Development And Validation Of A Smartphone As An Accelerometer-based Physical Activity Monitor
Bibliographic record
Abstract
Physical activity (PA) is a complex behaviour that plays an important role in human health. Numerous subjective and objective methods are utilized to assess free-living PA behaviours with varying success, but accelerometer-based PA monitors, which estimate the rate of energy expenditure due to PA (PAEE) in kcal per minute or metabolic equivalents (METS), have become a tool of choice in these studies. The latest generation of smartphones possess triaxial accelerometers, and are now receiving attention as possible PA monitors. The many features of smartphones may allow researchers to collect objective PAEE data more easily and for longer periods of time, while decreasing participant burden. PURPOSE: To determine whether or not a smartphone could be used as an accelerometer-based PA monitor for walking and running. METHODS: A software application was developed for the smartphone, which enabled the device to collect acceleration data and email these data to the researcher. Twenty-five healthy adults (11 males, 14 females) walked and ran at various speeds (2.5-7.0mph) on a treadmill while acceleration data and criterion measurements of PAEE (METS) were collected. Using panel regressions, a model was developed that transformed variables calculated from the acceleration data into estimates of activity type (walking or running), speed (mph), and PAEE (METS). The variables included standard deviation (vertical), root mean square (medio-lateral), and vector counts per minute. Accuracy was assessed through comparison with known types, speeds, and criterion measurements of PAEE. RESULTS: The model accuracy in identifying activity type was 99.0%. Estimated walking speed had a mean error of 0.011mph (SDERROR = 0.353mph), and running speed had a mean error of -0.017mph (SDERROR = 0.639mph). Estimated PAEE of walking had a mean error of 0.339METS (SDERROR = 0.663METS), and running had a mean error of -0.434METS (SDERROR = 1.16METS). CONCLUSION: The results of this study indicate that a smartphone can be used as an accelerometer-based PA monitor for treadmill walking and running in healthy adults, providing estimates of PAEE with accuracies similar to those published for other devices. Further development of this technology may improve the research tools used in studies of free-living PA behaviours.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".