Metal Solid Waste Recycling and Detection Method Based on Convolutional Attention and SCN
Bibliographic record
Abstract
A metal solid waste recycling and detection method based on convolutional attention and random configuration network is proposed to address the problem of insufficient detection accuracy caused by the diverse shapes, sizes, colors, and surface textures of metal solid waste. This method is based on You Only Look Once version 5 small, and introduces convolutional attention mechanism in its Head section to optimize feature extraction performance through feature recalibration of channels and spatial dimensions; Simultaneously building a classification model that integrates Softmax, random vector function linking, and deep random configuration network to improve the detection and classification accuracy of metal solid waste. The experimental findings denote that the proposed method has the lowest classification accuracy of 98.2%, an average accuracy of 98.7%, the highest false alarm rate of 8.8%, an average false alarm rate of 8.4%, and the lowest average accuracy of 96.3%, all of which are superior to the comparative methods. Meanwhile, the detection speed of this method is the slowest at 29.8 FPS, with an average detection speed of 30.7 FPS, which is faster than other methods. The above findings demonstrate that the proposed method has good effectiveness and superiority in the detection and classification of metal solid waste, which can effectively improve the efficiency of metal solid waste recycling management, optimize resource utilization, reduce industrial manufacturing costs, reduce environmental pollution, and promote sustainable development.
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 | 0.001 |
| 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".