Advanced Chain Regression and Deep Learning Models for Fish By-Product Drying Optimization: An Intelligent Conveyor System for Sustainable Waste Valorization

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 (R² = 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.