Application of a multilayer perceptron artificial neural network for identification of peach cultivars based on physical characteristics

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 multilayer perceptron (MLP) artificial neural network was applied for identification of the cultivars according to these attributes. The MLP was trained with an input layer including six input nodes, a single hidden layer with six hidden nodes, and an output layer with nine output nodes. A hyperbolic tangent activation function was used in the hidden layer and the cross entropy error was given because the softmax activation function was functional to the output layer. Results showed that the cross entropy error was 0.165. The peach identification process was significantly affected by the following variables in order of contribution (normalized importance): polar diameter (100%), L∗ (89.0), b∗ (88.0%), a∗ (78.5%), firmness (71.3%), and cross diameter (37.5.3%). The MLP was found to be a viable method of peach cultivar identification and classification because few identifying attributes were required and an overall classification accuracy of 100% was achieved in the testing phase. Measurements and quantitative discrimination of peach properties are provided in this research; these data may help enhance the processing efficiency and quality of processed peaches.

Physico-Chemical Properties Prediction of Flame Seedless Grape Berries Using an Artificial Neural Network Model

“…Furthermore, ANN was developed to predict the TSS, titratable acidity, TSS/titratable acidity, anthocyanin, vitamin C, and total carotenoids contents using surface-color CIELab coordinates of L*, hue, and chroma for fresh peach fruit based on inputs of juice volume, single fruit weight, and sphericity percent [ 84 ]. In addition, ANN could be employed as a tool for the identification of peach varieties based on physical characteristics [ 85 ]. Finally, ANN can be utilized as an alternative tool for fruit mass prediction of ber fruits ( Ziziphus mauritiana Lamk) [ 86 ] and peach fruits [ 87 ].…”

The Impact of Road Geometric Formation on Traffic Crash and Its Severity Level

“…The input layer receives the input signal (data) to be processed [35]. It was applied in a multilayer feed-forward network to transmit information [36]. It is used to determine its suitability for traffic accident prediction and to analyze the increasing amounts of traffic accident data and road traffic accident causes using machine learning [37][38][39].…”

Multi-Layer Perceptron-Based Classification with Application to Outlier Detection in Saudi Arabia Stock Returns

“…Many common practices to detect outliers are based on the use of threshold values computed from the available dataset, as in the classical Tukey (1977) method. In contrast to the traditional approach, machine learning and Artificial Neural Network (ANN)-based methods have been successfully applied in time series forecasting and are promising in the field of anomaly detection, refer to Rosenblatt (1958), McClelland et al (1986), Werbos (1989), Zurada (1992), Boughaci et al (2021), Rashedi et al (2021), Al-Saif et al (2021), and Bakhshande et al (2022). They offer several potential advantages with respect to alternative methods such as ARIMA models in that they are robust methods in tasks related to pattern classification and time series forecasting.…”

“…In this paper, we consider the MLP neural network, which is a form of the general Feed-Forward Neural Network (FFNN). For more details, we refer to Al-Saif et al (2021), Saha et al (2021), Agahian and Akan (2022), Bani-Salameh et al (2021), andHounmenou et al (2021).…”