Globally, Low back pain (LBP) is one of the top three contributors to years lived with disability. Self-management with an active lifestyle is the cornerstone for preventing and managing LBP. Digital interventions are introduced in the recent past to improve and reinforce self-management where regular exercises are a core component and they rely on self-reporting to keep track of exercises performed. This data directly influences the recommendations made by the digital intervention where accurate and reliable reporting is fundamental to the success of the intervention. In addition, performing exercises with precision is important where current systems are unable to provide the guidance required. The main challenge to implementing an end-to-end solution is the lack of public sensor-rich datasets to implement Machine Learning algorithms to perform Exercise Recognition (ExR) and qualitative analysis. Accordingly we introduce the ExR benchmark dataset “MEx”, which we have shared publicly to encourage furthering research. In this paper we benchmark state-of-the art classification algorithms with deep and shallow architectures on each sensor and achieve performance up to 90.2%. We recognise the scope of each sensor in capturing exercise movements with confusion matrices and highlight the most suitable sensors for deployment considering performance vs. obtrusiveness.
WIJEKOON, A., WIRATUNGA, N., COOPER, K. and BACH, K. 2020. Learning to recognise exercises for the self-management of low back pain. In Barták, R. and Bell, E. (eds.). Proceedings of the 33rd International Florida Artificial Intelligence Research Society (FLAIRS) 2020 conference (FLAIRS-33), 17-20 May 2020, Miami Beach, USA. Palo Alto: AAAI Press [online], pages 347-352. Available from: https://aaai.org/ocs/index.php/FLAIRS/FLAIRS20/paper/view/18460