Work

Development of freshness monitoring models for grass carp cutting products at multiple storage temperatures and construction of a real-time prediction platform

Year: 2025

Type: article

Abstract: Spoilage of aquatic products can cause economic losses and health risks, highlighting the need for real-time freshness monitoring technologies. In this study, four value-added grass carp cuts (dorsal, abdomen, belly, and tail) were stored at five temperatures (0, 3, 6, 9, and 12 °C) for 0-10 days. Five freshness indicators were accessed and six machine learning models were used to predict these five freshness indicators. The best-performing model for each indicator was ensembled into a real-time prediction platform. Results showed that the optimal models for predicting TVC, TVB-N, K value, overall sensory acceptability, and sensory evaluation score were radial basis function neural network (RBFNN), backpropagation neural network, gradient boosting machine, RBFNN, and support vector regression, achieving R² values of 0.9552, 0.9673, 0.9581, 0.9734, and 0.9659, respectively. TVC modeled by RBFNN yielded the best validation performance with relative errors ranging from 0.00 to 0.21. The real-time platform completed freshness prediction within 0.10 s and classified samples into "Fresh", "Less Fresh" or "Spoiled" levels. Thus, the proposed platform offers a robust and scalable approach for non-destructive evaluation of freshness and shelf life in grass carp cuts under cold storage, facilitating data-driven quality control throughout the aquatic supply chain.

Source: LWT

DOI: 10.1016/j.lwt.2025.118620