in performing human activity recognition in the ambient assistant living systems. It is particularly important for complex activity recognition when the events occur in short bursts with attributes of multiple sub-...
Dynamic sensor data segmentation for real-time knowledge-driven activity recognition
Approaches and algorithms for activity recognition have recently made substantial progress due to advancements in pervasive and mobile computing, smart environments and ambient assisted living. Nevertheless, it is still difficult to achieve real-time ...
Comments