Classification of Raw Milk Composition and Somatic Cell Count in Water Buffaloes with Support Vector Machines

TAHTALI, YALÇIN

doi:DOI: 10.9775/kvfd.2020.23955

Classification of Raw Milk Composition and Somatic Cell Count in Water Buffaloes with Support Vector Machines

Yalçın TAHTALI (Tokat Gaziosmanpaşa Üniversitesi, Ziraat Fakültesi, Zootekni Bölümü, Tokat, Türkiye)

Kafkas Üniversitesi Veteriner Fakültesi Dergisi

0 0

Yıl: 2020 Cilt: 26 Sayı: 4 Sayfa Aralığı: 541 - 549 Metin Dili: İngilizce DOI: DOI: 10.9775/kvfd.2020.23955 İndeks Tarihi: 07-11-2020

Classification of Raw Milk Composition and Somatic Cell Count in Water Buffaloes with Support Vector Machines

Öz:

The study investigates the classification of milk quality with support vector machines (SVM) using the raw milk composition and somatic cell count (SCC) data on buffalos. For this purpose, 11-variable (dry matter, fat-free dry matter, fat (%), protein, lactose, casein, urea, density, acidity, pH, freezing point) on milk composition and SCC of 288 buffalos were used. SVM is a classifier with a high generalization ability that is based on structural risk minimization with a statistical learning system and can be applied to both linear and non-linear data. The classification successes of some kernel functions used in the SVM (polynomial kernel, normalized polynomial kernel and radial basis kernel) were investigated and their classification performances were compared with a multilayer perceptron algorithm. The results showed that the classification successes of polynomial kernel, normalized polynomial kernel and radial basis kernel were 93.06%, 92.36% and 90.97%, respectively, while the classification success of the multilayer perceptron was 81.60%. The comparison of the results with respect to the root mean square error (RMSE) values revealed that the polynomial kernel had the lowest value (0.263), while the multilayer perceptron had the highest value (0.384). According to this criterion, the best classifier was the polynomial kernel function, while the weakest classifier was the multilayer perceptron (0.384). Considering the receiver operating characteristic (ROC) area values, with respect to the closeness to 1 criterion, normalized polynomial kernel was the best function, while the multilayer perceptron function was the weakest function. The separate evaluation of the precision, sensitivity and F-measure values showed that the polynomial kernel was the most successful function, while the multilayer perceptron was the weakest function.

Anahtar Kelime:

Mandalarda Çiğ Süt Bileşimi ve Somatic Hücre Sayısının Destek Vektör Makinaları İle Sınıflandırılması

Öz:

Bu çalışmada amaç mandalarda çiğ süt bileşimi ve somatik hücre sayısı verilerini kullanarak süt kalitesinin destek vektör makineleri (DVM) ile sınıflandırılmasını araştırmaktır. Bu amaçla, 288 mandaya ait somatik hücre sayısı ve 11 değişkenli (kuru madde, yağsız kuru madde, yağ, protein, laktoz, kazein, üre, yoğunluk, asitlik, pH, donma noktası) süt bileşenleri kullanılmıştır. DVM, istatistiksel öğrenme sistemi ile yapısal risk minimizasyonuna dayanan, hem doğrusal hem de doğrusal olmayan verilere uygulanabilen yüksek genelleme kabiliyetine sahip bir sınıflandırıcıdır. DVM’de kullanılan bazı çekirdek fonksiyonlarının (polinom çekirdeği, normalleştirilmiş polinom çekirdeği ve radyal temel çekirdeği) sınıflandırma başarıları araştırılmış ve sınıflandırma performansları çok katmanlı bir algılayıcı algoritması ile karşılaştırılmıştır. Sonuçlar, polinom çekirdeğinin, normalize polinom çekirdeğinin ve radyal temel çekirdeğin sınıflandırma başarılarının sırasıyla %93.06, %92.36 ve %90.97 olduğunu, çok katmanlı algılayıcı algoritmanın sınıflandırma başarısının %81.60 olduğunu göstermiştir. Çekirdek fonksiyonlarının hata kareleri ortalamasının karekökü (RMSE) değerleri ile karşılaştırılması yapıldığında, polinom çekirdeğinin en düşük değere (0.263) sahip olduğunu, çok katmanlı algılayıcının en yüksek değere (0.384) sahip olduğu tespit edilmiştir. Bu kritere göre, en iyi sınıflandırıcının polinom çekirdek fonksiyonu, en zayıf sınıflandırıcının ise çok katmanlı algılayıcı (0.384) olduğu görülmüştür. ROC eğrisi altında kalan alan değerleri göz önüne alındığında, 1’e yakınlık kriteri açısından, normalleştirilmiş polinom çekirdeği en iyi fonksiyon, çok katmanlı algılayıcının en zayıf fonksiyon olduğu gözlenmiştir. Hassasiyet, duyarlılık ve F-ölçüm değerlerinin ayrı ayrı değerlendirilmesi sonucunda sınıflandırmada en başarılı fonksiyonun polinom çekirdeğini, en başarısız fonksiyonun ise çok katmanlı algılayıcı olduğu belirlenmiştir.

