Mohsen Azadbakht - Department of Bio-System Mechanical Engineering, Gorgan University of Agricultural Sciences and Natural Resources, Gorgan, Iran
mohammad Vahedi Torshizi - Department of Mechanics, Faculty of Emam Ali, Kordkuy Branch, Technical and Vocational University (TVU), Golestan, Iran
Mohammad Javad Mahmoodi - Department of Mechanics, Faculty of Emam Ali, Kordkuy Branch, Technical and Vocational University (TVU), Golestan, Iran
Ahmad Abbaszadeh-Mayvan - Department of Bio-System Mechanical Engineering, Gorgan University of Agricultural Sciences and Natural Resources, Gorgan, Iran

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 (۳۰۰, ۳۵۰ and ۴۰۰ g) and different storage periods (۵, ۱۰ and ۱۵ 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 ۵ and ۱۰ 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 R۲ for dynamic loading in a network with ۵ neurons in the hidden layer and a sigmoid activation function were obtained for total phenol content (R۲ = ۰.۹۸۰), antioxidant (R۲ = ۰.۹۸۳) and Vitamin C (R۲ = ۰.۹۳۰). 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.

Activation function, Antioxidant, Neurons, phenol, storage