An Automated Mucilage Detection Model Using Deep Convolutional Neural Network: TuncerNeXt
Bibliographic record
Abstract
Convolutional Neural Networks (CNNs) are distinguished for their exceptional performance in image classification.A number of these models have been developed, drawing inspiration from seminal works.This research introduces an innovative CNN model that integrates attention mechanisms specifically tailored for detecting mucilage on the ocean surface.To facilitate this research, a comprehensive dataset was assembled from 15 disparate ports, segmented into three distinct categories: the presence of mucilage, sea surface without waves, and sea waves.The rationale for including the sea wave category is to augment the accuracy of the proposed CNN model by accounting for the morphological similarities between sea waves and mucilage.The developed model, termed TuncerNeXt, comprises four principal components: a stem, TuncerNeXt blocks, downsampling stages, and an output phase.The novelty of TuncerNeXt resides in its fusion of attention mechanisms with residual blocks, taking cues from the structural design of ConvNeXt's principal block.This innovative approach has resulted in TuncerNeXt being a streamlined CNN model, boasting approximately 2.1 million adjustable parameters, rendering it an efficacious approach for image classification endeavors.Upon evaluation with the compiled dataset, TuncerNeXt achieved a validation accuracy of 97.60% and a test accuracy of 98.66%.
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) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".