Detection of High-Intensity Interval Training in Accelerometer Data
Bibliographic record
Abstract
High-intensity interval training (HIIT) may lead to superior cardiometabolic benefits compared to moderate-intensity continuous training (MICT) and inactive individuals may prefer HIIT over MICT. Adherence to HIIT in a free-living environment is now a much-needed area of investigation. Accelerometers provide an objective measure of physical activity, but the detection of HIIT in accelerometer data has not previously been evaluated. PURPOSE: To devise and test a HIIT detecting algorithm. METHODS: Eight participants with prediabetes (age = 43±10 years; BMI = 31±6) participated in a 10 day, supervised HIIT intervention and were then asked to maintain HIIT over one month of independent free-living exercise. Accelerometer data was collected for three days during the intervention and for seven consecutive days after one-month of independent exercise. An algorithm that relied on Freedson cut points and was based on the alternating pattern of high and low peaks characteristic of HIIT in accelerometer data was developed. When analyzing the data using Freedson cut points, many bouts of HIIT were missed, even on supervised training days. Specifically, the brief bursts of vigorous physical activity (VPA) were not being detected due to not meeting Freedson cut point in magnitude and/or duration. As a result, a second algorithm that did not rely on Freedson cut points was created that systematically cycles through possible cut points while detecting the high-low HIIT pattern. RESULTS: The two algorithms were run on participants’ one-month free-living accelerometry data. Using Freedson cut points, 19 bouts and a total of 128 minutes of HIIT were detected in the data. With the second algorithm, 22 bouts and 356 min were detected. Visual data inspection confirmed these results. A paired t-test for number of minutes detected per participant showed a significant difference between algorithms at p = 0.02. CONCLUSION: Algorithms for the automatic detection of HIIT in accelerometer data were developed. A limitation is in defining when a person is engaged in VPA. The present data suggests Freedson cut points used primarily to analyze continuous bouts of activity may not allow for the accurate detection of HIIT in a sample of inactive individuals with prediabetes. Supported by UBC internal research fund
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 | 0.002 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".