Author:
Rüdiger Zillmer
Affiliation:
Unilever R&D Port Sunlight, United Kingdom
Keyword(s):
Activity monitoring, Free-living, Accelerometer, Classification.
Related
Ontology
Subjects/Areas/Topics:
Applications and Services
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computer Vision, Visualization and Computer Graphics
;
Devices
;
Health Information Systems
;
Human-Computer Interaction
;
Medical Image Detection, Acquisition, Analysis and Processing
;
Physiological Computing Systems
;
Wearable Sensors and Systems
Abstract:
The present paper discusses the characterisation of toothbrushing activity, using acceleration data collected for 50 subjects in free-living conditions. The data logging is triggered by super-threshold values of acceleration, which can give rise to false activations by non-brushing activities. Due to large intra and inter individual variations, it is not possible to obtain an exhaustive training-set of all activities that trigger the logging. Thus, a structural analysis of appropriate data features is performed, which reveals a clustering of the data. The comparison with brushing activity traces from laboratory experiments allows the identification of toothbrushing activity, while the remainder corresponds to various false activation events like electronic noise or brush handling. The distribution of the resulting toothbrushing activity shows distinct peaks for morning and night brushing activity.