Accuracy of physical activity recognition from a wrist-worn sensor.
MetadataShow full item record
COOPER, K., SANI, S., CORRIGAN, L., MACDONALD, H., PRENTICE, C., VARETA, R., MASSIE, S. and WIRATUNGA, N. 2017. Accuracy of physical activity recognition from a wrist-worn sensor. Presented at the Physiotherapy UK conference and trade exhibition 2017: transform lives, maximise independence and empower populations, 10-11 November 2017, Birmingham, UK.
The EU-funded project 'selfBACK' (http://www.selfback.eu) will utilise continuous objective monitoring of physical activity (PA) by a wrist-mounted wearable, combined with self-monitoring of symptoms and case-based reasoning. Together these will provide personalised self-management plans to people with low back pain via a novel digital health intervention. The purpose of this study was to determine the accuracy of PA recognition via wrist-mounted sensors compared to thigh-mounted sensors. Thigh or hip-mounted sensors have previously been shown to be the most accurate placement for single sensor-based PA monitoring. However, long-term adherence may be greatly enhanced with a less obtrusive wrist-worn sensor. It was therefore important to compare both locations.