CARL: a running recognition algorithm for free-living accelerometer data

Wearable accelerometers hold great promise for physical activity epidemiology and sports biomechanics. However, identifying and extracting data from specific physical activities, such as running, remains challenging. . To develop and validate an algorithm to identify bouts of running in raw, free-li...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Physiological measurement Ročník 42; číslo 11
Hlavní autoři: Davis, 4th, John J, Straczkiewicz, Marcin, Harezlak, Jaroslaw, Gruber, Allison H
Médium: Journal Article
Jazyk:angličtina
Vydáno: England 01.11.2021
Témata:
Accelerometry
Adult
Algorithms
Exercise
Humans
Monitoring, Ambulatory
Wrist
wearable sensors
wearable technology
machine learning
human activity recognition
ISSN:1361-6579, 1361-6579
On-line přístup:Zjistit podrobnosti o přístupu
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Wearable accelerometers hold great promise for physical activity epidemiology and sports biomechanics. However, identifying and extracting data from specific physical activities, such as running, remains challenging. . To develop and validate an algorithm to identify bouts of running in raw, free-living accelerometer data from devices worn at the wrist or torso (waist, hip, chest). . The CARL (continuous amplitude running logistic) classifier identifies acceleration data with amplitude and frequency characteristics consistent with running. The CARL classifier was trained on data from 31 adults wearing accelerometers on the waist and wrist, then validated on free-living data from 30 new, unseen subjects plus 166 subjects from previously-published datasets using different devices, wear locations, and sample frequencies. . On free-living data, the CARL classifier achieved mean accuracy ( score) of 0.984 (95% confidence interval 0.962-0.996) for data from the waist and 0.994 (95% CI 0.991-0.996) for data from the wrist. In previously-published datasets, the CARL classifier identified running with mean accuracy ( score) of 0.861 (95% CI 0.836-0.884) for data from the chest, 0.911 (95% CI 0.884-0.937) for data from the hip, 0.916 (95% CI 0.877-0.948) for data from the waist, and 0.870 (95% CI 0.834-0.903) for data from the wrist. Misclassification primarily occurred during activities with similar torso acceleration profiles to running, such as rope jumping and elliptical machine use. . The CARL classifier can accurately identify bouts of running as short as three seconds in free-living accelerometry data. An open-source implementation of the CARL classifier is available atgithub.com/johnjdavisiv/carl.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1361-6579
1361-6579
DOI:10.1088/1361-6579/ac41b8