Personalised human activity recognition using matching networks.
Sani, Sadiq; Wiratunga, Nirmalie; Massie, Stewart; Cooper, Kay
Professor Nirmalie Wiratunga firstname.lastname@example.org
Doctor Stewart Massie email@example.com
Professor Kay Cooper firstname.lastname@example.org
Michael T. Cox
Human Activity Recognition (HAR) is typically modelled as a classification task where sensor data associated with activity labels are used to train a classifier to recognise future occurrences of these activities. 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. From a practical perspective however, collecting sufficient training data from end users may not be feasible. This has made using subject-independent training far more common in real-world HAR systems. 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, which makes them very relevant to case-based reasoning. A key advantage of matching networks is that they use metric learning to produce feature embeddings or representations that maximise classification accuracy, given a chosen similarity metric. Evaluations show our approach to substantially out perform general subject-independent models by at least 6% macro-averaged F1 score.
|Start Date||Jul 9, 2018|
|Publication Date||Nov 8, 2018|
|Publisher||Springer (part of Springer Nature)|
|Series Title||Lecture notes in computer science|
|Institution Citation||SANI, S., WIRATUNGA, N., MASSIE, S. and COOPER, K. 2018. Personalised human activity recognition using matching networks. In Cox, M.T., Funk, P. and Begum, S. (eds.) Case-based reasoning research and development: proceedings of the 26th International conference on case-based reasoning (ICCBR 2018), 9-12 July 2018, Stockholm, Sweden. Lecture notes in computer science, 11156. Cham: Springer [online], pages 339-353. Available from: https://doi.org/10.1007/978-3-030-01081-2_23|
|Keywords||Human activity recognition; Matching network; Casebased reasoning; Matching networks|
SANI 2018 Personalised human activity recognition
You might also like
Developing a catalogue of explainability methods to support expert and non-expert users.
Ontology driven information retrieval.
Improving kNN for human activity recognition with privileged learning using translation models.