Identification and Classification of Physical Fatigue in Construction Workers Using Linear and Nonlinear Heart Rate Variability Measurements
Bibliographic record
Abstract
Several studies have analyzed heart rate variability (HRV) using nonlinear methods, such as approximate entropy, the largest Lyapunov exponent, and correlation dimension in patients with cardiovascular disorders. However, no studies have used nonlinear methods to analyze HRV so as to evaluate physical fatigue in construction workers. Therefore, the current study evaluated the linear and nonlinear methods of analyzing HRV in order to identify and classify physical fatigue in construction workers. Fifteen healthy construction workers aged 18 years or older (mean age, 33.2 6.9 years) were recruited. Following the baseline assessments, each participant was asked to perform 60-minute bar bending and fixing tasks, while the corresponding HRV was measured by a textile-based wearable sensor. Subjective fatigue levels were measured using the Borg-20 at baseline, 15, 30, 45, and 60 minutes of the task. The sensor was used to extract linear (e.g., time- and frequency-domain) and nonlinear (e.g., RRI variability, entropy, and detrended fluctuation analysis) HRV features. Five machine learning classifiers were used to identify fatigue and discern different physical fatigue levels. The accuracy and validity of the classifier models were evaluated using 10-fold cross-validation. The classification models were developed by combining and individualizing HRV features derived from linear and nonlinear analysis. In the individualized feature sets, time-domain features had the highest classification accuracy (92%) for the RF classifier. The combined feature (the time-domain and nonlinear features) sets showed the highest classification accuracy (93.5%) using the RF classifier. In conclusion, this study showed that both linear and nonlinear HRV analyses could be used to detect and classify physical fatigue in construction workers.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 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 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".