Zeki Optimizasyon Tabanlı Destek Vektör Makineleri ile Diyabet Teşhisi

Year 2019, , 557 - 566, 01.09.2019

Utku Köse

https://doi.org/10.2339/politeknik.418851

Cited By: 6

Abstract

Yapay Zekâ, farklı gerçek dünya
problemlerine etkin bir şekilde uygulanabilen ve geleceğimizi uzun bir süredir
şekillendiren, önemli bilim alanlarından birisidir. Uygulandığı problem türleri
çok çeşitli olmakla birlikte, bunlardan en dikkat çekenlerinden birisi de
medikal teşhistir. Açıklamalardan hareketle bu çalışmanın amacı,  zeki optimizasyon tabanlı Destek Vektör
Makineleri’ni (DVM) kullanarak diyabet teşhisi gerçekleştirmektir. Bu bağlamda,
günümüz güncel zeki optimizasyon algoritmalarından beş tanesi Gaussian-RBF
kernel fonksiyonu kullanan bir non-lineer DVM’yi optimize etmek amacıyla
kullanılmıştır. Elde edilen bulgular, farklı algoritmalar ile kurulmuş hibrit
sistemlerin, farklı düzeyde başarımlar gösterdiğini ancak genel anlamda zeki
optimizasyon-DVM yaklaşımıyla diyabet teşhisinde yüksek oranda tutarlı sonuçlar
elde edilebildiğini ortaya koymuştur. Çalışma bu yönüyle izlenen yaklaşımın
Yapay Zekâ tabanlı teşhis açısından önemli bir potansiyele sahip olduğunu da
teyit etmektedir.  

Keywords

Zeki optimizasyon, destek vektör makineleri, diyabet teşhisi, medikal teşhis, yapay zekâ

Diabetes Diagnosis with Intelligent Optimization Based Support Vector Machines

Abstract

Artificial Intelligence is one of the most important
scientific fields that can be applied effectively in different real world
problems and has been shaping our future for a long time. While there are
various types of problems in which it is applied, medical diagnosis is one of
the most remarkable one among them. Moving from the explanations, objective of
this study is to realize diabetes diagnosis by using intelligent optimization
based Support Vector Machines (SVM). In this context, five ones of today’s
recent intelligent optimization algorithms were used for optimizing a non-linear
SVM, which is using a Gaussian-RBF kernel function. Obtained findings showed
that hybrid systems formed with different algorithms show different-level
success but in general, good level accurate results can be achieved via
intelligent optimization-SVM approach. Hereby, the study also confirms that
this followed approach has a significant potential for Artificial Intelligence
based diagnosis.

Keywords

Intelligent optimization, support vector machines, diabetes diagnosis, medical diagnosis, artificial intelligence

