Application of Artificial Neural Network in the Baking Process of Salmon

The global production of farmed Atlantic salmon amounts to over 2 million tons per year. Consumed all the world, is not only delicious but also nutritious. This paper deals with relationship between moisture content, low-field nuclear magnetic resonance (LF-NMR), scanning electron microscope (SEM), and sensory evaluation in baking process salmon. An artificial neural network (ANN) model has been established simulate change content energy consumed process. Through study LF-NMR, SEM, evaluation, it was found that indexes consistent results observed by LF-NMR SEM. With increase temperature, muscle fibers contracted, interstices increased, rate water loss score decreased. Initial time, humidity, air velocity were employed as control parameters for ANN. ANN can be used determine best topology occurred 5 input layer neurons, 17 hidden output MSE 0.00153, Rall 0.99661. According experiment, demonstrated a reliable software-based method.