Performance of artificial neural networks and discriminant analysis in predicting fishing tactics from multispecific fisheries
Bibliographic record
Abstract
In the Mediterranean, bottom trawlers are multispecific and frequently apply different fishing tactics (FTs) even during the same fishing trip. Up to four individual FTs were distinguished in the study area where fishermen usually use mixtures of different FTs in daily fishing trips. Identifying the FTs actually performed is a key issue in traditional stock assessment methods. In this paper, we compare the performance of discriminant analysis and artificial neural networks for predicting FTs from the species composition of daily sale bills. We used data on the landings of each vessel from daily sale bills along with information on the FT actually performed, which was obtained by onboard observers who interviewed skippers about the FTs that they planned to employ. Discriminant analysis and artificial neural networks achieved comparable overall results and the success of predictions depended on both the sample size of the different data subsets (balancing) and the similarity between the species composition of different FTs (overlapping). Although the percentage of correct predictions was high for FTs with more than 25 cases, success decreased when the sample sizes were small. In addition, success in predicting mixtures of two different FTs increased with increasing dissimilarity between their corresponding species compositions.
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 | 0.010 | 0.016 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 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".