Unsupervised online activity discovery using temporal behaviour assumption

Gjoreski, Hristijan and Roggen, Daniel (2017) Unsupervised online activity discovery using temporal behaviour assumption. The 21st International Symposium on Wearable Computers (ISWC), Maui, Hawai, USA, 11.09 - 15.09.2017. Published in: International Symposium on Wearable Computers. 1 (3) 42-49. Association for Computing Machinery ISBN 9781450351881

[img] PDF - Accepted Version
Download (957kB)


We present a novel unsupervised approach, UnADevs, for discovering activity clusters corresponding to periodic and stationary activities in streaming sensor data. Such activities usually last for some time, which is exploited by our method; it includes mechanisms to regulate sensitivity to brief outliers and can discover multiple clusters overlapping in time to better deal with deviations from nominal behaviour. The method was evaluated on two activity datasets containing large number of activities (14 and 33 respectively) against online agglomerative clustering and DBSCAN. In a multi-criteria evaluation, our approach achieved significantly better performance on majority of the measures, with the advantages that: (i) it does not require to specify the number of clusters beforehand (it is open ended); (ii) it is online and can find clusters in real time; (iii) it has constant time complexity; (iv) and it is memory efficient as it does not keep the data samples in memory. Overall, it has managed to discover 616 of the total 717 activities. Because it discovers clusters of activities in real time, it is ideal to work alongside an active learning system.

Item Type: Conference Proceedings
Keywords: Activity recognition; Activity discovery; Online temporal clustering; Accelerometer; Segmentation
Schools and Departments: School of Engineering and Informatics > Engineering and Design
Research Centres and Groups: Sensor Technology Research Centre
Subjects: Q Science > Q Science (General) > Q0300 Cybernetics
Q Science > QA Mathematics > QA0276 Mathematical statistics
Q Science > QA Mathematics > QA0075 Electronic computers. Computer science
Depositing User: Hristijan Gjoreski
Date Deposited: 17 Jul 2017 07:42
Last Modified: 17 Oct 2017 11:10
URI: http://srodev.sussex.ac.uk/id/eprint/69277

View download statistics for this item

📧 Request an update
Project NameSussex Project NumberFunderFunder Ref
Lifelearn: Unbounded activity and context awarenessG1786EPSRC-ENGINEERING & PHYSICAL SCIENCES RESEARCH COUNCILEP/N007816/1