Modeling of Calcium Ascorbate Effect on Button Mushroom Characteristics During Postharvest Using Genetic Algorithm-artificial Neural Network

Modeling of calcium ascorbate effects on characteristics of button mushroom was investigated by Genetic Algorithm–Artificial Neural Network (GA-ANN). Calcium ascorbate is effective in maintaining the quality and reducing the waste of agricultural products after harvest.  In this study button mushrooms were treated by calcium ascorbate solutions in 45°C temperature at three levels of 0, 0.4 and 0.8 %, and after drying at room temperature, kept at 1°C and 90% relative humidity. Qualitative characteristics of button mushroom during postharvest period were evaluated after 0, 10, 15, 20 and 25 days. Modeling of calcium ascorbate effects on button mushroom characteristics were undertaken by GA-ANN method with 2 inputs (calcium ascorbate concentration and shelf life) and 9 output (weight loss, firmness, TDS, pH, chroma, hue angle, ΔE, browning index and total phenol) using multi-layer perceptron. The results showed that networks with 12 neurons in a hidden layer using tangent activation function could predict effect of calcium ascorbate on button mushroom characteristics with correlation coefficient equal to 0.95. Results of sensitivity analysis by optimum neural network (2-12-9), was defined shelf life as the most effective factor in predicting button mushroom attributes during postharvest period.