Applying Adaptive Neuro-Fuzzy Inference System and Artificial Neural Network to the Prediction of Quality changes of Hawthorn Fruit (Crataegus pinnatifida) during Various Storage Conditions

ماشین های کشاورزی

Article 16, Volume 11, Issue 2 - Serial Number 22, 2021, Pages 343-357   

Document Type: Research Article

DOI: 10.22067/jam.v11i2.86654

Authors

M. Zandi^* ; A. Ganjloo; M. Bimakr

Department of Food Science and Engineering, University of Zanjan, Zanjan, Iran

Abstract

Introduction
In recent decades, artificial intelligence systems were employed for developing predictive models to estimate and predict many agriculture processes. Neural networks have the capability of identifying complex nonlinear systems with their own high learning ability. Artificial Neural Networks as a modern approach has successfully been used to solve an extensive variety of problems in the science and engineering, exclusively for some space where the conventional modeling procedure fail. A well-trained Artificial Neural Networks can be used as a predictive model for a special use, which is a data processing system inspired by biological neural system. The short storage life of hawthorn fruit and its high susceptibility to water loss and browning are the main factors limiting its marketability. So, it is important to evaluate parameters that affected the hawthorn quality. An adaptive neuro-fuzzy inference system or adaptive network-based fuzzy inference system (ANFIS) is a kind of artificial neural network that is based on Takagi-Sugeno fuzzy inference system. To estimate changes in fruit quality as a function of storage conditions, the evolution of certain quality-indicative properties such as color, firmness or weight can be used to provide related information on the quality grade of the product stored. Measurement of these parameters is an expensive and time-consuming process. Therefore, parameter prediction due to affecting factors will be more useful. In this study, the physicochemical properties of hawthorn fruit during various storage was predicted using artificial neural networks method. Hawthorn (Crataegus pinnatifida), belonging to the Rosaceae family, consists of small trees and shrubs. The color of the ripe fruit ranges from yellow, through green to red, and on to dark purple. Hawthorn is one of the most widely consumed horticultural products, either in fresh or processed form. It is also an important component of many processed food products because of its excellent flavor, attractive color and high content of many macro- and micro-nutrients.
Materials and Methods
The purpose of this study was a prediction of color, physical and mechanical properties of hawthorn fruit (Crataegus pinnatifida) during storage condition using artificial neural networks (ANNs) and adaptive network-based fuzzy inference system (ANFIS). Experimental data obtained from fruit storage, were used for training and testing the network. In the present research, artificial neural networks were used for modeling the relationship between physicochemical properties and color attributes with different storage time. Several criteria such as training algorithm, learning function, number of hidden layers, number of neurons in each hidden layer and activation function were given to improve the performance of the artificial neural networks. The total number of hidden layers and the number of neurons in each hidden layer were chosen by trial and error. The network’s inputs include storage time, hawthorn moisture content and storage temperature and the network’s output were the values of the physicochemical and color properties. The training rules were Momentum and Levenberg-Marquardt. The transfer functions were TanhAxon and SigmoidAxon.
Results and Discussion
To predict the weight loss and firmness multilayer perceptron network with the momentum learning algorithm, topologies of 3-15-5-1 and 3-8-5-1 with R²=0.9938 and 0.9953 were optimal arrangement, respectively. The optimal topologies for color change, hue, Chroma were 3-9-7-1 (R²=0.9421), 3-9-3-1 (R²=0.9947) and 3-7-1 (R²=0.9535) respectively, with momentum learning algorithm and TanhAxon activation function. The best network for ripening index prediction was Multilayer perceptron network with the TanhAxon activation function, Levenberg-Marquardt Levenberg-Marquardt learning algorithm, topology of 3-5-1-1 and R²=0.9956.
Conclusion
Three factors including firmness, total soluble solids and titratable acidity were considered for ripening index calculation during fruits storage condition. Momentum and Levenberg-Marquardt learning algorithms with SigmoidAxon and TanhAxon activation functions were used for training the patterns. Results indicated artificial neural networks to be accurate and versatile and they predicted the quality changes in hawthorn fruits. The outcomes of this study provide additional and useful information for hawthorn fruits storage conditions.

Keywords

Adaptive neuro-fuzzy inference system; Artificial neural network; Hawthorn; Multilayer perceptron

References

1. Abbaspour Gilandeh, Y., A. Jahanbakhshi, and M. Kaveh. 2020. Prediction kinetic, energy and exergy of quince under hot air dryer using ANNs and ANFIS. Food Science & Nutrition 8: 594-611.

2. Ahangarnezhad, N., G. Najafi, and A. Jahanbakhshi. 2019. Determination of the physical and mechanical properties of a potato (the Agria variety) in order to mechanise the harvesting and post-harvesting operations. Research in Agricultural Engineering 65: 33-39.

3. Amiri Chayjan, R., M. Kaveh, and S. Khayati. 2015. Modeling Drying Characteristics of Hawthorn Fruit under Microwave Convective Conditions. Journal of Food Processing and Preservation 39: 239-253.