References

• [1] Russell, S.J., Norvig, P., Canny, J.F., Malik, J.M. and Edwards, D.D., “Artificial Intelligence: A Modern Approach”, 2(9): Upper Saddle River: Prentice Hall, (2003).
• [2] Nabiyev, V.V., “Yapay Zeka: Problemler-Yöntemler-Algoritmalar”, Seçkin Yayıncılık, (2012).
• [3] Goertzel, B., “Artificial general intelligence: concept, state of the art, and future prospects”, Journal of Artificial General Intelligence, 5(1): 1-48, (2014).
• [4] Allahverdi, N., “Uzman Sistemler: Bir Yapay Zeka Uygulaması”, Atlas Yayın Dağıtım, (2002).
• [5] Alpaydın, E., “Yapay Öğrenme”, İstanbul, Boğaziçi Üniversitesi Yayınevi, (2011).
• [6] Aydın, A.O., “Yapay Zekâ: Bütünleşik Bilişe Doğru”, İstanbul, İstanbul Gelişim Üniversitesi Yayınları, (2013).
• [7] Hamet, P. and Tremblay, J., “Artificial intelligence in medicine”, Metabolism, 69: 36-40, (2017).
• [8] Jaeger, H., “Artificial intelligence: Deep neural reasoning”, Nature, 538(7626): 467-468, (2016).
• [9] Strong, A., “Applications of artificial intelligence and associated technologies”, Science (ETEBMS-2016), 5(6), (2016).
• [10] Szolovits, P., Patil, R.S. and Schwartz, W.B., “Artificial intelligence in medical diagnosis”, Annals of Internal Medicine, 108(1): 80-87, (1988).
• [11] Kononenko, I., “Machine learning for medical diagnosis: history, state of the art and perspective”, Artificial Intelligence in Medicine, 23(1): 89-109, (2001).
• [12] Abbass, H.A., “An evolutionary artificial neural networks approach for breast cancer diagnosis”, Artificial Intelligence in Medicine, 25(3): 265-281, (2002).
• [13] Al-Shayea, Q.K., “Artificial neural networks in medical diagnosis”, International Journal of Computer Science Issues, 8(2): 150-154, (2011).
• [14] Dhar, J. and Ranganathan, A., “Machine learning capabilities in medical diagnosis applications: Computational results for hepatitis disease”, International Journal of Biomedical Eng and Tech, 17(4): 330-340, (2015).
• [15] Botero-Rosas, D., Leon-A,J., Reina, J.M., Obando, A. and Bastidas, A.R., “Use of artificial ıntelligence in the diagnosis of chronic obstructive pulmonary disease (COPD)”, Am. J. Respir. Crit. Care. Med., 191, (2015).
• [16] Thong, N.T., “HIFCF: An effective hybrid model between picture fuzzy clustering and intuitionistic fuzzy recommender systems for medical diagnosis”, Expert Systems with Applications, 42(7): 3682-3701, (2015).
• [17] Faris, H., Hassonah, M.A., Ala’M, A.Z., Mirjalili, S. and Aljarah, I., “A multi-verse optimizer approach for feature selection and optimizing SVM parameters based on a robust system architecture”, Neural Computing and Applications, 1-15, (2017).
• [18] Das, S.P. and Padhy, S., “A novel hybrid model using teaching–learning-based optimization and a support vector machine for commodity futures index forecasting”, International Journal of Machine Learning and Cybernetics, 9(1): 97-111, (2018).
• [19] Pradhan, B., Jebur, M.N. and Abdullahi, S., “Spatial Prediction of Landslides Along Jalan Kota in Bandar Seri Begawan (Brunei) Using Airborne LiDAR Data and Support Vector Machine”. In Laser Scanning Applications in Landslide Assessment, 167-178: Springer, Cham, (2017).
• [20] Ling, X., Feng, X., Chen, Z., Xu, Y. and Zheng, H., “Short-term traffic flow prediction with optimized Multi-kernel Support Vector Machine”. In Evolutionary Computation (CEC), 2017 IEEE Congress on, 294-300: IEEE, (2017).
• [21] Tharwat, A. and Hassanien, A.E., “Chaotic antlion algorithm for parameter optimization of support vector machine”, Applied Intelligence, 48(3): 670-686, (2018).
• [22] Frank, A. and Asuncion, A., “UCI Machine Learning Repository”, University of California Irvine, School of Information and Computer Science, http://archive.ics.uci.edu/ml, [Erişim: 11.01.2018], (2010).
• [23] Turney, P., “Pima Indians Diabetes Data Set”, UCI M.L. Repository. Originally from: National Ins. of Diabetes and Digestive and Kidney Diseases, https://archive.ics.uci.edu/ml/datasets/pima+indians+diabetes, [Erişim: 11.01.2018], (1990; updated: 2011).
• [24] Çomak, E., Arslan, A. and Türkoğlu, İ., “A decision support system based on support machines for diagnosis of the heart valve diseases”, Computers in Biology and Medicine, 37: 21-27, (2007).
• [25] Vapnik, V., Golowich, S. and Smola, A., “Support vector method for function approximation, regression estimation, and signal processing”, Advances in Neural Information Processing Systems, 9: 281–287, (1997).
• [26] Akşehirli, Ö.Y., Ankaralı, H., Aydın, D. and Saraçlı, Ö., “Tıbbi tahminde alternatif bir yaklaşım: Destek vektör makineleri”, Turkiye Klinikleri Journal of Biostatistics, 5(1), (2013).
• [27] Chung, S.S. and Zhang, S., “Volatility estimation using support vector machine: Applications to major foreign exchange rates”, Electronic Journal of Applied Statistical Analysis, 10(2): 499-511, (2017).
