Detection of physical activity types with accelerometers in adolescents in free-living settings

2016 ◽  
Vol 49 ◽  
pp. 201-202
Keyword(s):  
Physical Activity ◽  
Free Living ◽  
Activity Types

scholarly journals A Machine Learning Classifier for Detection of Physical Activity Types and Postures During Free-Living

2021 ◽  
pp. 1-8
Author(s):  
Kerstin Bach ◽  
Atle Kongsvold ◽  
Hilde Bårdstu ◽  
Ellen Marie Bardal ◽  
Håkon S. Kjærnli ◽  
...  
Keyword(s):  
Physical Activity ◽  
Machine Learning ◽  
Ground Truth ◽  
Daily Physical Activity ◽  
Gradient Boosting ◽  
Free Living ◽  
Recording Time ◽  
Learning Classifier ◽  
Extreme Gradient Boosting ◽  
Activity Types

Introduction: Accelerometer-based measurements of physical activity types are commonly used to replace self-reports. To advance the field, it is desirable that such measurements allow accurate detection of key daily physical activity types. This study aimed to evaluate the performance of a machine learning classifier for detecting sitting, standing, lying, walking, running, and cycling based on a dual versus single accelerometer setups during free-living. Methods: Twenty-two adults (mean age [SD, range] 38.7 [14.4, 25–68] years) were wearing two Axivity AX3 accelerometers positioned on the low back and thigh along with a GoPro camera positioned on the chest to record lower body movements during free-living. The labeled videos were used as ground truth for training an eXtreme Gradient Boosting classifier using window lengths of 1, 3, and 5 s. Performance of the classifier was evaluated using leave-one-out cross-validation. Results: Total recording time was ∼38 hr. Based on 5-s windowing, the overall accuracy was 96% for the dual accelerometer setup and 93% and 84% for the single thigh and back accelerometer setups, respectively. The decreased accuracy for the single accelerometer setup was due to a poor precision in detecting lying based on the thigh accelerometer recording (77%) and standing based on the back accelerometer recording (64%). Conclusion: Key daily physical activity types can be accurately detected during free-living based on dual accelerometer recording, using an eXtreme Gradient Boosting classifier. The overall accuracy decreases marginally when predictions are based on single thigh accelerometer recording, but detection of lying is poor.

scholarly journals Towards a Portable Model to Discriminate Activity Clusters from Accelerometer Data

Sensors ◽  
2019 ◽  
Vol 19 (20) ◽  
pp. 4504 ◽  
Author(s):  
Petra Jones ◽  
Evgeny M. Mirkes ◽  
Tom Yates ◽  
Charlotte L. Edwardson ◽  
Mike Catt ◽  
...  
Keyword(s):  
Physical Activity ◽  
Cross Validation ◽  
Accelerometer Data ◽  
Activity Type ◽  
Free Living ◽  
Independent Dataset ◽  
Clustering Model ◽  
Activity Types ◽  
Unsupervised Approach ◽  
Viable Approach

Few methods for classifying physical activity from accelerometer data have been tested using an independent dataset for cross-validation, and even fewer using multiple independent datasets. The aim of this study was to evaluate whether unsupervised machine learning was a viable approach for the development of a reusable clustering model that was generalisable to independent datasets. We used two labelled adult laboratory datasets to generate a k-means clustering model. To assess its generalised application, we applied the stored clustering model to three independent labelled datasets: two laboratory and one free-living. Based on the development labelled data, the ten clusters were collapsed into four activity categories: sedentary, standing/mixed/slow ambulatory, brisk ambulatory, and running. The percentages of each activity type contained in these categories were 89%, 83%, 78%, and 96%, respectively. In the laboratory independent datasets, the consistency of activity types within the clusters dropped, but remained above 70% for the sedentary clusters, and 85% for the running and ambulatory clusters. Acceleration features were similar within each cluster across samples. The clusters created reflected activity types known to be associated with health and were reasonably robust when applied to diverse independent datasets. This suggests that an unsupervised approach is potentially useful for analysing free-living accelerometer data.

Validity of the Acti4 method for detection of physical activity types in free-living settings: comparison with video analysis

Ergonomics ◽  
2015 ◽  
Vol 58 (6) ◽  
pp. 953-965 ◽  
Author(s):  
Ingunn Stemland ◽  
Jørgen Ingebrigtsen ◽  
Caroline S. Christiansen ◽  
Bente R. Jensen ◽  
Christiana Hanisch ◽  
...  
Keyword(s):  
Physical Activity ◽  
Video Analysis ◽  
Free Living ◽  
Activity Types

Detection of Physical Activity Types Using Triaxial Accelerometers

2014 ◽  
Vol 11 (1) ◽  
pp. 76-84 ◽  
Author(s):  
Jørgen Skotte ◽  
Mette Korshøj ◽  
Jesper Kristiansen ◽  
Christiana Hanisch ◽  
Andreas Holtermann
Keyword(s):  
Physical Activity ◽  
Sensitivity And Specificity ◽  
Standardized Test ◽  
Test Procedure ◽  
Pressure Sensors ◽  
High Sensitivity ◽  
Threshold Values ◽  
Free Living ◽  
Sitting Posture ◽  
Activity Types

