Advanced Chain Regression and Deep Learning Models for Fish By‐Product Drying Optimization: An Intelligent Conveyor System for Sustainable Waste Valorization
Bibliographic record
Abstract
ABSTRACT The rapid increase in global fish waste, estimated at two‐thirds of total catch, presents critical environmental and economic challenges. This study introduces an innovative approach combining a heat conveyor dryer with advanced machine learning techniques for optimizing fish by‐product processing. The experimental design evaluated three critical parameters: drying temperatures (60°C, 70°C, and 80°C), air conveying speeds (1, 1.5, and 2 m/s), and product layer thicknesses (5, 7, and 9 mm). The optimal configuration achieved a 150‐min drying time at 80°C, 2 m/s air velocity, and 5 mm thickness, reducing processing time by 70% compared to conventional methods. Deep Neural Networks with 12 layers demonstrated superior prediction accuracy (R 2 = 0.979) for moisture content, while chain regression models using XGBoost achieved 97.8% accuracy in moisture ratio prediction. The dried products retained high nutritional value with 45.08% protein and 15.1% fat content, comparable to fresh samples. Compared to the best mathematical model (Page), the optimal machine learning model (deep neural network 12) provided more accurate and robust predictions of drying behavior across all tested conditions. This integrated approach offers a sustainable solution for fish waste valorization, potentially reducing processing energy consumption by 35% while maintaining product quality. The developed models enable real‐time process optimization, contributing to both economic efficiency and environmental conservation in fisheries waste management.
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 | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".