AI-Driven Automated Helmet Detection in Underground Coal Mines using Attention-Enhanced Vision Transformer
Bibliographic record
Abstract
Ensuring safety compliance in underground coal mines is essential for preventing accidents and safeguarding miners. Traditional methods for monitoring helmet usage are often ineffective due to poor visibility, dust, and equipment occlusion. This study proposes an attention-enhanced Vision Transformer (ViT) model, specifically adapted for helmet detection in challenging underground environments. The model processes images as sequences of patches, leveraging multi-head self-attention mechanisms to capture global dependencies and improve feature extraction. A custom dataset was developed from underground coal mine footage, and the model was trained using supervised learning with a cross-entropy loss function. The customized ViT achieved an accuracy of 98%, outperforming other State-Of-The-Art (SOTA) models, such as YOLOv8 with attention mechanisms, Mask R-CNN, and Detectron2. The results demonstrate the effectiveness of the attention-enhanced ViT in accurately detecting helmets, even in low-light and cluttered environments. This research contributes to developing real-time, automated safety monitoring systems, which reduce human error and enhance worker safety in hazardous mining operations.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".