K-Ortalama Kümelerinin Sınıf Bilgisi Olarak Karar Ağacı Oluşturmada Kullanılması ve Glokom Çoklu Sınıflandırılmasında Başarıma Etkisi

Abstract

Bu çalışma çoklu sınıflandırmada performans artırımı için K-Ortalama ve Karar Ağacı yöntemlerinden oluşan bir model sunmaktadır. Model glukom veri kümesi üzerinde test edilmiş  kesinlik ölçütü 0,808, ROC alanı 0,839 bulunmuştur.

Keywords

• Veri Madencliği
• Sınıflama
• Kümeleme
• K-Ortalama
• Karar Ağacı

Usage Of K-Means Clusters as Class Labes In Decısıon Trees and Its Effect On Multıclassıfıcatıon Performance Of Glaucoma

Abstract

In this study a model of K-Means - Decision Tree is presented to increase the multiclassification performance. This model is tested on glaucoma dataset, the accuracy and the are under ROC curve is calculated as 0.808, 0.839 respectively.

Keywords

• Data Mining
• Classification
• Clustering
• K-Means
• Decision Tree

References

1. E.S. Berner, Clinical Decision Support Systems: State of the Art. AHRQ Publication, Rockville, MD (2009).
2. E. Coiera, Clinical Decision Support Systems: Guide to Health Informatics. 3rd Edition, CRC
3. Press, (2003)
4. Sen, Arun et al. Journal of Biomedical Informatics 45(5)(2012)1009–1017.
5. A. Satyanandam et al. International Journal of Computer & Organization
6. Trends.2(3)(2012)53-60
7. I. Kononenko Artificial Intelligence in Medicine 23(1)(2001)89–109
8. M. You et al. Int J Data Min Bioinform. 5(4)(2011)383-401.

9. N. Mehra, S. Grupta International Journal of Computer Science and Information
10. Technologies 4(4)(2013)572 – 576
11. G. Tsoumakas, I. Katakis Data Warehousing and Mining: Concepts, Methodologies, Tools,
12. and Applications,6. Baskı, IGI Global, (2008)
13. B.M. Shahshahani, D.A. Landgrebe. Geoscience and Remote Sensing 32(5)(1994)1087 – 1095
14. S.W. Kim, R.P.W. Duin, On Improving Dissimilarity-Based Classifications Using a Statistical Similarity Measure, 15th Iberoamerican Congress on Pattern Recognition, Sao Paulo – Brazil,
15. (2010) 418–425
16. Savini et al. Current Opinion in Ophthalmology 22 (2)(2011)115–123
17. Y. Burnstein et al. American Journal of Ophthalmology 129(3)(2000)328–333
18. L. Churilov et al. Journal of Management Information Systems 21(4)(2005)85-100
19. X. Wu et al. Knowl. Inf. Syst. 14(1)(2008):1-37
20. M. Bramer, Principles of data mining, 1st Ed., Springer-Verlag, (2007)
21. Anonim,
22. http://www.academia.edu/4857097/Integrating_Clustering_with_Different_Data_Mining_Techniques_in_the_Diagnosis_of_Heart_Disease (Erişim tarihi: 17th of January, 2015)
23. N.S. Nithya et al. International Journal of Computer Science Trends and Technology
24. (2)(2013)17-23
25. P. Filipczuk et al. Image Processing and Communications Challenges, 3. Baskı, Springer,
26. (2011)
27. U. Orhan et al. Expert Systems with Applications 38(10)(2011)13475–13481.
28. J. Demsar et al. Journal of Machine Learning Research 14(2013)2349-2353.
29. P. Rousseeuw et al. Journal of Statistical Software 1(4)(1996)1-30.
30. A.T. Azar et al. Neural Computing and Applications 23(7)(2013)2387-2403.
31. J.C. Mwanza et al. Ophthalmology 119(6)(2012)1151–1158.
32. O. Tan et al. Ophthalmology 116(12)(2009)2305–2314.
33. R. Sihota et al. Invest Ophthalmol Vis Sci 47(5)(2006)2006-2010.
34. Z. Yang et al. PLoS ONE 10(5)(2015)e0125957.
35. C. Bowd, M.H.Goldbaum Optometry & Vision Science 85(6)(2008) 396–405.