kNN sampling for personalised human recognition.

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

Abstract

The need to adhere to recommended physical activity guidelines for a variety of chronic disorders calls for high precision Human Activity Recognition (HAR) systems. In the SelfBACK system, HAR is used to monitor activity types and intensities to enable self-management of low back pain (LBP). HAR is typically modelled as a classification task where sensor data associated with activity labels are used to train a classifier to predict future occurrences of those activities. An important consideration in HAR 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 that using personalised data results in more accurate predictions. However, from a practical perspective, collecting sufficient training data from the end user may not be feasible. This has made using subject-independent data by far the more common approach in commercial HAR systems. In this paper, we introduce a novel approach which uses nearest neighbour similarity to identify examples from a subject-independent training set that are most similar to sample data obtained from the target user and uses these examples to generate a personalised model for the user. This nearest neighbour sampling approach enables us to avoid much of the practical limitations associated with training a classifier exclusively with user data, while still achieving the benefit of personalisation. Evaluations show our approach to significantly out perform a general subject-independent model by up to 5%.

Citation

SANI, S., WIRATUNGA, N., MASSIE, S. and COOPER, K. 2017. kNN sampling for personalised human recognition. In Aha, D.W. and Lieber, J. (eds.) Case-based reasoning research and development: proceedings of the 25th International case-based reasoning conference (ICCBR 2017), 26-28 June 2017, Trondheim, Norway. Lecture notes in computer science, 10339. Cham: Springer [online], pages 330-344. Available from: https://doi.org/10.1007/978-3-319-61030-6_23

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 25th International case-based reasoning conference (ICCBR 2017)
• Start Date: Jun 26, 2017
• End Date: Jun 28, 2017
• Acceptance Date: Apr 12, 2017
• Online Publication Date: Jun 21, 2017
• Publication Date: Jun 21, 2017
• Deposit Date: Sep 1, 2017
• Publicly Available Date: Jun 22, 2018
• Print ISSN: 0302-9743
• Publisher: Springer
• Peer Reviewed: Peer Reviewed
• Pages: 330-344
• Series Title: Lecture notes in computer science
• Series Number: 10339
• Series ISSN: 0302-9743
• ISBN: 9783319610290
• DOI: https://doi.org/10.1007/978-3-319-61030-6_23
• Keywords: Physical activity; Chronic disorders; Human activity recognition (HAR); Low back pain
• Public URL: http://hdl.handle.net/10059/2486
• Contract Date: Sep 1, 2017