Background:The aim of this study was to validate a triaxial accelerometer setup for identifying everyday physical activity types (ie, sitting, standing, walking, walking stairs, running, and cycling).Methods:Seventeen subjects equipped with triaxial accelerometers (ActiGraph GT3X+) at the thigh and hip carried out a standardized test procedure including walking, running, cycling, walking stairs, sitting, and standing still. A method was developed (Acti4) to discriminate between these physical activity types based on threshold values of standard deviation of acceleration and the derived inclination. Moreover, the ability of the accelerometer placed at the thigh to detect sitting posture was separately validated during free living by comparison with recordings of pressure sensors in the hip pockets.Results:Sensitivity for discriminating between the physical activity types sitting, standing, walking, running, and cycling in the standardized trials were 99%–100% and 95% for walking stairs. Specificity was higher than 99% for all activities. During free living (140 hours of measurements), sensitivity and specificity for detection of sitting posture were 98% and 93%, respectively.Conclusion:The developed method for detecting physical activity types showed a high sensitivity and specificity for sitting, standing, walking, running, walking stairs, and cycling in a standardized setting and for sitting posture during free living.

Automatic identification of physical activity types and sedentary behaviors from triaxial accelerometer: laboratory-based calibrations are not enough

2015 ◽  
Vol 118 (6) ◽  
pp. 716-722 ◽  
Author(s):  
Thomas Bastian ◽  
Aurélia Maire ◽  
Julien Dugas ◽  
Abbas Ataya ◽  
Clément Villars ◽  
...  
Keyword(s):  
Physical Activity ◽  
Real Life ◽  
Classification Algorithm ◽  
Living Conditions ◽  
Automatic Identification ◽  
Sedentary Behaviors ◽  
Triaxial Accelerometer ◽  
Free Living ◽  
Activity Types ◽  
Free Living Conditions

“Objective” methods to monitor physical activity and sedentary patterns in free-living conditions are necessary to further our understanding of their impacts on health. In recent years, many software solutions capable of automatically identifying activity types from portable accelerometry data have been developed, with promising results in controlled conditions, but virtually no reports on field tests. An automatic classification algorithm initially developed using laboratory-acquired data (59 subjects engaging in a set of 24 standardized activities) to discriminate between 8 activity classes (lying, slouching, sitting, standing, walking, running, and cycling) was applied to data collected in the field. Twenty volunteers equipped with a hip-worn triaxial accelerometer performed at their own pace an activity set that included, among others, activities such as walking the streets, running, cycling, and taking the bus. Performances of the laboratory-calibrated classification algorithm were compared with those of an alternative version of the same model including field-collected data in the learning set. Despite good results in laboratory conditions, the performances of the laboratory-calibrated algorithm (assessed by confusion matrices) decreased for several activities when applied to free-living data. Recalibrating the algorithm with data closer to real-life conditions and from an independent group of subjects proved useful, especially for the detection of sedentary behaviors while in transports, thereby improving the detection of overall sitting (sensitivity: laboratory model = 24.9%; recalibrated model = 95.7%). Automatic identification methods should be developed using data acquired in free-living conditions rather than data from standardized laboratory activity sets only, and their limits carefully tested before they are used in field studies.

scholarly journals A Comparison of Two Motion Sensors for the Assessment of Free-Living Physical Activity of Adolescents

2010 ◽  
Vol 7 (4) ◽  
pp. 1558-1576 ◽  
Author(s):  
Roman Cuberek ◽  
Walid El Ansari ◽  
Karel Frömel ◽  
Krzysztof Skalik ◽  
Erik Sigmund
Keyword(s):  
Physical Activity ◽  
Motion Sensors ◽  
Free Living

Analysis of Physical Activity Among Free–Living Nonagenarians From a Sardinian Longevous Population

2018 ◽  
Vol 26 (2) ◽  
pp. 254-258 ◽  
Author(s):  
Giovanni Mario Pes ◽  
Maria Pina Dore ◽  
Alessandra Errigo ◽  
Michel Poulain
Keyword(s):  
Physical Activity ◽  
Free Living

scholarly journals Objective measurement of physical activity in Macaca fascicularis

1982 ◽  
Vol 16 (3) ◽  
pp. 240-243
Author(s):  
Wayne T. Corbett ◽  
Harry M. Schey ◽  
A. W. Green
Keyword(s):  
Physical Activity ◽  
Standard Deviation ◽  
Macaca Fascicularis ◽  
Living Environment ◽  
Activity Levels ◽  
Free Living ◽  
Activity Measurements ◽  
Active Intermediate ◽  
The Mean ◽  
The Relationship

The mean and standard deviation over 24 h for 3 groups of animals - active, intermediate and inactive - in physical activity units were 10948 ± 3360, 2611 ± 1973 and 484 ± 316 respectively. The differences were significant ( P = 0·004), demonstrating the ability of the method to distinguish between groups that can be visibly differentiated. The small within-animal physical activity standard deviation (18·85 PAU) obtained in another group, suggests that it also yields reliable physical activity measurements for non-human primates. The monitoring device used can discriminate between individual nonhuman primate physical activity levels in a free-living environment and does not alter daily behaviour. This makes possible the study of the relationship between physical activity and atherosclerosis in nonhuman primates.

Sign in / Sign up

Export Citation Format

Share Document