Musculoskeletal Disorders have a long term impact on individuals as well as on the community. They require self-management, typically in the form of maintaining an active lifestyle that adheres to prescribed exercises regimes. In the recent past m-health applications gained popularity by gamification of physical activity monitoring and has had a positive impact on general health and well-being. However maintaining a regular exercise routine with correct execution needs more sophistication in human movement recognition compared to monitoring ambulatory activities. In this research we propose a digital intervention which can intercept, recognize and evaluate exercises in real-time with a view to supporting exercise self-management plans. We plan to compile a heterogeneous multi-sensor dataset for exercises, then we will improve upon state of the art machine learning models implement reasoning methods to recognise exercises and evaluate performance quality.
WIJEKOON, A. 2018. Reasoning with multi-modal sensor streams for m-health applications. In Minor, M. (ed.) Workshop proceedings for the 26th International conference on case-based reasoning (ICCBR 2018), 9-12 July 2018, Stockholm, Sweden. Stockholm: ICCBR [online], pages 234-238. Available from: http://iccbr18.com/wp-content/uploads/ICCBR-2018-V3.pdf#page=234