ARCHIVES

Shrimp is a popular seafood product, but it spoils quickly even when stored at low temperatures. This is mainly because of microbial growth, enzyme activity, and chemical changes that reduce its freshness and quality over time. Therefore, predicting the shelf life of shrimp is important for maintaining food quality, ensuring consumer safety, reducing food waste, and improving storage management. Traditional methods for checking shrimp quality usually involve laboratory tests, which require time, skilled personnel, and specialized equipment. In this study, an Artificial Neural Network (ANN) model is developed to predict the shelf life of shrimp during cold storage. The model uses important quality factors such as storage temperature, storage duration, pH, Total Viable Count (TVC), Total Volatile Basic Nitrogen (TVB-N), Thiobarbituric Acid Reactive Substances (TBARS), moisture content, water activity, and sensory evaluation scores. These data are used to train and test the ANN model so that it can learn the relationship between quality changes and shelf life. The performance of the model is evaluated using statistical measures, including Mean Squared Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and the coefficient of determination (R²). The developed model provides an easy and reliable way to estimate the remaining shelf life of shrimp. It can support quality control, improve cold storage management, reduce product losses, and help the seafood industry deliver safer and better-quality products to consumers.