To date, non-wear detection algorithms commonly employ a 30, 60, or even 90 mins interval or window in which acceleration values need to be below a threshold value. A major drawback of such intervals is that they need to be long enough to prevent false positives (type I errors), while short enough to prevent false negatives (type II errors), which limits detecting both short and longer episodes of non-wear time. In this paper, we propose a novel non-wear detection algorithm that eliminates the need for an interval. Rather than inspecting acceleration within intervals, we explore acceleration right before and right after an episode of non-wear time. We trained a deep convolutional neural network that was able to infer non-wear time by detecting when the accelerometer was removed and when it was placed back on again. We evaluate our algorithm against several baseline and existing non-wear algorithms, and our algorithm achieves a perfect precision, a recall of 0.9962, and an F1 score of 0.9981, outperforming all evaluated algorithms. Although our algorithm was developed using patterns learned from a hip-worn accelerometer, we propose algorithmic steps that can easily be applied to a wrist-worn accelerometer and a retrained classification model.

 

NOTE: This study used the CamNtech Actiwave Cardio which was discontinued in Jan 2019 – The direct replacement is Actiheart 5 which offers superior performance.

 

Direct Link: https://doi.org/10.1038/s41598-021-87757-z

Journal: Scientific Reports. 2021 Apr 23;11(1):1-2.

Keywords: ECG, neural networks, non-wear detection, Physical Activity,

Applications: Physical Activity,

CamNtech Reference: AH21063

Back to Search Results

UK & International customers

CamNtech Ltd.
Manor Farm
Fenstanton
Cambridgeshire
PE28 9JD, UK

US customers

CamNtech Inc.
630 Boerne Stage Airfield,
Boerne,
Texas 78006,
USA

Copyright

© 2024 CamNtech Ltd and CamNtech Inc

Company information

Registered in England No. 2221302
VAT No: GB486 3019 34


Privacy Policy