Using adaptive neuro‐fuzzy inference system and multiple linear regression to estimate orange taste

Abstract

In this research, some characteristic qualities of orange fruits such as vitamin C and acid content; weight; fruit and skin diameter; and red (R), green (G), and blue (B) values of the RGB color model for 70 samples were used to predict the taste of orange grown in Darab, southeast of Fars Province, Iran, by multiple linear regression (MLR) and adaptive neuro‐fuzzy inference system (ANFIS). To use MLR, firstly the most important input data were selected, and then, the best model to predict the taste of orange was applied. In this research, methodology of ANFIS consisted of selection of dependent orange taste, fuzzification, fuzzy inference rule, membership function, and defuzzification process. The predictive capability of these models was evaluated by various descriptive statistical indicators such as mean square error (MSE) and determination coefficient (R 2). The results showed that the prediction performance of the MLR model has a strong significant relationship between orange taste and vitamin C (0.897**), red color (0.901**), and blue color (0.713*). Also, the results of ANFIS model showed that with low error for train and check data increased the most accuracy for prediction of orange taste. Moreover, the results indicated that the success rate of taste determination for orange is higher by using ANFIS compared to the MLR. This research was to provide valuable information for orange taste.

Quality Attributes Prediction of Flame Seedless Grape Clusters Based on Nutritional Status Employing Multiple Linear Regression Technique

“…Despite being viewed as ineffectual, MLR models are frequently employed in the modelling process and successfully validated. A study employing the MLR model to predict the flavor of orange using 70 samples is an example of this, and the results revealed that the prediction performance of the MLR model had a strong significant relationship between orange taste and vitamin C, red color, and blue color as reported by Mokarram et al [87]. Furthermore, eight aroma properties of Dianhong tea were predicted using MLR produced R 2 > 0.95 [46].…”

The Application of Artificial Intelligence and Big Data in the Food Industry

“…In addition, Abbaspour-Gilandeh et al [113] designed a system combining artificial neural networks and ANFIS for predicting the kinetic energy and energy of quince under a hot air dryer, Kaveh [114] designed an ANFIS model for predicting the moisture diffusivity and specific energy consumption of drying potatoes, garlic, and melons under convection hot air dryers, Arabameri et al [112] utilized an adaptive neuro-fuzzy inference system (ANFIS) to assess and forecast the oxidative stability of virgin olive oil. Mokarram et al [115] employed an adaptive neuro-fuzzy inference system and multivariate linear regression to estimate the flavor of oranges. Table 2 lists the published ANFIS technology applications in the food industry.…”

Comparative Studies of RSM, RSM–GA and ANFILS for Modeling and Optimization of Naphthalene Adsorption on Chitosan–CTAB–Sodium Bentonite Clay Matrix

“…Tanhaei et al [18] described ANFILS as the model best in data prediction with very low error value. It is commonly used in production and other segment of industries [58][59][60][61][62]; agricultural processes [63] and separation processes for water treatment and purification [18,19,[64][65][66][67]. The dearth of insightful information on the response surface methodology (RSM), RSM-genetic algorithm (GA) and adaptive neuro-fuzzy inference logic system (ANFILS) modeling and optimization of the process variables involved in the adsorption of naphthalene adsorption on chitosan-CTAB-bentonite matrix necessitated this study, which, to the best of our knowledge, has not been reported in the literature.…”