Automated Detection of Waterborne Pathogens in Aquaculture Using an Enhanced Swin-Transformer Model
Bibliographic record
Abstract
Waterborne pathogens in aquaculture systems pose significant threats to fish health and production, as well as potential risks to human health.To address the critical need for early and precise pathogen detection, this study introduces an enhanced Swin-Transformer model tailored for automated pathogen identification in aquaculture environments.The Swin-Transformer, a modern deep-learning architecture, excels in image recognition tasks.The proposed model integrates convolutional neural networks (CNNs) for feature extraction and Swin-Transformers for classification.CNN layers process the input images, extracting key features, which are subsequently refined by the Swin-Transformer's self-attention and feedforward network mechanisms.This dual approach captures both localized details and longrange dependencies, enhancing classification accuracy.To train the model, a dataset of water sample images representing various waterborne diseases was utilized, along with data augmentation techniques to boost generalization.The model demonstrated superior performance, achieving an F-measure (Fowlkes-Mallow's index) of 88.26%, a Critical Success Index of 84.39%, recall of 94.75%, accuracy of 94.44%, and Matthew's correlation coefficient of 0.87.Comparative analyses indicate that the proposed model surpasses existing methods, making it a robust solution for disease prevention and management in aquaculture systems.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| 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".