Anahtar Kelime:

Belge Türü: Makale Makale Türü: Araştırma Makalesi Erişim Türü: Erişime Açık

1. Abukhait J, Mansour AM, Obeidat M: Classification based on gaussiankernel support vector machine with adaptive fuzzy inference system. Prz Elektrotechnıczn, 94 (5): 14-22, 2018. DOI: 10.15199/48.2018.05.03
2. Ghafouri-Kesbi F, Rahimi-Mianji G, Honarvar M, Nejati-Javaremi A: Predictive ability of random forests, boosting, support vector machines and genomic best linear unbiased prediction in different scenarios of genomic evaluation. Anim Prod Sci, 57 (2): 229-236, 2017. DOI: 10.1071/AN15538
3. Damé MCF, Lima CTS, Marcondes CR, Ribeiro MER, Garnero ADV: Preliminary study on buffalo (Bubalus bubalis) milk production in Southern Brazil. Rev Vet, 21 (1): 585-587, 2010.
4. Barth K: Evaluation of somatic cell count under automatic milking conditions. Physiological and technical aspects of machine milking. Proceedings of an International Conference, Nitra, Slovak Republic, 165169, 26-27 June 2001.
5. Dhakal IP, Kapur MP, Anshu S: Significance of differential somatic cell counts in milk for the diagnosis of subclinical mastitis in buffaloes using foremilk and stripping milk. Indian J Anim Health, 31, 39-42, 1992.
6. Singh M, Ludri RS: Somatic cell count in Murrah buffaloes (Bubalus bubalis) during different stages of lactation, parity and season. Asian Australas J Anim Sci, 14, 189-192, 2001. DOI: 10.5713/ajas.2001.189
7. Sharma N, Singh NK, Bhadwal MS: Relationship of somatic cell count and mastitis: An overview. Asian Australas J Anim Sci, 24 (3): 429-438, 2011. DOI: 10.5713/ajas.2011.10233
8. Anonymous: Türkiye İstatistik Kurumu Hayvancılık İstatistikleri. http://www.tuik.gov.tr/hayvancilikapp/hayvancilik.zul”hayvancilikapp/ hayvancilik.zul. Accessed: 12.05.2019.
9. Vapnik VN: The Nature of Statistical Learning Theory. 167-174, SpringerVerlag, New York, 1995. DOI: 10.1007/978-1-4757-2440-0
10. Vapnik VN: Statistics for Engineering and Information Science. The Nature of Statistical Learning Theory. 2th ed., 131-137, Springer, New York, 2000. DOI: 10.1007/978-1-4757-3264-1
11. Radhakrishnan S, Ramanathan R: A support vector machine with gabor features for animal ıntrusion detection in agriculture fields. Procedia Comput Sci, 143, 493-501, 2018. DOI: 10.1016/j.procs.2018.10.422
12. Udaya Shalika AWD, Seneviratne L: Animal classification system based on image processing & support vector machine. J Comput Commun, 4 (1): 12-21, 2016. DOI: 10.4236/jcc.2016.41002
13. Wang G: Machine learning for inferring animal behavior from location and movement data. Ecol Inform, 49, 69-76, 2019. DOI: 10.1016/j. ecoinf.2018.12.002
14. Zhao HT, Feng YZ, Chen W, Jia GF: Application of invasive weed optimization and least square support vector machine for prediction of beef adulteration with spoiled beef based on visible near-infrared (VisNIR) hyperspectral imaging. Meat Sci, 151, 75-81, 2019. DOI: 10.1016/j. meatsci.2019.01.010
