Skip to main content

Research Repository

Advanced Search

Learning to compare with few data for personalised human activity recognition.

Wiratunga, Nirmalie; Wijekoon, Anjana; Cooper, Kay

Authors

Anjana Wijekoon



Contributors

Ian Watson
Editor

Rosina Weber
Editor

Abstract

Recent advances in meta-learning provides interesting opportunities for CBR research, in similarity learning, case comparison and personalised recommendations. Rather than learning a single model for a specific task, meta-learners adopt a generalist view of learning-to-learn, such that models are rapidly transferable to related (but different) new tasks. Unlike task-specific model training, a meta-learner’s training instance - referred to as a meta-instance - is a composite of two sets: a support set and a query set of instances. In our work, we introduce learning-to-learn personalised models from few data. We motivate our contribution through an application where personalisation plays an important role, mainly that of human activity recognition for self-management of chronic diseases. We extend the meta-instance creation process where random sampling of support and query sets is carried out on a reduced sample conditioned by a domain-specific attribute; namely the person or user, in order to create meta-instances for personalised HAR. Our meta-learning for personalisation is compared with several state-of-the-art meta-learning strategies: 1) matching network (MN), which learns an embedding for a metric function; 2) relation network (RN) that learns to predict similarity between paired instances; and 3) MAML, a model-agnostic machine-learning algorithm that optimizes the model parameters for rapid adaptation. Results confirm that personalised meta-learning significantly improves performance over non personalised meta-learners.

Citation

WIRATUNGA, N., WIJEKOON, A. and COOPER, K. 2020. Learning to compare with few data for personalised human activity recognition. In Watson, I and Weber, R. (eds.) Case-based reasoning research and development: proceedings of the 28th International conference on case-based reasoning research and development (ICCBR 2020), 8-12 June 2020, Salamanca, Spain [virtual conference]. Lecture notes in computer science, 12311. Cham: Springer [online], pages 3-14. Available from: https://doi.org/10.1007/978-3-030-58342-2_1

Conference Name 28th International conference on case-based reasoning research and development (ICCBR 2020)
Conference Location [virtual conference]
Start Date Jun 8, 2020
End Date Jun 12, 2020
Acceptance Date Apr 14, 2020
Online Publication Date Oct 3, 2020
Publication Date Oct 31, 2020
Deposit Date Jun 15, 2020
Publicly Available Date Jun 15, 2020
Publisher Springer
Volume 12311
Pages 3-14
Series Title Lecture notes in computer science
Series Number 12311
Series ISSN 0302-9743
Book Title Case-based resoning research and development: proceedings of the 28th International conference on case-based reasoning research and development 2020 (ICCBR 2020), 8-12 June 2020, Salamanca, Spain [virtual conference].
ISBN 9783030583415
DOI https://doi.org/10.1007/978-3-030-58342-2_1
Keywords Artificial intelligence; Machine learning; Meta-learning; Personalised meta-learning; Case-based reasoning
Public URL https://rgu-repository.worktribe.com/output/932917

Files





You might also like



Downloadable Citations