Comparison of adaptive neuro‐fuzzy inference system and artificial neural networks for estimation of oxidation parameters of sunflower oil added with some natural byproduct extracts

Karaman, Safa; Öztürk, İsmet; Yalçın, Hasan; Kayacıer, Ahmed; Sağdıç, Osman

doi:10.1002/jsfa.4540

Cited by 19 publications

(10 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to results of present study ANFIS is better predict the fatty acid composition of the oils than ANN. These results are in agreement with those reported by previous studies 37, 38.…”

Section: Resultssupporting

confidence: 94%

Prediction of fatty acid composition of vegetable oils based on rheological measurements using nonlinear models

Yalçın

Toker

Öztürk

et al. 2012

Euro J Lipid Sci & Tech

Self Cite

View full text Add to dashboard Cite

The aim of this study was to model the fatty acid composition of vegetable oils by using the adaptive neuro fuzzy inference system (ANFIS) and artificial neural network (ANN) based on rheological measurements. For this aim, seven different refined vegetable oils (hazelnut, soybean, sunflower, olive, canola, corn, and cotton seed) were used. Olive oil had the highest viscosity value of 0.067 Pa s. Principal component analysis (PCA) was performed to determine the correlations among the fatty acids of the oils to reduce parameters which were modeled. PC1 composed of C18:0, C18:1, C18:2, and C20:0 as PC2 composed of C16:0, C18:3, and C22:0. After determination of the fatty acid composition and the rheological properties of the oils, ANN and ANFIS models were established. The inputs were selected as oil type, shear rate and shear stress and the outputs were C16:0 and C18:2. The root mean square error (RMSE), mean absolute error (MAE), and determination coefficient (R 2 ) were used for testing the accuracy of the models. This comparison showed that ANFIS and ANN achieved a satisfactory prediction for fatty acid composition of the vegetable oils studied and ANFIS is better than ANN.Practical applications: Determination of the fatty acid composition of vegetable oils is important for the assessment of the purity of the oils as well as the nutritional quality. The fatty acid composition of the oils affects their rheological characteristics. Rheological measurements are easier than chromatographic analysis. Therefore, we aimed to establish a model for prediction of the fatty acid composition of the oils based on their rheological behaviors.Abbreviations: ANFIS, adaptive neuro-fuzzy inference system; ANN, artificial neural network; MAE, mean absolute error; MF, membership function; PCA, principal component analysis; RMSE, root mean square error Eur.

show abstract

Section: Resultssupporting

confidence: 94%

Prediction of fatty acid composition of vegetable oils based on rheological measurements using nonlinear models

Yalçın

Toker

Öztürk

et al. 2012

Euro J Lipid Sci & Tech

Self Cite

View full text Add to dashboard Cite

show abstract

“…Network parameters include arranged fuzzy membership functions and weight parameters of neural networks to minimize the mean squared error ( MSE ) between the model's output (predicted values) and experimental values and/or to maximize the relationship ( R 2 ) between those two variables through the training phase. Recently, some scientists have attempted to provide various models for the prediction of the qualitative parameters of the extracted oils, for instance researchers compared ANFIS and Artificial Neural Network (ANN) tools in prediction of the stability of sunflower oil enriched by bioactive compounds against deterioration (Karman, Ozturk, Yalcin, Kayacier, & Sagdic, ).…”

Section: Introductionmentioning

confidence: 99%

Application of an adaptive neuro_fuzzy inference system (ANFIS) in the modeling of rapeseeds' oil extraction

Farzaneh

Bakhshabadi

Gharekhani

et al. 2017

J Food Process Engineering

View full text Add to dashboard Cite

In the present study, the temperature and moisture content of the output seeds of the cooking pot were considered as inputs or independent variables and the insoluble fine partial content of the extracted oil, moisture content of the extracted oil and obtained meals, as well as the oil content of the achieved meals and acidity value of the extracted oil were considered as responses and were designed. Three different activation functions, including Gaussian membership and triangular as well as trapezoidal were applied and studied. The trapezoidal function with a 3–3 membership function for the three output variables including insoluble fine partials of oil, oil acidity and moisture content of the meals as well as the triangle membership function with 2–2 and 3–3 functions, respectively, for moisture content of the extracted oil and the oil content of the obtained meals were evaluated and detected as optimized models in the current study. The above mentioned models demonstrated higher correlation coefficients (R2) between the experimental and predicted values and the lowest root mean squared errors, confirming the adaptability of the applied models in the present study. Practical applications Today, because of the high demand for crops for extensive application in the human diet, increases in the efficiency of the processing are attracting much more attention. In this regard, discovering and detection of the optimized conditions for processing with the minimum wastes looks very important and economic. Therefore, the uses of predictive methods in different food processes have been considered appropriate tools for improving of the efficiency of the processes as well as the enhancement of the quality of the produced products. In this respect, the ANFIS design as a novel predictive analytic tool, along with Response Surface Methodology (RSM) and Artificial Neural Network (ANN), are applied extensively. Thus regarding the above mentioned content, ANFIS design was applied to predict and optimize some of the selected physico‐chemical properties of the extracted oil through the extraction process. Therefore prediction of the optimized conditions of oil extraction could improve the quality of the extracted oil and performance of the extraction process with the minimum wastes during short and logical extraction time.

show abstract

“…The results showed that oxidation parameters could be successfully predicted using the ANFIS model. Karaman et al also compared the ANFIS and ANN for estimation of oxidation parameters of sunflower oil added with apple pomace, orange peel and potato peel as natural byproduct research. The results indicated that the ANFIS model with a high coefficient of determination ( R 2 = 0.999) had better performance compared to ANN ( R 2 = 0.89).…”

Section: Introductionmentioning

confidence: 99%

Prediction of oxidation parameters of purified Kilka fish oil including gallic acid and methyl gallate by adaptive neuro‐fuzzy inference system (ANFIS) and artificial neural network

2016

View full text Add to dashboard Cite

show abstract

Comparison of adaptive neuro‐fuzzy inference system and artificial neural networks for estimation of oxidation parameters of sunflower oil added with some natural byproduct extracts

Cited by 19 publications

References 41 publications

Prediction of fatty acid composition of vegetable oils based on rheological measurements using nonlinear models

Prediction of fatty acid composition of vegetable oils based on rheological measurements using nonlinear models

Application of an adaptive neuro_fuzzy inference system (ANFIS) in the modeling of rapeseeds' oil extraction

Prediction of oxidation parameters of purified Kilka fish oil including gallic acid and methyl gallate by adaptive neuro‐fuzzy inference system (ANFIS) and artificial neural network

Contact Info

Product

Resources

About