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.

BACKGROUND Apple pomace, orange peel and potato peel, which have important antioxidative compounds in their structures, are byproducts obtained from fruit or vegetable processing. Use of vegetable extracts is popular and a common technique in the preservation of vegetable oils. Utilization of apple pomace, orange peel and potato peel extracts as natural antioxidant agents in refined sunflower oil during storage in order to reduce or retard oxidation was investigated. All byproduct extracts were added at 3000 ppm to sunflower oil and different nonlinear models were constructed for the estimation of oxidation parameters. RESULTS Peroxide values of sunflower oil samples containing different natural extracts were found to be lower compared to control sample. Adaptive neuro-fuzzy inference system (ANFIS) and artificial neural networks (ANN) were used for the construction of models that could predict the oxidation parameters and were compared to multiple linear regression (MLR) for the determination of the best model with high accuracy. It was shown that the ANFIS model with high coefficient of determination (R(2) = 0.999) performed better compared to ANN (R(2) = 0.899) and MLR (R(2) = 0.636) for the prediction of oxidation parameters CONCLUSION Incorporation of different natural byproduct extracts into sunflower oil provided an important retardation in oxidation during storage. Effective predictive models were constructed for the estimation of oxidation parameters using ANFIS and ANN modeling techniques. These models can be used to predict oxidative parameter values.

[1]  ZIA-UR-REHMAN,et al.  Antioxidant activity of ginger extract in sunflower oil , 2003 .

[2]  Prediction of effect of natural antioxidant compounds on hazelnut oil oxidation by adaptive neuro-fuzzy inference system and artificial neural network. , 2011, Journal of food science.

[3]  Yingming Pan,et al.  Antioxidant activity of ethanolic extract of Cortex fraxini and use in peanut oil , 2007 .

[4]  George Boskou,et al.  Polyphenolic content and in vitro antioxidant characteristics of wine industry and other agri-food solid waste extracts , 2007 .

[5]  Ozgur Kisi,et al.  Streamflow Forecasting Using Different Artificial Neural Network Algorithms , 2007 .

[6]  S. Karaman,et al.  Effect of temperature on rheological characteristics of molasses: Modeling of apparent viscosity using Adaptive Neuro – Fuzzy Inference System (ANFIS) , 2011 .

[7]  J. Manthey.  Fractionation of orange peel phenols in ultrafiltered molasses and mass balance studies of their antioxidant levels. , 2004, Journal of agricultural and food chemistry.

[8]  Yongguang Yin,et al.  A close to real-time prediction method of total coliform bacteria in foods based on image identification technology and artificial neural network. , 2009 .

[9]  Murad Samhouri,et al.  Formulation and fuzzy modeling of emulsion stability and viscosity of a gum–protein emulsifier in a model mayonnaise system , 2008 .

[10]  Arun Sharma,et al.  Potato peel extract-a natural antioxidant for retarding lipid peroxidation in radiation processed lamb meat. , 2005, Journal of agricultural and food chemistry.

[11]  L. Foo,et al.  Antioxidant and radical scavenging activities of polyphenols from apple pomace. , 2000 .

[12]  Awad Mahmoud,et al.  Antioxidant properties of various solvent extracts of potato peel, sugar beet pulp and sesame cake. , 2010, Journal of the science of food and agriculture.

[13]  K. Benmahammed,et al.  Application of Artificial Neuro-Fuzzy Logic Inference System for Predicting the Microbiological Pollution in Fresh Water , 2008 .

[14]  Mesure de l'activité antiradicalaire du jus et des peaux d'oranges tunisiennes par le radical DPPH , 2006 .

[15]  Seung-Cheol Lee,et al.  Effect of heat treatment on the antioxidant activity of extracts from citrus peels. , 2004, Journal of agricultural and food chemistry.

[16]  V. R. Lima,et al.  Clean recovery of antioxidant flavonoids from citrus peel: Optimizing an aqueous ultrasound-assisted extraction method , 2010 .

[17]  Nandita Singh,et al.  Free radical scavenging activity of an aqueous extract of potato peel , 2004 .

[18]  Daniel E. Guyer,et al.  Apple Grading Using Fuzzy Logic , 2003 .

[19]  Hongfei Lu,et al.  An adaptive neural-fuzzy inference system (ANFIS) for detection of bruises on Chinese bayberry (Myrica rubra) based on fractal dimension and RGB intensity color , 2011 .

[20]  L. Medina-Juárez,et al.  ANTIOXIDANT ACTIVITY COMPARISON OF THOMPSON GRAPE POMACE EXTRACT, ROSEMARY AND TOCOPHEROLS IN SOYBEAN OIL , 2009 .

[21]  Álvaro Cortés Cabrera,et al.  Application of artificial neural networks to the prediction of the antioxidant activity of essential oils in two experimental in vitro models , 2010 .

[22]  C. Berset,et al.  Antioxidant activity and phenolic composition of citrus peel and seed extracts , 1998 .

[23]  Zia-ur-Rehman,et al.  Citrus peel extract – A natural source of antioxidant , 2006 .

[24]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[25]  Vesna Tumbas,et al.  Assessment of polyphenolic content and in vitro antiradical characteristics of apple pomace. , 2008, Food chemistry.

[26]  R. Liu,et al.  Nutrition: Antioxidant activity of fresh apples , 2000, Nature.

[27]  A. Al-Khalifa,et al.  EFFECT OF MICROWAVE OVEN HEATING ON STABILITY OF SOME OILS AND FATS , 1998 .

[28]  Z. Rehman,et al.  Utilization of potato peels extract as a natural antioxidant in soy bean oil , 2004 .

[29]  P. Kefalas,et al.  Radical scavenging activity of various extracts and fractions of sweet orange peel (Citrus sinensis) , 2006 .

[30]  Sakir Tasdemir,et al.  Fuzzy Expert System Approach for Determination of α-Linolenic Acid Content of Eggs Obtained from Hens by Dietary Flaxseed , 2007 .

[31]  A Escarpa,et al.  High-performance liquid chromatography with diode-array detection for the determination of phenolic compounds in peel and pulp from different apple varieties. , 1998, Journal of chromatography. A.

[32]  M. Hanna,et al.  An Adaptive Neuro‐Fuzzy Inference System for Modeling Mechanical Properties of Tapioca Starch‐Poly(Lactic Acid) Nanocomposite Foams , 2008 .

[33]  Francisco Parra,et al.  Phenolic profiles, antioxidant activity and in vitro antiviral properties of apple pomace , 2010 .

[34]  Yong-Seo Park,et al.  Comparison of some biochemical characteristics of different citrus fruits , 2001 .

[35]  B. Halliwell,et al.  Free radicals and antioxidants in food and in vivo: what they do and how they work. , 1995, Critical reviews in food science and nutrition.

[36]  I. Lambropoulos,et al.  Antioxidant activity of red wine phenolic extracts towards oxidation of corn oil , 2007 .

[37]  Jing-yu Wei,et al.  Evaluation of antioxidant properties of pomegranate peel extract in comparison with pomegranate pulp extract , 2006 .

[38]  F. Anwar,et al.  Antioxidant potential of corncob extracts for stabilization of corn oil subjected to microwave heating , 2007 .

[39]  Digvir S. Jayas,et al.  Microbial growth modelling with artificial neural networks. , 2001 .

[40]  S. Fukushima,et al.  Carcinogenicity and modification of the carcinogenic response by BHA, BHT, and other antioxidants. , 1985, Critical reviews in toxicology.