15. Amraei S, Mehdizadeh SA, Sallary S: Application of computer vision and support vector regression for weight prediction of live broiler chicken. Eng Agric Environ Food, 10 (4): 266-271, 2017. DOI: 10.1016/j. eaef.2017.04.003
16. Ahmadi H, Rodehutscord M: Application of artificial neural network and support vector machines in predicting metabolizable energy in compound feeds for pigs. Front Nutr, 4:27, 2017. DOI: 10.3389/fnut. 2017.00027
17. Harmon RJ: Physiology of mastitis and factors affecting somatic cell counts. J Dairy Sci, 77, 2103-2112, 1994. DOI: 10.3168/jds.S00220302(94)77153-8
18. Mammadova N, Keskin İ: Application of the support vector machine to predict subclinical mastitis in dairy cattle. Sci World J, 2013:603897, 2013. DOI: 10.1155/2013/603897
19. Cavero D, Tölle KH, Buxade C, Krieter J: Mastitis detection in dairy cows by application of fuzzy logic. Livest Sci, 105, 207-213, 2006. DOI: 10.1016/j.livsci.2006.06.006
20. De Mol RM, Ouweltjes W: Detection model for mastitis in cows milked in an automatic milking system, Prev Vet Med, 49, 71-82. 2001. DOI: 10.1016/s0167-5877(01)00176-3
21. Colman E, Waegeman W, De Baets B, Fievez V: Prediction of subacute ruminal acidosis based on milk fatty acids: A comparison of linear discriminant and support vector machine approaches for model development. Comput Electron Agr, 111, 179-185, 2015. DOI: 10.1016/j. compag.2015.01.002
22. Gao X, Xue H, Pan X, Jiang X, Zhou Y, Luo X: Somatic cells recognition by application of gabor feature-based (2D)2PCA. Int J Pattern Recogn, 31 (12):1757009, 2017. DOI: 10.1142/S0218001417570099
23. Cerón-Muñoz M, Tonhati H, Duarte J, Oliveira J, Muñoz-Berrocal M, Jurado-Gámez H: Factors affecting somatic cell counts and their relations with milk and milk constituent yield in buffaloes. J Dairy Sci, 85 (11): 2885-2889, 2002. DOI: 10.3168/jds.S0022-0302(02)74376-2
24. Sekerden Ö, Avsar YK: Milk composition, rennet coagulation time, urea content and environmental factors affecting them in Anatolian Buffaloes. J Anim Prod, 49 (2): 7-14, 2008.
25. Fernandes SA, de Mattos WRS, Matarazzo SM, Gama MAS, Malhado CHM, Ferrão, SPB, Etchegaray MAL, Lima CGD: Effect of somatic cell count on Murrah buffaloes milk. Prev Vet, 21 (1): 552-553, 2010.
26. Ayasan T, Hızlı H, Yazgan E, Kara U, Gök K: The effect of somatic cell count on milk urea nitrogen and milk composition. Kafkas Unıv Vet Fak Derg, 17 (4): 659-662, 2011. DOI: 10.9775/kvfd.2011.4489
27. Yesilova A, Yilmaz A, Ser G, Kaki B: Modeling with Gaussian mixture regression for lactation milk yield in Anatolian buffaloes. Indian J Anim Res, 50 (6): 989-994, 2016. DOI: 10.18805/ijar.v0iOF.4545
28. Anonim: Türk Gıda Kodeksi Yönetmeliği. T.C. Resmi Gazete, 14 Şubat 2000, Sayı 23964, s. 35. Ankara, 2000
29. Beykaya M, Özbey A, Yıldırım Z: Determination of physical, chemical and microbiological properties of milk from some dairy plants in Sivas Province. TURJAF, 5 (4): 388-396, 2017. DOI: 10.24925/turjaf.v5i4. 388-396.1172

