An unsupervised approach to activity recognition and segmentation based on object-use fingerprints

Gu, T, Chen, S, Tao, X and Lu, J 2010, 'An unsupervised approach to activity recognition and segmentation based on object-use fingerprints', Elsevier Journal of Data and Knowledge Engineering (DKE), vol. 69, no. 6, pp. 533-544.


Document type: Journal Article
Collection: Journal Articles

Title An unsupervised approach to activity recognition and segmentation based on object-use fingerprints
Author(s) Gu, T
Chen, S
Tao, X
Lu, J
Year 2010
Journal name Elsevier Journal of Data and Knowledge Engineering (DKE)
Volume number 69
Issue number 6
Start page 533
End page 544
Total pages 12
Publisher Elsevier
Abstract Human activity recognition is an important task which has many potential applications. In recent years, researchers from pervasive computing are interested in deploying on-body sensors to collect observations and applying machine learning techniques to model and recognize activities. Supervised machine learning techniques typically require an appropriate training process in which training data need to be labeled manually. In this paper, we propose an unsupervised approach based on object-use fingerprints to recognize activities without human labeling. We show how to build our activity models based on object-use fingerprints, which are sets of contrast patterns describing significant differences of object use between any two activity classes. We then propose a fingerprint-based algorithm to recognize activities. We also propose two heuristic algorithms based on object relevance to segment a trace and detect the boundary of any two adjacent activities. We develop a wearable RFID system and conduct a real-world trace collection done by seven volunteers in a smart home over a period of 2 weeks. We conduct comprehensive experimental evaluations and comparison study. The results show that our recognition algorithm achieves a precision of 91.4% and a recall 92.8%, and the segmentation algorithm achieves an accuracy of 93.1% on the dataset we collected.
Subject Information Systems not elsewhere classified
Keyword(s) Human activity recognition
activity trace segmentation
contrast patterns
emerging patterns
fingerprint
object-use
web mining
RFID
DOI - identifier 10.1016/j.datak.2010.01.004
Copyright notice © 2010 Elsevier B.V. All rights reserved.
ISSN 0169-023X
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 63 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 71 times in Scopus Article | Citations
Altmetric details:
Access Statistics: 194 Abstract Views  -  Detailed Statistics
Created: Thu, 15 Jan 2015, 13:42:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us