Image Recognition of Coal and Coal Gangue Using a Convolutional Neural Network and Transfer Learning
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Recognizing and distinguishing coal and gangue are essential in engineering, such as in coal-fired power plants. This paper employed a convolutional neural network (CNN) to recognize coal and gangue images and help segregate coal and gangue. A typical workflow for CNN image recognition is presented as well as a strategy for updating the model parameters. Based on a powerful trained image recognition model, VGG16, the idea of transfer learning was introduced to build a custom CNN model to solve the problems of massive trainable parameters and limited computing power linked to the building of a brand-new model from scratch. Two hundred and forty coal and gangue images were collected in a database, including 100 training images and 20 validation images for each material. A recognition accuracy of 82.5% was obtained for the validation images, which demonstrated a decent performance of our model. According to the analysis of parameter updating in the training process, a principal constraint for obtaining a higher recognition accuracy mainly resided in a shortage of training samples. This model was also used to identify photos from a washing plant stockpiles, which verified its capability of dealing with field pictures. CNN combined with the transfer learning method we used can provide fast and robust coal/gangue distinction that does not require harsh data support and equipment support. This method will exhibit brighter prospects in engineering if the target image database (as with the coal and gangue images in this study) can be further enlarged.
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.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 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 | 0.000 |
| 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 it