APA	TAHTALI Y (2020). Classification of Raw Milk Composition and Somatic Cell Count in Water Buffaloes with Support Vector Machines. , 541 - 549. DOI: 10.9775/kvfd.2020.23955
Chicago	TAHTALI YALÇIN Classification of Raw Milk Composition and Somatic Cell Count in Water Buffaloes with Support Vector Machines. (2020): 541 - 549. DOI: 10.9775/kvfd.2020.23955
MLA	TAHTALI YALÇIN Classification of Raw Milk Composition and Somatic Cell Count in Water Buffaloes with Support Vector Machines. , 2020, ss.541 - 549. DOI: 10.9775/kvfd.2020.23955
AMA	TAHTALI Y Classification of Raw Milk Composition and Somatic Cell Count in Water Buffaloes with Support Vector Machines. . 2020; 541 - 549. DOI: 10.9775/kvfd.2020.23955
Vancouver	TAHTALI Y Classification of Raw Milk Composition and Somatic Cell Count in Water Buffaloes with Support Vector Machines. . 2020; 541 - 549. DOI: 10.9775/kvfd.2020.23955
IEEE	TAHTALI Y "Classification of Raw Milk Composition and Somatic Cell Count in Water Buffaloes with Support Vector Machines." , ss.541 - 549, 2020. DOI: 10.9775/kvfd.2020.23955
ISNAD	TAHTALI, YALÇIN. "Classification of Raw Milk Composition and Somatic Cell Count in Water Buffaloes with Support Vector Machines". (2020), 541-549. https://doi.org/DOI: 10.9775/kvfd.2020.23955

APA	TAHTALI Y (2020). Classification of Raw Milk Composition and Somatic Cell Count in Water Buffaloes with Support Vector Machines. Kafkas Üniversitesi Veteriner Fakültesi Dergisi, 26(4), 541 - 549. DOI: 10.9775/kvfd.2020.23955
Chicago	TAHTALI YALÇIN Classification of Raw Milk Composition and Somatic Cell Count in Water Buffaloes with Support Vector Machines. Kafkas Üniversitesi Veteriner Fakültesi Dergisi 26, no.4 (2020): 541 - 549. DOI: 10.9775/kvfd.2020.23955
MLA	TAHTALI YALÇIN Classification of Raw Milk Composition and Somatic Cell Count in Water Buffaloes with Support Vector Machines. Kafkas Üniversitesi Veteriner Fakültesi Dergisi, vol.26, no.4, 2020, ss.541 - 549. DOI: 10.9775/kvfd.2020.23955
AMA	TAHTALI Y Classification of Raw Milk Composition and Somatic Cell Count in Water Buffaloes with Support Vector Machines. Kafkas Üniversitesi Veteriner Fakültesi Dergisi. 2020; 26(4): 541 - 549. DOI: 10.9775/kvfd.2020.23955
Vancouver	TAHTALI Y Classification of Raw Milk Composition and Somatic Cell Count in Water Buffaloes with Support Vector Machines. Kafkas Üniversitesi Veteriner Fakültesi Dergisi. 2020; 26(4): 541 - 549. DOI: 10.9775/kvfd.2020.23955
IEEE	TAHTALI Y "Classification of Raw Milk Composition and Somatic Cell Count in Water Buffaloes with Support Vector Machines." Kafkas Üniversitesi Veteriner Fakültesi Dergisi, 26, ss.541 - 549, 2020. DOI: 10.9775/kvfd.2020.23955
ISNAD	TAHTALI, YALÇIN. "Classification of Raw Milk Composition and Somatic Cell Count in Water Buffaloes with Support Vector Machines". Kafkas Üniversitesi Veteriner Fakültesi Dergisi 26/4 (2020), 541-549. https://doi.org/DOI: 10.9775/kvfd.2020.23955