4. Aral, S., and A. Vildan Bese. 2016. Convective drying of hawthorn fruit (Crataegus spp.): Effect of experimental parameters on drying kinetics, color, shrinkage, and rehydration capacity. Food Chemistry 210: 577-584.

5. Arzate-Vazquez, I., J. J. Chanona-Perez, M. D. J. Perea-Flores, G. Calderon-Domı´nguez, M. Moreno-Armendariz, and G. Gutierrez-Lopez. 2011. Image processing applied to classification of avocado variety Hass (Persea americana Mill) during the ripening process. Food and Bioprocess Technology 4: 1307-1313.

6. Asghari, M. R., R. Ebrahimi, B. Hosseinzadeh, and D. Ghanbarian. 2017. Mulberry qualitative pramaters modelling in drying process using artificial neural networks. Iranian Journal of Biosystems Engineering 48: 9-18. (In Farsi).

7. Ashournezhad, M., and M. Ghasemnezhad. 2012. Effects of cellophane-film packaging and cold storage on the keeping quality and storage life of loquat fruit (Eriobotrya japonica). Iranian Journal of Nutrition Sciences & Food Technology 7: 95-102. (In Farsi).

8. Azarmdel, H., A. Jahanbakhshi, S. S. Mohtasebi, and A. R. Muñoz. 2020. Evaluation of image processing technique as an expert system in mulberry fruit grading based on ripeness level using artificial neural networks (ANNs) and support vector machine (SVM). Postharvest Biology and Technology 166: 111201.

9. Billy, L., E. Mehinagic, G. Royer, C. M. G. C. Renard, G. Arvisenet, and C. Prost. 2008. Relationship between texture and pectin composition of two apple cultivars during storage. Postharvest Biology and Technology 47: 315-324.

10. Cardenas-Perez, S., J. Chanona-Perez, J. V. Mendez-Mendez, G. Calderon-Domınguez, R. Lopez-Santiago, M. A. J. Perea-Flores, and I. Arzate-Vazquez. 2017. Evaluation of the ripening stages of apple (Golden Delicious) by means of computer vision system. Biosystems Engineering 159: 46-58.

11. Derili gharjalar, S., H. Hassanpour, and A. Farokhzad. 2017. Pomological characteristics of some hawthorn genotypes in West Azerbaijan province. Iranian Journal of Horticultural Science 48: 689-700.

12. Dhakala, S., V. M. Balasubramaniam, H. Ayvaza, and L. E. Rodriguez-Saona. 2018. Kinetic modeling of ascorbic acid degradation of pineapple juice subjected to combined pressure-thermal treatment. Journal of Food Engineering 224: 62-70.

13. Farzan, E., M. R. Rahimi, and V. Madadi Avargani. 2017. Drying kinetic and shrinkage study of a Hawthorn sample in a vibro fluidized bed dryer using an adsorption system in order to control of inlet air humidity. Journal of Innovative Food Technologies 107-122. (In Farsi).

14. Guadarrama, A., and S. Andrade. 2012. Physical, chemical and biochemical changes of Sweetsop (Annona squamosa L.) and golden apple (Spondias citherea Sonner) fruits during ripening. Journal of Agricultural Science and Technology 1148-1157.

15. Helrich, K. 1990. AOAC Official Methods of Analysis. Official Methods of Analysis of the AOAC International. Gaithersburg: Association of official analytical chemists Inc (AOAC International).

16. Jahanbakhshi, A., R. Yeganeh, and G. Shahgoli. 2019a. Determination of mechanical properties of banana fruit under quasi-static loading in pressure, bending, and shearing tests. International Journal of Fruit Science: 1-9

17. Jahanbakhshi, A., Y. Abbaspour Gilandeh, B. Ghamari, and K. Heidarbeigi. 2019b. Assessment of physical, mechanical, and hydrodynamic properties in reducing postharvest losses of cantaloupe (Cucumis melo var. Cantaloupensis). Journal of Food Process Engineering 42: e13091.

18. Jahanbakhshi, A., V. Rasooli Sharabiani, K. Heidarbeigi, M. Kaveh, and E. Taghinezhad. 2019c. Evaluation of engineering properties for waste control of tomato during harvesting and postharvesting. Food Science & Nutrition 7: 1473-1481.

19. Jahangiri-Saleh, M., S. R. Hassan-Beygi, M. Aboonajmi, and M. Lotfi. 2017. Prediction of Cucumber Acoustic Response, CrispnessIndex and Firmness Using Artificial Neural Networks. Food Science and Technology 14: 265-276. (In Farsi).

20. Kami, D., L. Shi, T. Sato, T. Suzuki, and K. Oosawa. 2009. Cryopreservation of shoot apices of hawthorn in vitro cultures originating from East Asia. Scientia Horticulturae 120: 84-88.

21. Karaman, S., I. Ozturk, H. Yalcin, A. Kayacier, and O. Sagdic. 2012. 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. Journal of the Science of Food and Agriculture 92: 49-58.

22. Kaveh, M., Y. Abbaspour-Gilandeh, R. A. Chayjan, and R. Mohammadigol. 2019. Comparison of Mathematical Modeling, Artificial Neural Networks and Fuzzy Logic for Predicting the Moisture Ratio of Garlic and Shallot in a Fluidized Bed Dryer. Journal of Agricultural Machinery 9. (In Farsi).

23. Khayati, S., and R. A. Chayjan. 2016. Prediction of some thermal, physical and mechanical properties of terebinth fruit after semi-industrial continuous drying using artificial neural networks. Food Science and Technology 13: 161-172.

24. Li, T., J. Zhu, L. Guo, X. Shi, Y. Liu, and X. Yang. 2013. Differential effects of polyphenols-enriched extracts from hawthorn fruit peels and fleshes on cell cycle and apoptosis in human MCF-7 breast carcinoma cells. Food Chemistry 141: 1008-1018.

25. Li, W.-Q., Q.-P. Hu, and J.-G. Xu. 2015. Changes in physicochemical characteristics and free amino acids of hawthorn (Crataegus pinnatifida) fruits during maturation. Food Chemistry 175: 50-56.

26. Liu, P., B. Yang, and H. Kallio. 2010. Characterization of phenolic compounds in Chinese hawthorn (Crataegus pinnatifida Bge. var. major) fruit by high performance liquid chromatography–electrospray ionization mass spectrometry. Food Chemistry 121: 1188-1197.

27. Liu, P., H. Kallio, and B. Yang. 2011a. Phenolic compounds in hawthorn (Crataegus grayana) fruits and leaves and changes during fruit ripening. Journal of Agricultural and Food Chemistry 59: 11141-11149.

28. Liu, P., H. Kallio, D. Lü, C. Zhou, and B. Yang. 2011b. Quantitative analysis of phenolic compounds in Chinese hawthorn (Crataegus spp.) fruits by high performance liquid chromatography-electrospray ionisation mass spectrometry. Food Chemistry 127: 1370-1377.

29. Luo, Y., G. Chen, B. Li, B. Ji, Y. Guo, and F. Tia. 2009. Evaluation of antioxidative and hypolipidemic properties of a novel functional diet formulation of Auricularia auricula and Hawthorn. Innovative Food Science and Emerging Technologies 10: 215-221.

30. Majidzadeh, H., B. Emadi, and A. A. Farzad. 2015. Prediction the moisture content of kiwifruit in vacuum drier using artificial neural network. Iranian Food Science and Technology Research Journal 11: 107-117. (In Farsi).

31. Menz, G., and F. Vriesekoop. 2010. Physical and chemical changes during the maturation of gordal sevillana olives (Olea europaea L., cv. Gordal Sevillana). Journal of Agricultural and Food Chemistry 58: 4934-4938.

32. Mohammadigol, R., F. Azadshahraki, and V. Lotfi. 2017. Quantification of total phenol in grape by near infrared spectroscopy and artificial neural network. Journal of Research and Innovation in Food Science and Technology 6: 313-320. (In Farsi).

33. Mraihi, F., M. Hidalgo, S. Pascual-Teresa, M. Trabelsi-Ayadi, and J. K. Cherif. 2015. Wild grown red and yell ow Hawthorn fruits from Tunisia as source of antioxidants. Arabian Journal of Chemistry 8: 570-578.

34. Nordey, T., M. Lechaudel, M. Genard, and J. Joas. 2014. Spatial and temporal variations in mango colour, acidity, and sweetness in relation to temperature and ethylene gradients within the fruit. Journal of Plant Physiology 171: 1555-1563.

35. Opara, U. L., and M. R. Al-Ani, and N. M. Al-Rahbi. 2012. Effect of fruit ripening stage on physico-chemical properties, nutritional composition and antioxidant components of tomato (Lycopersicum esculentum) cultivars. Food and Bioprocess Technology 5: 3236-3243.

36. Razavi, F., M. Roghayeh, V. Rabiei, M. Soleimani Aghdam, and A. Soleimani. 2018. Glycine betaine treatment attenuates chilling injury and maintains nutritional quality of hawthorn fruit during storage at low temperature. Scientia Horticulturae 233: 188-194.

37. Velez-Rivera, N., J. Blasco, J. Chanona-Perez, G. Calderon-Dominguez, M. D. J. Perea-Flores, I. Arzate-Vazquez, S. Cubero, and R. Farrera-Rebollo. 2014. Computer Vision System Applied to Classification of “Manila” Mangoes During Ripening Process. Food and Bioprocess Technology 7: 1183-1194.

38. Wang, H., F. Chen, H. Yang, Y. Chen, L. Zhang, and H. An. 2012. Effects of ripening stage and cultivar on physicochemical properties and pectin nanostructures of jujubes. Carbohydrate Polymers 89: 1180-1188.

39. Wen, L., X. Guo, R. Hai Liu, L. You, A. Mehmood Abbasi, and X. Fu. 2015. Phenolic contents and cellular antioxidant activity of Chinese hawthorn “Crataegus pinnatifida”. Food Chemistry: 54-62.

40. Zheng, H. Z., Y. I. Kim, and S. K. Chung. 2012. A profile of physicochemical and antioxidant changes during fruit growth for the utilisation of unripe apples. Food Chemistry 131: 106-110.