Dataset Information

Feasibility Study Comparing Physical Activity Classifications from Accelerometers with Wearable Camera Data.

ABSTRACT: Device-based assessments are frequently used to measure physical activity (PA) but contextual measures are often lacking. There is a need for new methods, and one under-explored option is the use of wearable cameras. This study tested the use of wearable cameras in PA measurement by comparing intensity classifications from accelerometers with wearable camera data. Seventy-eight 18-30-year-olds wore an Actigraph GT9X link accelerometer and Autographer wearable camera for three consecutive days. An image coding schedule was designed to assess activity categories and activity sub-categories defined by the 2011 Compendium of Physical Activities (Compendium). Accelerometer hourly detailed files processed using the Montoye (2020) cut-points were linked to camera data using date and time stamps. Agreement was examined using equivalence testing, intraclass correlation coefficient (ICC) and Spearman's correlation coefficient (rho). Fifty-three participants contributing 636 person-hours were included. Reliability was moderate to good for sedentary behavior (rho = 0.77), light intensity activities (rho = 0.59) and moderate-to-vigorous physical activity (MVPA) (rho = 0.51). The estimates of sedentary behavior, light activity and MVPA from the two methods were similar, but not equivalent. Wearable cameras are a potential complementary tool for PA measurement, but practical challenges and limitations exist. While wearable cameras may not be feasible for use in large scale studies, they may be feasible in small scale studies where context is important.

SUBMITTER: Davies A

PROVIDER: S-EPMC7764508 | biostudies-literature | 2020 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Feasibility Study Comparing Physical Activity Classifications from Accelerometers with Wearable Camera Data.

Davies Alyse A Allman-Farinelli Margaret M Owen Katherine K Signal Louise L Hosking Cameron C Wang Leanne L Bauman Adrian A

International journal of environmental research and public health 20201213 24

Device-based assessments are frequently used to measure physical activity (PA) but contextual measures are often lacking. There is a need for new methods, and one under-explored option is the use of wearable cameras. This study tested the use of wearable cameras in PA measurement by comparing intensity classifications from accelerometers with wearable camera data. Seventy-eight 18-30-year-olds wore an Actigraph GT9X link accelerometer and Autographer wearable camera for three consecutive days. A ...[more]

PMID: 33322117

Similar Datasets

Project description:BACKGROUND:Skin cancer is the most prevalent cancer in Australia. Skin cancer prevention programs aim to reduce sun exposure and increase sun protection behaviors. Effectiveness is usually assessed through self-report. OBJECTIVE:It was the aim of this study to test the acceptance and validity of a newly developed ultraviolet radiation (UVR) exposure app, designed to reduce the data collection burden to research participants. Physical activity data was collected because a strong focus on sun avoidance may result in unhealthy reductions in physical activity. This paper provides lessons learned from collecting data from participants using paper diaries, a mobile app, dosimeters, and accelerometers for measuring end-points of UVR exposure and physical activity. METHODS:Two participant groups were recruited through social and traditional media campaigns 1) Group A-UVR Diaries and 2) Group B-Physical Activity. In Group A, nineteen participants wore an UVR dosimeter wristwatch (University of Canterbury, New Zealand) when outside for 7 days. They also recorded their sun exposure and physical activity levels using both 1) the UVR diary app and 2) a paper UVR diary. In Group B, 55 participants wore an accelerometer (Actigraph, Pensacola, FL, USA) for 14 days and completed the UVR diary app. Data from the UVR diary app were compared with UVR dosimeter wristwatch, accelerometer, and paper UVR diary data. Cohen kappa coefficient score was used to determine if there was agreement between categorical variables for different UVR data collection methods and Spearman rank correlation coefficient was used to determine agreement between continuous accelerometer data and app-collected self-report physical activity. RESULTS:The mean age of participants in Groups A (n=19) and B (n=55) was 29.3 and 25.4 years, and 63% (12/19) and 75% (41/55) were females, respectively. Self-reported sun exposure data in the UVR app correlated highly with UVR dosimetry (?=0.83, 95% CI 0.64-1.00, P<.001). Correlation between self-reported UVR app and accelerometer-collected moderate to vigorous physical activity data was low (?=0.23, P=.10), while agreement for low-intensity physical activity was significantly different (?=-0.49, P<.001). Seventy-nine percent of participants preferred the app over the paper diary for daily self-report of UVR exposure and physical activity. CONCLUSIONS:This feasibility study highlights self-report using an UVR app can reliably collect personal UVR exposure, but further improvements are required before the app can also be used to collect physical activity data.

