Comparison of different methods for determining diabetes

YURTAY, Nilüfer; SERTKAYA, Cengiz; BOZKURT, MEHMET RECEP; YILMAZ, Ziynet

Comparison of different methods for determining diabetes

Mehmet Recep BOZKURT, (Sakarya Üniversitesi, Elektrik Elektronik Mühendisliği Bölümü, Sakarya, Türkiye)

Nilüfer YURTAY, (Sakarya Üniversitesi, Bilgisayar Mühendisliği Bölümü, Sakarya, Türkiye)

Ziynet YILMAZ, (Sakarya Üniversitesi, Elektrik Elektronik Mühendisliği Bölümü, Sakarya, Türkiye)

Cengiz SERTKAYA (Sakarya Üniversitesi, Bilgisayar Mühendisliği Bölümü, Sakarya, Türkiye)

Turkish Journal of Electrical Engineering and Computer Sciences

1 0

Yıl: 2014 Cilt: 22 Sayı: 4 Sayfa Aralığı: 1044 - 1055 Metin Dili: İngilizce İndeks Tarihi: 29-07-2022

Comparison of different methods for determining diabetes

Öz:

In this study, the Pima Indian Diabetes dataset was categorized with 8 different classifiers. The data were taken from the University of California Irvine Machine Learning Repository's web site. As a classifier, 6 different neural networks [probabilistic neural network (PNN), learning vector quantization, feedforward networks, cascade-forward networks, distributed time delay networks (DTDN), and time delay networks], the artificial immune system, and the Gini algorithm from decision trees were used. The classifier's performance ratios were studied separately as accuracy, sensitivity, and specificity and the success rates of all of the classifiers are presented. Among these 8 classifiers, the best accuracy and specificity values were achieved with the DTDN and the best sensitivity value was achieved with the PNN.

Anahtar Kelime:

Konular: Mühendislik, Elektrik ve Elektronik

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

[1] U. Masharani, J.H. Karam, Current Medical Diagnosis & Treatment 2003: A Lange Medical Book, San Francisco, CA, USA, McGraw-Hill, 2003.
[2] WHO, World Diabetes Statistics, Geneva, Switzerland, WHO, available at http://www.who.int/diabetes/en/index.html, © 2014.
[3] Y. Huang, P. McCullagh, N. Black, R. Harper, “Feature selection and classification model construction on type 2 diabetic patients data”, Artificial Intelligence in Medicine, Vol. 41, pp. 251–262, 2007.
[4] S. Lekkas, L. Mikhailov, “Evolving fuzzy medical diagnosis of Pima Indians diabetes and of dermatological diseases”, Artificial Intelligence in Medicine, Vol. 50, pp. 117–126, 2010.
[5] K. Polat, S. Güneş, “An expert system approach based on principal component analysis and adaptive neuro-fuzzy inference system to diagnosis of diabetes disease”, Digital Signal Processing, Vol. 17, pp. 702–710, 2007.
[6] H. Temurtas, N. Yumusak, F. Temurtas, “A comparative study on diabetes disease diagnosis using neural networks”, Expert Systems with Applications, Vol. 36, pp. 8610–8615, 2009.
[7] K. Kayaer, T. Yildirim, “Medical diagnosis on Pima Indian diabetes using general regression neural networks”, Proceedings of the International Conference on Artificial Neural Networks and Neural Information Processing, pp. 181–184, 2003.
[8] L. Meng, P. Putten, H. Wang, “A comprehensive benchmark of the artificial immune recognition system (AIRS)”, Proceedings of the First International Conference on Advanced Data Mining and Applications, pp. 575–582, 2005.
[9] New Mexico State University, The Human Genome Project and Diabetes: Genetics of Type II Diabetes, Las Cruces, NM, USA, 1997.
[10] UCI Machine Learning, Pima Indians Diabetes Data Set, Irvine, CA, USA, University of California Irvine, available at http://archive.ics.uci.edu/ml/machine-learning-databases/pima-indians-diabetes.
[11] O. Engin, A. Döyen, “Artificial immune systems and applications in industrial problems”, Gazi University Journal of Science, Vol. 17, pp. 71–84, 2004.
[12] L.N. Castro, J. Timmis, Artificial Immune Systems: A New Computational Intelligence Approach, 1st ed., London, UK, Springer, 2002.
[13] S.M. Garrett, “How do we evaluate artificial immune systems”, Evolutionary Computation, Vol. 13, pp. 145–178, 2005.
[14] K. Polat, S. Güneş, “Computer aided medical diagnosis system based on principal component analysis and artificial immune recognition system classifier algorithm”, Expert System with Applications, Vol. 34, pp. 773–779, 2008.
[15] Y. Özkan, Veri Madenciliği Yöntemleri, istanbul, Turkey, Papatya Yayıncılık, 2008 (in Turkish).
[16] Rapidminer, Rapid - I - Rapidminer, available at http://rapid-i.com/content/view/181/190.
[17] E. Öztemel, Artificial Neural Networks, istanbul, Turkey, Papatya Yayıncılık, 2003.
[18] Probabilistic Neural Networks, available at http://herselfsai.com/2007/03/probabilistic-neural-networks.html.
[19] MathWorks, Probabilistic Neural Networks Radial Basis Networks, available at http://www.mathworks.com/help/toolbox/nnet/ug/bss38ji-1.html.
[20] Learning Vector Quantization Networks – Self-Organizing and Learning Vector Quantization Nets, available at http://www.kxcad.net/cae MATLAB/toolbox/nnet/self o17.html.
[21] MathWorks, Learning Vector Quantization Neural Network - MATLAB, available at http://www.mathworks.com/help/toolbox/nnet/ref/lvqnet.html.
[22] Wikipedia, Feedforward Neural Network, available at http://en.wikipedia.org/wiki/Feedforward neural network.
[23] MathWorks, Feedforward Neural Network – MATLAB, available at http://www.mathworks.com/help/toolbox/nnet/ref/feedforwardnet.html.
[24] Feedforward Network Backpropagation (Neural Network Toolbox), available at http://www.kxcad.net/cae MATLAB/toolbox/nnet/backpro7.html.
[25] MathWorks, Cascade Forward Neural Network – MATLAB, available at http://www.mathworks.com/help/toolbox/nnet/ref/cascadeforwardnet.html.
[26] MathWorks, Distributed Time Delay Neural Network – Dynamic Networks (Neural Network Toolbox), available at http://www.mathworks.com/help/toolbox/nnet/ug/bss36c8-1.html.
[27] MathWorks, Distributed Delay Network – MATLAB, available at http://www.mathworks.com/help/toolbox/nnet/ref/distdelaynet.html.
[28] Focused Time Delay Neural Network – Dynamic Networks (Neural Network Toolbox), available at http://www.kxcad.net/cae MATLAB/toolbox/nnet/dynamic7.html.
[29] MathWorks, Time Delay Neural Network – MATLAB, available at http://www.mathworks.com/help/toolbox/nnet/ref/timedelaynet.html.
[30] Wikipedia, ROC, available at http://tr.wikipedia.org/wiki/ROC (in Turkish).
[31] Wikipedia, Receiver operating characteristic, available at http://en.wikipedia.org/wiki/Receiver operating characteristic.
[32] K.K. Gündoğan, B. Alataş, A. Karcı, “Mining classification rules by using genetic algorithms with non-random initial population and uniform operator”, Turkish Journal of Electrical Engineering & Computer Science, Vol. 12, pp. 43–52, 2004.

