Matching networks for personalised human activity recognition.
MetadataShow full item record
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 17th International autonomous agents and multiagent systems conference (AAMAS 2018), 35th International conference on machine learning (ICML 2018), 27th International joint conference on artificial intelligence (IJCAI 2018) and 26th International conference on case-based reasoning (ICCBR 2018), 13-19 July 2018, Stockholm, Sweden. Stockholm: CEUR [online], pages 61-64. Available from: http://ceur-ws.org/Vol-2142/short4.pdf
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.