Project description:IntroductionWearable sensors may be used for the assessment of behavioral manifestations of cigarette smoking under natural conditions. This paper introduces a new camera-based sensor system to monitor smoking behavior. The goals of this study were (1) identification of the best position of sensor placement on the body and (2) feasibility evaluation of the sensor as a free-living smoking-monitoring tool.MethodsA sensor system was developed with a 5MP camera that captured images every second for continuously up to 26 hours. Five on-body locations were tested for the selection of sensor placement. A feasibility study was then performed on 10 smokers to monitor full-day smoking under free-living conditions. Captured images were manually annotated to obtain behavioral metrics of smoking including smoking frequency, smoking environment, and puffs per cigarette. The smoking environment and puff counts captured by the camera were compared with self-reported smoking.ResultsA camera located on the eyeglass temple produced the maximum number of images of smoking and the minimal number of blurry or overexposed images (53.9%, 4.19%, and 0.93% of total captured, respectively). During free-living conditions, 286,245 images were captured with a mean (±standard deviation) duration of sensor wear of 647(±74) minutes/participant. Image annotation identified consumption of 5(±2.3) cigarettes/participant, 3.1(±1.1) cigarettes/participant indoors, 1.9(±0.9) cigarettes/participant outdoors, and 9.02(±2.5) puffs/cigarette. Statistical tests found significant differences between manual annotations and self-reported smoking environment or puff counts.ConclusionsA wearable camera-based sensor may facilitate objective monitoring of cigarette smoking, categorization of smoking environments, and identification of behavioral metrics of smoking in free-living conditions.ImplicationsThe proposed camera-based sensor system can be employed to examine cigarette smoking under free-living conditions. Smokers may accept this unobtrusive sensor for extended wear, as the sensor would not restrict the natural pattern of smoking or daily activities, nor would it require any active participation from a person except wearing it. Critical metrics of smoking behavior, such as the smoking environment and puff counts obtained from this sensor, may generate important information for smoking interventions.

Project description:There are challenges for researchers and clinicians to select the most appropriate physical activity tool, and a balance between precision and feasibility is needed. Currently it is unclear which physical activity tool should be used to assess physical activity in Bronchiectasis. The aim of this research is to compare assessment methods (pedometer and IPAQ) to our criterion method (ActiGraph) for the measurement of physical activity dimensions in Bronchiectasis (BE), and to assess their feasibility and acceptability.Patients in this analysis were enrolled in a cross-sectional study. The ActiGraph and pedometer were worn for seven consecutive days and the IPAQ was completed for the same period. Statistical analyses were performed using SPSS 20 (IBM). Descriptive statistics were used; the percentage agreement between ActiGraph and the other measures were calculated using limits of agreement. Feedback about the feasibility of the activity monitors and the IPAQ was obtained.There were 55 (22 male) data sets available. For step count there was no significant difference between the ActiGraph and Pedometer, however, total physical activity time (mins) as recorded by the ActiGraph was significantly higher than the pedometer (mean?±?SD, 232 (75) vs. 63 (32)). Levels of agreement between the two devices was very good for step count (97% agreement); and variation in the levels of agreement were within accepted limits of ±2 standard deviations from the mean value. IPAQ reported more bouted- moderate - vigorous physical activity (MVPA) [mean, SD; 167(170) vs 6(9) mins/day], and significantly less sedentary time than ActiGraph [mean, SD; 362(115) vs 634(76) vmins/day]. There were low levels of agreement between the two tools (57% sedentary behaviour; 0% MVPA10+), with IPAQ under-reporting sedentary behaviour and over-reporting MVPA10+ compared to ActiGraph. The monitors were found to be feasible and acceptable by participants and researchers; while the IPAQ was accepta ble to use, most patients required assistance to complete it.Accurate measurement of physical activity is feasible in BE and will be valuable for future trials of therapeutic interventions. ActiGraph or pedometer could be used to measure simple daily step counts, but ActiGraph was superior as it measured intensity of physical activity and was a more precise measure of time spent walking. The IPAQ does not appear to represent an accurate measure of physical activity in this population.Clinical Trials Registration Number NCT01569009 : Physical Activity in Bronchiectasis.

Dataset Information

Feasibility Study Comparing Physical Activity Classifications from Accelerometers with Wearable Camera Data.

Publications

Feasibility Study Comparing Physical Activity Classifications from Accelerometers with Wearable Camera Data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets