Application of artificial neural network and support vector regression in predicting mass of ber fruits (Ziziphus mauritiana Lamk.) based on fruit axial dimensions.

Mahmoud Abdel-Sattar,Bandar M Alnahdi,Abdulwahed M Aboukarima,Le Hoang Son

doi:10.1371/journal.pone.0245228

Mahmoud Abdel-Sattar, Bandar M Alnahdi + Show 2 more

Open Access

https://doi.org/10.1371/journal.pone.0245228

Copy DOI

Abstract

Fruit quality attributes are important factors for designing a market for agricultural goods and commodities. Support vector regression (SVR), MLR, and ANN models were established to predict the mass of ber fruits (Ziziphus mauritiana Lamk.) based on the axial dimensions of the fruit from manual measurements of fruit length, minor fruit diameter, and maximum fruit diameter of four ber cultivars. The precision and accuracy of the established models were assessed given their predicted values. The results revealed that using the validation dataset, the developed ANN (R2 = 0.9771; root mean square error [RMSE] = 1.8479 g) and SVR (R2 = 0.9947; RMSE = 1.8814 g) models produced better results when predicting ber fruit mass than those obtained by the MLR model (R2 = 0.4614; RMSE = 11.3742 g). In estimating ber fruit mass, the established SVR and ANN models produced more precise prediction values than those produced by the MLR model; however, the performance differences between the SVR and ANN models were not clear.

Highlights

Ziziphus mauritiana Lamk. originates from the Rhamnaceae family and is known as Indian jujube
The objectives of the present study are to build multiple linear regression (MLR), artificial neural network (ANN), and support vector regression (SVR) models to predict ber fruit mass based on axial dimensions, to compare the performance of the established models in term of precision and accuracy given their obtained prediction values
The statistical criteria values in modeling ber fruit mass based on the ber cultivar type and three axial dimensions were represented by R2, mean absolute error (MAE), and root mean squared error (RMSE) corresponding to the Support vector regression (SVR), MLR, and ANN models

Summary

Introduction

Ziziphus mauritiana Lamk. originates from the Rhamnaceae family and is known as Indian jujube. Ber requires minimum agricultural inputs to grow [4]. This fruit has variable sizes and shapes depending on the cultivars. Ber fruits are a popular fruit in some parts of Saudi Arabia, and are appreciated by consumers due to their quality. They are rich in a variety of vitamins and minerals [5, 6], and their nutritional value is high. Their prices are higher than those of other fruits

Objectives

Methods

Results

Discussion

Conclusion