Mohsen Azadbakht; Mohammad Vahedi Torshizi; Mohammad Javad Mahmoodi; Ahmad Abbaszadeh-Mayvan
Abstract
The current study was aimed to evaluate the physiological properties of pear influenced by two dynamics of loading force and the storage time. In this experiment, the pears were subjected to dynamic loading (300, 350 and 400 g) and different storage periods (5, 10 and 15 d). The amounts of fruit total ...
Read More
The current study was aimed to evaluate the physiological properties of pear influenced by two dynamics of loading force and the storage time. In this experiment, the pears were subjected to dynamic loading (300, 350 and 400 g) and different storage periods (5, 10 and 15 d). The amounts of fruit total phenol, antioxidant and Vitamin C contents were evaluated after each storage period. In the present study, multilayer perceptron (MLP) artificial neural network featuring a hidden layer and two activating functions (hyperbolic tangent-sigmoid) and a total number of 5 and 10 neurons in each layer were selected for the loading force and storage period so that the amounts of the total phenol, antioxidants and Vitamin C contents of the fruits could be forecasted. According to the obtained results, the highest R2 for dynamic loading in a network with 5 neurons in the hidden layer and a sigmoid activation function were obtained for total phenol content (R2 = 0.980), antioxidant (R2 = 0.983) and Vitamin C (R2 = 0.930). Additionally, considering the value of Epoch and Run for the network, the ability of the neural network to predict total phenol, antioxidant and Vitamin C contents can be used. According to the obtained results, the neural network with these two activation functions possesses an appropriate ability in overlapping and predicting the simulated data based on real data.
Mohsen Azadbakht; Mohammad Javad Mahmoodi; Mohammad Vahedi Torshizi
Abstract
Nowadays, due to the necessity of increasing quality awareness in the food sector and its health, the non-destructive computed tomography (CT) method, which is one of the most widely used methods because of the ability to detect internal bruise in a non-destructive way, attracted so much attention. By ...
Read More
Nowadays, due to the necessity of increasing quality awareness in the food sector and its health, the non-destructive computed tomography (CT) method, which is one of the most widely used methods because of the ability to detect internal bruise in a non-destructive way, attracted so much attention. By using the non-destructive CT method a total of 81 healthy pears was selected and then subjected to quasi-static and dynamical loading. The experiment was performed on wide edge quasi-static pressure of 70, 100, 130 N and thin edge of 15, 20, 25 N and dynamic load of 300, 350, 400 g and storage period for 5, 10 and 15 days, to investigate the different effects of loading forces and storage periods on the percentage of the bruise and its relation with the qualitative properties such as phenol, antioxidant and vitamin C contents and firmness. The results of the experiments showed that the highest and lowest percentages of the bruise were related to a load of 400 N of 15 days and a 15 N 5-day thin line with values of 47.36 and 0.007, respectively. The highest and lowest physiological values were 15 N load of the 5-day thin edge and the 400 N of 15-day impact. Finally, the highest antioxidant content was 51.5% for 300 g dynamic loading force and 5- day storage, 28.86 mg/100g phenol for loading force of 70 N wide edge and 5 day storage and 7.4 mg/100ml vitamin C for loading force of 70 N wide edge and 5 day storage. Finally, according to the obtained results, there was an inverse relationship between the amount of bruising and chemical properties of pear.