Research on real-time monitoring and response method of AI emergency safety scenarios in energy industry based on machine vision
Bibliographic record
Abstract
The study applies machine vision technology to the production and operation process of energy enterprises, and constructs a fire detection model based on improved YOLOv4 from the real-time monitoring of fire emergency safety scenarios.Based on the original YOLOv4 algorithm, the model lightens the feature extraction and feature fusion networks, and introduces CA attention mechanism in the bottom layer of the feature extraction network to improve the accuracy of target detection.An intelligent fire alarm system is built on this basis as a response method for emergency security scenarios.Comparison with the basic YOLOv4 algorithm reveals that the improved YOLOv4 algorithm reduces the parameter amount by 45.97%, improves the FPS by 27.75, and improves the mAP value by 14.10%, which achieves a better detection accuracy on the basis of greatly reducing the amount of computation and parameter count, and also achieves a better Loss value and mAP in the comparison with other detection methods.Intelligent Fire Alarm The system integrates intelligent detection, intelligent alarm, intelligent alarm receiving and intelligent alarm dispatching, and can complete the fire alarm process within 6s.In summary, it shows that the method proposed in this paper can be used in real-time monitoring of emergency security scenarios and can provide timely warning at the early stage of security hazards.
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 | 0.001 |
| 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 | 0.002 |
| Open science | 0.001 | 0.001 |
| 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".