Practical Approach on Using of Artificial Neural Network for Posture Prediction and Computation of Spinal Loads across Biomechanical Models
Bibliographic record
Abstract
Background: Workers usually perform lifting and reaching tasks as part of their daily job. Having proper posture plays a key role for reducing the loads implemented to spine during lifting and prevention of further injuries. We aimed to extend a previously published work on spinal load estimation that used different biomechanical tools, by using artificial neural network (ANN) for posture prediction instead of camera-marker during lifting and reaching. Method: In this study, to underline the efficacy of biomechanical models, we examined and compared the results of multiple mathematical tools (loads at L4/L5 and L5/S1 levels) for reach-and-lift in the sagittal plane (i.e., symmetric tasks) and for lifting tasks with and of back rotation (i.e., asymmetric tasks). In this regard, we employed AnyBody, OpenSim, and 3DSSPP (which are modeling software), a regression equation called Arjmand equation, and finally, McGill, Potvin, and Merryweather that are estimators. Inputs to these models are provided using an artificial neural network (ANN), a posture prediction model introduced by literature for predicting the three-dimensional posture of the spine in various activities, which is trained and tested by experimental data. Results: Results showed that while Anybody has the most accurate approximations, Arjmand equation also offers a quite realistic output that is, considering its simplicity, compatible with the biomechanical nature of the problem. Using ANN posture prediction, the results (for 4 symmetric taks) show less than 15% error from a marker-based study in the literature which was considered as a accurate model. Conclusion: Arjmand regression along with using ANN for posture prediction may lead to a reliable solution for spinal loads estimation during lifting and reaching, especially when an equipped laboroatory or/and expensive software licenses are not available.
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 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 | 0.006 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 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 | 0.001 |
| 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 teacher head, 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".