Optimal time window for temporal segmentation of sensor streams in multi-activity recognition

Liono, J, Qin, K and Salim, F 2016, 'Optimal time window for temporal segmentation of sensor streams in multi-activity recognition', in Proceedings of the 13th International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services (MOBIQUITOUS 2016), Hiroshima, Japan, 28 November -1 December 2016, pp. 10-19.


Document type: Conference Paper
Collection: Conference Papers

Title Optimal time window for temporal segmentation of sensor streams in multi-activity recognition
Author(s) Liono, J
Qin, K
Salim, F
Year 2016
Conference name MOBIQUITOUS 2016
Conference location Hiroshima, Japan
Conference dates 28 November -1 December 2016
Proceedings title Proceedings of the 13th International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services (MOBIQUITOUS 2016)
Publisher Association for Computing Machinery
Place of publication New York, United States
Start page 10
End page 19
Total pages 10
Abstract Multi-activity recognition in the urban environment is a challenging task. This is largely attributed to the influence of urban dynamics, the variety of the label sets, and the heterogeneous nature of sensor data that arrive irregularly and at different rates. One of the first tasks in multi-activity recognition is temporal segmentation. A common temporal segmentation method is the sliding window approach with a fixed window size, which is widely used for single activity recognition. In order to recognise multiple activities from heterogeneous sensor streams, we propose a new time windowing technique that can optimally extract segments with multiple activity labels. The mixture of activity labels causes the impurity in the corresponding temporal segment. Hence, larger window size imposes higher impurity in temporal segments while increasing class separability. In addition, the combination of labels from multiple activity label sets (i.e. number of unique multi-activity) may decrease as impurity increases. Naturally, these factors will affect the performance of classification task. In our proposed technique, the optimal window size is found by gaining the balance between minimising impurity and maximising class separability in temporal segments. As a result, it accelerates the learning process for recognising multiple activities (such as higher level and atomic human activities under different environment contexts) in comparison to laborious tasks of sensitivity analysis. The evaluation was validated by experiments on a real-world dataset for recognising multiple human activities in a smart environment.
Subjects Ubiquitous Computing
Pattern Recognition and Data Mining
Keyword(s) Temporal segmentation
Multivariate sensor streams
Multi-activity recognition
Data stream processing
Multi-objective function
Optimal window size
Copyright notice © 2016 Copyright is held by the owner/author(s). Publication rights licensed to Association for Computing Machinery (ACM)
ISBN 9781450347501
Versions
Version Filter Type
Access Statistics: 40 Abstract Views  -  Detailed Statistics
Created: Tue, 20 Dec 2016, 10:05:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us