APA	BOZKURT M, YURTAY N, YILMAZ Z, SERTKAYA C (2014). Comparison of different methods for determining diabetes. , 1044 - 1055.
Chicago	BOZKURT MEHMET RECEP,YURTAY Nilüfer,YILMAZ Ziynet,SERTKAYA Cengiz Comparison of different methods for determining diabetes. (2014): 1044 - 1055.
MLA	BOZKURT MEHMET RECEP,YURTAY Nilüfer,YILMAZ Ziynet,SERTKAYA Cengiz Comparison of different methods for determining diabetes. , 2014, ss.1044 - 1055.
AMA	BOZKURT M,YURTAY N,YILMAZ Z,SERTKAYA C Comparison of different methods for determining diabetes. . 2014; 1044 - 1055.
Vancouver	BOZKURT M,YURTAY N,YILMAZ Z,SERTKAYA C Comparison of different methods for determining diabetes. . 2014; 1044 - 1055.
IEEE	BOZKURT M,YURTAY N,YILMAZ Z,SERTKAYA C "Comparison of different methods for determining diabetes." , ss.1044 - 1055, 2014.
ISNAD	BOZKURT, MEHMET RECEP vd. "Comparison of different methods for determining diabetes". (2014), 1044-1055.

APA	BOZKURT M, YURTAY N, YILMAZ Z, SERTKAYA C (2014). Comparison of different methods for determining diabetes. Turkish Journal of Electrical Engineering and Computer Sciences, 22(4), 1044 - 1055.
Chicago	BOZKURT MEHMET RECEP,YURTAY Nilüfer,YILMAZ Ziynet,SERTKAYA Cengiz Comparison of different methods for determining diabetes. Turkish Journal of Electrical Engineering and Computer Sciences 22, no.4 (2014): 1044 - 1055.
MLA	BOZKURT MEHMET RECEP,YURTAY Nilüfer,YILMAZ Ziynet,SERTKAYA Cengiz Comparison of different methods for determining diabetes. Turkish Journal of Electrical Engineering and Computer Sciences, vol.22, no.4, 2014, ss.1044 - 1055.
AMA	BOZKURT M,YURTAY N,YILMAZ Z,SERTKAYA C Comparison of different methods for determining diabetes. Turkish Journal of Electrical Engineering and Computer Sciences. 2014; 22(4): 1044 - 1055.
Vancouver	BOZKURT M,YURTAY N,YILMAZ Z,SERTKAYA C Comparison of different methods for determining diabetes. Turkish Journal of Electrical Engineering and Computer Sciences. 2014; 22(4): 1044 - 1055.
IEEE	BOZKURT M,YURTAY N,YILMAZ Z,SERTKAYA C "Comparison of different methods for determining diabetes." Turkish Journal of Electrical Engineering and Computer Sciences, 22, ss.1044 - 1055, 2014.
ISNAD	BOZKURT, MEHMET RECEP vd. "Comparison of different methods for determining diabetes". Turkish Journal of Electrical Engineering and Computer Sciences 22/4 (2014), 1044-1055.