Skip to main content

Research Repository

Advanced Search

Matching networks for personalised human activity recognition.

Sani, Sadiq; Wiratunga, Nirmalie; Massie, Stewart; Cooper, Kay


Sadiq Sani


Isabelle Bichindaritz

Christian Guttmann

Pau Herrero

Fernando Koch

Andrew Koster

Richard Lenz

Beatriz L�pez Ib��ez

Cindy Marling

Clare Martin

Sara Montagna

Stefania Montani

Manfred Reichert

David Ria�o

Michael I. Schumacher

Annette ten Teije


Human Activity Recognition (HAR) has many important applications in health care which include management of chronic conditions and patient rehabilitation. An important consideration when training HAR models is whether to use training data from a general population (subject-independent), or personalised training data from the target user (subject-dependent). Previous evaluations have shown personalised training to be more accurate because of the ability of resulting models to better capture individual users' activity patterns. However, collecting sufficient training data from end users may not be feasible for real-world applications. In this paper, we introduce a novel approach to personalised HAR using a neural network architecture called a matching network. Matching networks perform nearest-neighbour classification by reusing the class label of the most similar instances in a provided support set. Evaluations show our approach to substantially out perform general subject-independent models by more than 5% macro-averaged F1 score.


SANI, S., WIRATUNGA, N., MASSIE, S. and COOPER, K. 2018. Matching networks for personalised human activity recognition. In Bichindaritz, I., Guttmann, C., Herrero, P., Koch, F., Koster, A., Lenz, R., López Ibáñez, B., Marling, C., Martin, C., Montagna, S., Montani, S., Reichert, M., Riaño, D., Schumacher, M.I., ten Teije, A. and Wiratunga, N. (eds.) Proceedings of the 1st Joint workshop on artificial intelligence in health, organized as part of the Federated AI meeting (FAIM 2018), co-located with the 17th International conference on autonomous agents and multiagent systems (AAMAS 2018), the 35th International conference on machine learning (ICML 2018), the 27th International joint conference on artificial intelligence (IJCAI 2018), and the 26th International conference on case-based reasoning (ICCBR 2018), 13-19 July 2018, Stockholm, Sweden. CEUR workshop proceedings, 2142. Aachen: CEUR-WS [online], pages 61-64. Available from:

Conference Name 1st Joint workshop on artificial intelligence in health
Conference Location Stockholm, Sweden
Start Date Jul 13, 2018
End Date Jul 19, 2018
Acceptance Date Apr 24, 2018
Online Publication Date Jul 13, 2018
Publication Date Jul 23, 2018
Deposit Date Aug 17, 2018
Publicly Available Date Aug 17, 2018
Print ISSN 1613-0073
Publisher CEUR Workshop Proceedings
Pages 61-64
Series Title CEUR workshop proceedings
Series Number 2142
Series ISSN 1613-0073
Keywords Human activity recognition; Health care; Management of chronic conditions; SelfBACK project; Matching networks
Public URL
Publisher URL


You might also like

Downloadable Citations