A Smart Sensing Wheelchair System (SSWS) for Continuous Sitting Posture Recognition and Monitoring using Machine Learning and a Mobile App.

The COVID-19 pandemic has posed major challenges for healthcare. The NHS is considering how it meets the rehabilitation needs of people who require long term postural management and whose health and level of activity and participation has been severely impacted. Currently, healthcare professionals undertake regular postural assessments of individuals who require special seating to manage their posture. These assessments are resource-intensive, time-consuming, require close physical contact with clinical staff, and may cause considerable discomfort and distress to the patients. The assessments also require that patients travel to a specialised clinic. There is an urgent need for a remote health monitoring solution that can continuously collect and process the data from a wheelchair to obtain clinical information related to the patient’s condition, the state of repair of the seating, and estimate the optimum time for reassessment.

We propose a novel SSWS equipped with low cost and unobtrusive sensors embedded in the seat covering to monitor and record several quantities of interest (such as pressure, shear force, temperature, humidity, respiration and heart rate) across the seat surface, thus enabling continuous posture and health monitoring. An algorithm has been developed to obtain interpretable measures related to the patient’s posture and health (such as sitting duration, level of asymmetry, active and static sitting, pressure areas and balance when seated), enabling posture classification and linking the data with the specific musculoskeletal condition. In addition, the research aims to determine if AI techniques could be developed to predict the need and optimum time for the reassessment.

Figure 1. A Smart Sensing Wheelchair System (SSWS)

References:

1. Kulon, J., Partlow, A., Gibson, C., Wilson, I. and Wilcox, S. J., “Rule-Based Algorithm for the Classification of Sitting Postures in the Sagittal Plane from the Cardiff Body Match Measurement System,” Journal of Medical Engineering and Technology, vol. 38, no. 1, pp 5-15, 2014. DOI: 10.3109/03091902.2013.844208


2. Partlow A., Gibson G., Kulon J., Wilson I., Wilcox S. Pelvis feature extraction and classification of Cardiff body match rig base measurements for input into a knowledge-based system, Journal of Medical Engineering & Technology, vol. 36, no. 8, pp. 399-406, Nov. 2012. DOI: 10.3109/03091902.2012.712202