AI-Driven Physical Fatigue Classification in a Pharmaceutical Case Study Using Wearable Biometric Data
Bibliographic record
Abstract
Physical fatigue is a significant concern in repetitive production line operations, often contributing to musculoskeletal disorders (MSDs) and high absenteeism rates. This study focuses on a pharmaceutical packaging line where workers frequently develop MSDs due to the repetitive nature of their tasks. To address this issue, biometric data from smartwatches, including pulse rate, internal temperature, electrodermal activity, and movement patterns, were collected alongside demographic factors such as age and experience and occupational factors related to task demands, including physical load, and operational conditions such as production line location, day of the week, work shift, and timing within the shift. Principal Component Analysis was first applied to reduce the dataset's dimensionality, extracting the most relevant features. Subsequently, fuzzy logic was employed to label the data into two and four levels of fatigue based on prior research. The resulting features and labels were then used as inputs for machine learning classification models to predict fatigue states. Our findings demonstrate that integrating wearable sensor data significantly enhances classification performance. In binary classification, the Random Forest model achieved an F1 score of 0.935 with biometric data and 0.681 without it. For the four-level classification, incorporating biometric data improved the F1 score from 0.573 to 0.903, highlighting its importance in fatigue prediction. This study contributes by developing a generalized predictive fatigue model and establishing a foundation for a real-time fatigue alert system to enhance worker safety and productivity.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 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 | 0.001 |
| 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".