Application of a multilayer perceptronartificial neural network for identificationof peach cultivars based on physicalcharacteristics
Abstract: In the fresh fruit industry, identification of fruit cultivars and fruit quality is of
vital importance. In the current study, nine peach cultivars (Dixon, Early Grande,Flordaprince, Flordastar, Flordaglo, Florda 834, TropicSnow, Desertred, and Swelling)were evaluated for differences in skin color, firmness, and size. Additionally, a multilayerperceptron (MLP) artificial neural network was applied for identification of the cultivarsaccording to these attributes. The MLP was trained with an input layer including sixinput nodes, a single hidden layer with six hidden nodes, and an output layer with nineoutput nodes. A hyperbolic tangent activation function was used in the hidden layer andthe cross entropy error was given because the softmax activation function was functionalto the output layer. Results showed that the cross entropy error was 0.165. The peachidentification process was significantly affected by the following variables in order ofcontribution (normalized importance): polar diameter (100%), L* (89.0), b* (88.0%),a* (78.5%), firmness (71.3%), and cross diameter (37.5.3%). TheMLPwas found to be aviable method of peach cultivar identification and classification because few identifyingattributes were required and an overall classification accuracy of 100% was achieved inthe testing phase. Measurements and quantitative discrimination of peach propertiesare provided in this research; these data may help enhance the processing efficiency andquality of processed peaches.
Publication year 2021
Organization Name
serial title PeerJ, DOI
Author(s) from ARC
External authors (outside ARC)
    عادل السيف
    محمود عبدالستار
    داليا ايشرا
Publication Type Journal
↑