Sulaimon Adebayo Bashir
A framework for unsupervised change detection in activity recognition.
Bashir, Sulaimon Adebayo; Petrovski, Andrei; Doolan, Daniel
Authors
Andrei Petrovski
Daniel Doolan
Abstract
Purpose - This purpose of this paper is to develop a change detection technique for activity recognition model. The approach aims to detect changes in the initial accuracy of the model after training and when the model is deployed for recognizing new unseen activities without access to the ground truth. The changes between the two sessions may occur because of differences in sensor placement, orientation and user characteristics such as age and gender. However, many of the existing approaches for model adaptation in activity recognition are blind methods because they continuously adapt the recognition model without explicit detection of changes in the model performance. Design/methodology/approach - The approach determines the variation between reference activity data belonging to different classes and newly classified unseen data. If there is coherency between the data, it means the model is correctly classifying the instances; otherwise, a significant variation indicates wrong instances are being classified to different classes. Thus, the approach is formulated as a two-level architectural framework comprising of the off-line phase and the online phase. The off-line phase extracts of Shewart Chart change parameters from the training data set. The online phase performs classification of new samples and the detection of the changes in each class of activity present in the data set by using the change parameters computed earlier. Findings - The approach is evaluated using a real activity-recognition data set. The results show that there are consistent detections that correlate with the error rate of the model. Originality/value - The developed approach does not use ground truth to detect classifier performance degradation. Rather, it uses a data discrimination method and a base classifier to detect the changes by using the parameters computed from the reference data of each class to discriminate outliers in the new data being classified to the same class. The approach is the first, to the best of the authors' knowledge, that addresses the problem of detecting within-user and cross-user variations that lead to concept drift in activity recognition. The approach is also the first to use statistical process control method for change detection in activity recognition, with a robust integrated framework that seamlessly detects variations in the underlying model performance.
Citation
BASHIR, S.A., PETROVSKI, A. and DOOLAN, D. 2017. A framework for unsupervised change detection in activity recognition. International journal of pervasive computing and communications [online], 13(2), pages 157-175. Available from: https://doi.org/10.1108/IJPCC-03-2017-0027
Journal Article Type | Article |
---|---|
Acceptance Date | Apr 3, 2017 |
Online Publication Date | Jun 5, 2017 |
Publication Date | Jun 30, 2017 |
Deposit Date | Oct 3, 2017 |
Publicly Available Date | Oct 3, 2017 |
Journal | International journal of pervasive computing and communications |
Print ISSN | 1742-7371 |
Electronic ISSN | 1742-738X |
Publisher | Emerald |
Peer Reviewed | Peer Reviewed |
Volume | 13 |
Issue | 2 |
Pages | 157-175 |
DOI | https://doi.org/10.1108/IJPCC-03-2017-0027 |
Keywords | Activity recognition; Change detection; Concept drift; Machine learning; Model adaptation |
Public URL | http://hdl.handle.net/10059/2524 |
Contract Date | Oct 3, 2017 |
Files
BASHIR 2017 A framework for unsupervised change
(3.2 Mb)
PDF
Publisher Licence URL
https://creativecommons.org/licenses/by-nc/4.0/
You might also like
Applications of artificial intelligence in geothermal resource exploration: a review.
(2024)
Journal Article
Securing cyber-physical systems with two-level anomaly detection strategy.
(2024)
Presentation / Conference Contribution
Temporal graph convolutional autoencoder based fault detection for renewable energy applications.
(2024)
Presentation / Conference Contribution
Downloadable Citations
About OpenAIR@RGU
Administrator e-mail: publications@rgu.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2025
Advanced Search