• [28] Güner, N. and Çomak, E., “Mühendislik öğrencilerinin matematik I derslerindeki başarısının destek vektör makineleri kullanılarak tahmin edilmesi”, Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 17(2): 87-96, (2011).
• [29] Rastogi, R., Sharma, S. and Chandra, S., “Robust parametric twin support vector machine for pattern classification”, Neural Processing Letters, 1-31, (2017).
• [30] Kavzoğlu, T. and Çölkesen, İ., “Destek vektör makineleri ile uydu görüntülerinin sınıflandırılmasında kernel fonksiyonlarının etkilerinin incelenmesi”, Harita Dergisi, 144(7): 73-82, (2010).
• [31] Hasni, H., Alavi, A.H., Jiao, P. and Lajnef, N., “Detection of fatigue cracking in steel bridge girders: a support vector machine approach”, Archives of Civil and Mechanical Engineering, 17(3): 609-622, (2017).
• [32] Tamura, H. and Tanno, K., “Midpoint validation method for support vector machines with margin adjustment technique”, International Journal of Innovative Computing, Information and Control, 5: 4025-4032, (2009).
• [33] Çomak, E., “Destek Vektör Makineleri Çoklu Sınıf Problemleri için Çözüm Önerileri”, Yüksek Lisans Tezi, Selçuk Üniversitesi Fen Bilimleri Enstitüsü, Bilgisayar Mühendisliği ABD., (2004).
• [34] Özkaya, A.U., Kaya, M.E. and Gürgen, F. “Destek Vektör Makineleri Kullanılarak Aritmi Sınıflandırması”. Biyomedikal Müh. Ulusal Toplantısı, (2005).
• [35] Karaç, E.I., “Model Selection for Multi-Class Support Vector Machines”, Yüksek Lisans Tezi, Boğaziçi Üniversitesi Fen Bilimleri Enstitüsü, Bilgisayar Mühendisliği ABD., (2005).
• [36] Özkan, Y., “Veri Madenciliği Yöntemleri”, Papatya Yayıncılık, (2008).
• [37] Özkaya, A.U., “Intelligent Arrhythmia Classification Based on Support Vector Machines”, Yüksek Lisans Tezi, İstanbul Teknik Üniversitesi Fen Bilimleri Enstitüsü, Bilgisayar Mühendisliği Bölümü, (2003).
• [38] Köse, U., “Yapay Zekâ Tabanlı Optimizasyon Algoritmaları Geliştirilmesi”, Doktora Tezi, Selçuk Üniversitesi, Fen Bilimleri Enstitüsü, Bilgisayar Mühendisliği ABD., (2017).
• [39] Karaboğa, D., “Yapay Zekâ Optimizasyon Algoritmaları”, Ankara, Nobel Akademik Yayıncılık, (2014).
• [40] Yang, X.-S., “Nature-Inspired Metaheuristic Algorithms”, Luniver Press, (2010).
• [41] Yang, X.-S., Cui, Z., Xiao, R., Gandomi, A.H. and Karamanoglu, M., “Swarm Intelligence and Bio-Inspired Computation: Theory and Applications”, Newnes, (2013).
• [42] Hassanien, A.E. and Emary, E., “Swarm Intelligence: Principles, Advances, and Applications”, CRC Press, (2016).
• [43] Eberhart, R. and Kennedy, J., “A new optimizer using particle swarm theory”, Micro Machine and Human Science, 1995. MHS'95., Proceedings of the Sixth International Symposium on, 39-43, (1995).
• [44] Shi, Y. and Eberhart, R., “A modified particle swarm optimizer”, Evolutionary Computation Proceedings, 1998. IEEE World Congress on Computational Intelligence., The 1998 IEEE International Conference on, 69-73, (1998).
• [45] Kennedy, J., “Particle Swarm Optimization”, In: Encyclopedia of Machine Learning, Eds: Springer, 760-766, (2011).
• [46] Back, T., “Evolutionary Algorithms in Theory and Practice: Evolution Strategies, Evolutionary Programming”, Genetic Algorithms, Oxford University Press, (1996).
• [47] Goldberg, D.E., “Genetic Algorithms”, Pearson Education India, (2006).
• [48] Holland, J.H., “Genetic algorithms”, Scholarpedia, 7(12): 1482, http://www.scholarpedia.org/article/Genetic_algorithms, [Erişim: 20.01.2018], (2012).
• [49] Yang, X.-S. and Deb, S., “Cuckoo search via Lévy flights”, Nature & Biologically Inspired Computing, 2009. NaBIC 2009. World Congress on, 210-214, (2009).
• [50] Mandelbrot, B.B., “The Fractal Geometry of Nature”, New York, W. H. Freeman, (1982).
• [51] Yang, X.-S. and Deb, S., “Engineering optimisation by cuckoo search”, International Journal of Mathematical Modelling and Numerical Optimisation, 1(4): 330-343, (2010).
• [52] Passino, K.M., “Biomimicry of bacterial foraging for distributed optimization and control”, IEEE Control Systems, 22(3): 52-67, (2002).
• [53] Passino, K.M., “Bacterial foraging optimization”, Innovations and Developments of Swarm Intelligence Applications, 219-233, (2012).
• [54] Gazi, V. and Passino, K.M., “Bacteria Foraging Optimization”, In: Swarm Stability and Optimization, Eds: Springer, 233-249, (2011).
• [55] Yang, X.-S., “Flower Pollination Algorithm for Global Optimization”, International Conference on Unconventional Computing and Natural Computation, 240-249, (2012).
• [56] Yang, X.-S., Karamanoglu, M. and He, X., “Flower pollination algorithm: A novel approach for multiobjective optimization”, Engineering Optimization, 46(9): 1222-1237, (2014).