Dr Anjana Wijekoon a.wijekoon1@rgu.ac.uk
Research Fellow B
Dr Anjana Wijekoon a.wijekoon1@rgu.ac.uk
Research Fellow B
Professor Nirmalie Wiratunga n.wiratunga@rgu.ac.uk
Associate Dean for Research
Max Bramer
Editor
Richard Ellis
Editor
State-of-the-art methods of Human Activity Recognition(HAR) rely on a considerable amount of labelled data to train deep architectures. This becomes prohibitive when tasked with creating models that are sensitive to personal nuances in human movement, explicitly present when performing exercises and when it is infeasible to collect training data to cover the whole target population. Accordingly, learning personalised models with few data remains an open challenge in HAR research. We present a meta-learning methodology for learning-to-learn personalised models for HAR; with the expectation that the end-user only need to provide a few labelled data. These personalised HAR models benefit from the rapid adaptation of a generic meta-model using provided few end-user data. We implement the personalised meta-learning methodology with two algorithms, Personalised MAML and Personalised Relation Networks. A comparative study shows significant performance improvements against state-of-the-art deep learning algorithms and other personalisation algorithms in multiple HAR domains. Also, we show how personalisation improved meta-model training, to learn a generic meta-model suited for a wider population while using a shallow parametric model.
WIJEKOON, A. and WIRATUNGA, N. 2020. Personalised meta-learning for human activity recognition with few-data. In Bramer, M. and Ellis, R. (eds.) Artificial intelligence XXXVII: proceedings of 40th British Computer Society's Specialist Group on Artificial Intelligence (SGAI) Artificial intelligence international conference 2020 (AI-2020), 15-17 December 2020, [virtual conference]. Lecture notes in artificial intelligence, 12498. Cham: Springer [online], pages 79-93. Available from: https://doi.org/10.1007/978-3-030-63799-6_6
Conference Name | 40th British Computer Society's Specialist Group on Artificial Intelligence (SGAI) Artificial intelligence international conference 2020 (AI-2020) |
---|---|
Conference Location | [virtual conference] |
Start Date | Dec 15, 2020 |
End Date | Dec 17, 2020 |
Acceptance Date | Sep 3, 2020 |
Online Publication Date | Dec 8, 2020 |
Publication Date | Dec 31, 2020 |
Deposit Date | Sep 18, 2020 |
Publicly Available Date | Sep 18, 2020 |
Publisher | Springer |
Volume | 12498 |
Pages | 79-93 |
Series Title | Lecture notes in artificial intelligence |
Series ISSN | 0302-9743 |
Book Title | Artificial intelligence XXXVII: proceedings of 40th SGAI Artificial intelligence international conference (AI 2020), 15-17 December 2020, Cambridge, UK |
ISBN | 9783030637989 |
DOI | https://doi.org/10.1007/978-3-030-63799-6_6 |
Keywords | Personalisation; Human activity recognition; Meta-learning; Few-shot learning |
Public URL | https://rgu-repository.worktribe.com/output/968384 |
WIJEKOON 2020 Personalised meta (AAM)
(1.9 Mb)
PDF
CBR driven interactive explainable AI.
(2023)
Conference Proceeding
AGREE: a feature attribution aggregation framework to address explainer disagreements with alignment metrics.
(2023)
Conference Proceeding
The current and future role of visual question answering in eXplainable artificial intelligence.
(2023)
Conference Proceeding
About OpenAIR@RGU
Administrator e-mail: publications@rgu.ac.uk
This application uses the following open-source libraries:
Apache License Version 2.0 (http://www.apache.org/licenses/)
Apache License Version 2.0 (http://www.apache.org/licenses/)
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/)
Advanced Search