Dataset Information

Towards a Portable Model to Discriminate Activity Clusters from Accelerometer Data.

ABSTRACT: 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.

SUBMITTER: Jones P

PROVIDER: S-EPMC6832944 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Purpose: Most built environment studies have quantified characteristics of the areas around participants' homes. However, the environmental exposures for physical activity (PA) are spatially dynamic rather than static. Thus, merged accelerometer and global positioning system (GPS) data were utilized to estimate associations between the built environment and PA among adults. Methods: Participants (N = 142) were recruited on trails in Massachusetts and wore an accelerometer and GPS unit for 1-4 days. Two binary outcomes were created: moderate-to-vigorous PA (MVPA vs. light PA-to-sedentary); and light-to-vigorous PA (LVPA vs. sedentary). Five built environment variables were created within 50-meter buffers around GPS points: population density, street density, land use mix (LUM), greenness, and walkability index. Generalized linear mixed models were fit to examine associations between environmental variables and both outcomes, adjusting for demographic covariates. Results: Overall, in the fully adjusted models, greenness was positively associated with MVPA and LVPA (odds ratios [ORs] = 1.15, 95% confidence interval [CI] = 1.03, 1.30 and 1.25, 95% CI = 1.12, 1.41, respectively). In contrast, street density and LUM were negatively associated with MVPA (ORs = 0.69, 95% CI = 0.67, 0.71 and 0.87, 95% CI = 0.78, 0.97, respectively) and LVPA (ORs = 0.79, 95% CI = 0.77, 0.81 and 0.81, 95% CI = 0.74, 0.90, respectively). Negative associations of population density and walkability with both outcomes reached statistical significance, yet the effect sizes were small. Conclusions: Concurrent monitoring of activity with accelerometers and GPS units allowed us to investigate relationships between objectively measured built environment around GPS points and minute-by-minute PA. Negative relationships between street density and LUM and PA contrast evidence from most built environment studies in adults. However, direct comparisons should be made with caution since most previous studies have focused on spatially fixed buffers around home locations, rather than the precise locations where PA occurs.

Project description:ObjectivePhysical activity is critically important for successful aging, but its effect on adiposity markers at older ages is unclear as much of the evidence comes from self-reported data on physical activity. We assessed the associations of questionnaire-assessed and accelerometer-assessed physical activity with adiposity markers in older adults.Design/setting/participantsThis was a cross-sectional study on 3940 participants (age range 60-83 years) of the Whitehall II study who completed a 20-item physical activity questionnaire and wore a wrist-mounted accelerometer for 9 days in 2012 and 2013.MeasurementsTotal physical activity was estimated using metabolic equivalent hours/week for the questionnaire and mean acceleration for the accelerometer. Time spent in moderate-and-vigorous physical activity (MVPA) was also assessed by questionnaire and accelerometer. Adiposity assessment included body mass index, waist circumference, and fat mass index. Fat mass index was calculated as fat mass/height² (kg/m²), with fat mass estimated using bioimpedance.ResultsGreater total physical activity was associated with lower adiposity for all adiposity markers in a dose-response manner. In men, the strength of this association was 2.4 to 2.8 times stronger with the accelerometer than with questionnaire data. In women, it was 1.9 to 2.3 times stronger. For MVPA, questionnaire data in men suggested no further benefit for adiposity markers past 1 hour/week of activity. This was not the case for accelerometer-assessed MVPA where, for example, compared with men undertaking <1 hour/week of accelerometer-assessed MVPA, waist circumference was 3.06 (95% confidence interval 2.06-4.06) cm lower in those performing MVPA 1-2.5 hours/week, 4.69 (3.47-5.91) cm lower in those undertaking 2.5-4 hours/week, and 7.11 (5.93-8.29) cm lower in those performing ≥4 hours/week.ConclusionsThe association of physical activity with adiposity markers in older adults was stronger when physical activity was assessed by accelerometer compared with questionnaire, suggesting that physical activity might be more important for adiposity than previously estimated.

Dataset Information

Towards a Portable Model to Discriminate Activity Clusters from Accelerometer Data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets