Objective Training Load Monitoring Using Smart Swim Goggles
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Modern technology and analysis methods enable training loads (TLs) to be estimated from objective measurements. Various metrics have been developed to quantify TLs, including Banister’s training impulse (bTRIMP), session rating of perceived exertion (sRPE) TRIMP, and SwimScore. These metrics are expressed as a product of duration and an intensity component. The intensity component is the product of the average measure of training intensity for a session and a non-linear intensity multiplying factor (IMF). The IMF can be expressed as an exponential equation, Aebx, or a power law, Axb , with A and b as adjustable parameters. Theoretical work demonstrates that the relationships between TLs are determined primarily by the IMF. An unanswered question is the extent to which optimizing the IMF for a given TL metric can improve its association with observed changes in fitness. PURPOSE: To determine how the intensity components affect TL estimates and associations with changes in fitness. METHODS: Experienced recreational swimmers completed an individualized 12-week training program. Swimming fitness was measured through critical swim speed (CSS). We collected measures of sRPE via self-report, and measures of heart rate and swimming velocity from smart swim goggles (Form Athletica Inc., Vancouver). TL metrics were calculated from these data sources. We then iteratively adjusted the parameters of the IMFs for SwimScore and bTRIMP and evaluated the resulting association between the TLs and changes in CSS. RESULTS: Linear models fit with the change in fitness as the dependent variable and mean weekly TL as the independent variable revealed less than 50% of the variance being accounted for by the model. R2 values were 0.46, 0.09, and 0.00031 for SwimScore, bTRIMP, and sRPE-TRIMP, respectively. Adjusting the parameters for SwimScore and bTRIMP did not result in improved model fits. CONCLUSION: Manual tuning of IMF parameters did not improve the association of training loads and changes in fitness. Future research should employ formal optimization methods to find IMF parameter values that provide best-fit relationships between TLs and changes in CSS. MITACS, NSERC, Form Athletica Inc.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.003 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.002 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it