ÖZNİTELİKLER ARASI KORELASYONUN DÜŞÜK OLDUĞU VERİ KÜMELERİNDE SINIFLANDIRMA BAŞARISINI ARTIRMAK İÇİN YOĞUNLUK TEMELLİ ÖZNİTELİK OLUŞTURMA
Abstract
Veri kümesinde, sınıfları aynı olan öznitelikler (özellikler) arasındaki korelasyon düşük ise sınıflandırma yöntemlerinin başarı oranı da düşük olacaktır. Bu çalışmanın amacı bu tip veri kümelerinde sınıflandırıcıların başarı oranını yükseltmektir. Çalışmada veri kümesinin özniteliklerindeki veriler, öncelikle yoğunluk katsayılarına dönüştürülmüştür. Böylece öznitelikler arasında daha yüksek korelasyon bulunan yeni veri kümeleri oluşturulmuştur. Ardından bu yeni veri kümesinin asıl veri kümesinin yapısına göre sınıflandırmaya ne kadar katkıda bulunduğu değerlendirilmiştir. Değerlendirme işlemi için hem gerçek veri kümelerine hem de önerilen yöntem sayesinde oluşturulan yeni veri kümelerine çeşitli sınıflandırma yöntemleri uygulanmıştır. Sınıflandırma sonuçları karşılaştırıldığında, önerilen yöntemin sınıflandırıcıların başarı oranına yaklaşık % 18 oranda katkıda bulunduğu gözlemlenmiştir.
References
- Kenzie, G.M. ve Peng, D., Statistical Modelling in Biostatistics and Bioinformatics Contributions to Statistics, Springer, 2014.
- Köklü, M., Kahramanlı, H., Allahverdi, N., “Sınıflandırma Kurallarının Çıkarımı İçin Etkin ve Hassas Yeni Bir Yaklaşım”, Gazi Üniv. Müh. Mim. Fak. Der. Journal of the Faculty of Engineering and Architecture of Gazi University, Cilt 29, No 3, 477-486, 2014.
- Hsu, H.H., Hsieh, C.W., “Feature Selection via Correlation Coefficient Clustering”, Journal of software, Cilt 5, No 12, 1371-1377, 2010.
- Deisy, C., Subbulakshmi, B., Baskar, S., Ramaraj, N., “Efficient Dimensionality Reduction Approaches for Feature Selection,” International Conference on Computational Intelligence and Multimedia Applications, 121- 127, 2007.
- Guyon, I., Nikravesh, M., Gunn, S., Zadeh, L.A., Feature Extraction Foundations and Applications, Springer Berlin Heidelberg, 2006.
- Nixon, M., Aguado, A., Feature Extraction and Image Processing, Academic Press is an Imprint of Elsevier, 2008.
- Kohavi, R., John, G., “Wrappers for Feature Subset Selection,” Artificial Intelligence, Cilt 97, 273-324, 1997.
- Quinlan, J.R., Discovering Rules from Large Collections of Examples: A Case Study, In Michie, D. ed., Expert Systems in the Microelectronic Age, Scotland: Edinburgh University Press, Edinburgh, 1979.
- Liu, Y., Yin, Y.F., Gao, J.J., Tan, C. G., “Wrapper Feature Selection Optimized SVM Model for Demand Forecasting,” The International Conference on Young Computer Scientists, 953-958, 2008.
- Qian, L., Honggang, Q., Jun, M, Wentao, Z, Guiping, S., “One-Class Classification with Extreme Learning Machine,” Mathematical Problems in Engineering, Article ID 412957, in press.
- Rodgers, J.L., Nicewander, W.A., “Thirteen ways to look at the correlation coefficient”, The American Statistician, Cilt 42, No 1, 59–66, 1988.
- Park, S., Bera, Y. Anil, K. "Maximum Entropy Autoregressive Conditional Heteroskedasticity Model", Journal of Econometrics (Elsevier), Cilt 150, No 2, 219–230, 2009.
- Frank, A., Asuncion, A., UCI Machine Learning Repository., 2014, http://www.archive.ics.uci.edu/ml
- Babich, G.A., “Weighted Parzen windows for pattern classification”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Cilt 18 No 5, 567-570, 2002.
- Wanga, S., Chungb, F., Xionga, F., “A novel image thresholding method based on Parzen window estimate”, Pattern Recognition, Cilt 41, No 1, 117-129, 2008.
- Erdogmus, D., Hild, K.E., Principe, J.C., Lazaro, M., Santamaria, I., “Adaptive Blind Deconvolution of Linear Channels Using Renyi’s Entropy with Parzen Window Estimation”, IEEE Transactions on Signal Processing, Cilt 52, No 6, 1489-1498, 2004.
- Veon, K.L. “Dept. of Electr. & Comput. Localized support vector machines using Parzen window for incomplete sets of categories”, Applications of Computer Vision (WACV), IEEE Workshop on, 448-454, 2011.
- Yuichi T., Paul, J. Choi, G.L., Huiyi C., Mohan, B., Jeremy, H., Andrew, E.X., Sunney, X, “Quantifying E. coli Proteome and Transcriptome with Single-Molecule Sensitivity in Single Cells”, Science, Cilt 329, No 5991, 533-538, 2010.
Year 2015,
Volume: 30 Issue: 4, 0 - 0, 25.12.2015
Abstract
References
- Kenzie, G.M. ve Peng, D., Statistical Modelling in Biostatistics and Bioinformatics Contributions to Statistics, Springer, 2014.
- Köklü, M., Kahramanlı, H., Allahverdi, N., “Sınıflandırma Kurallarının Çıkarımı İçin Etkin ve Hassas Yeni Bir Yaklaşım”, Gazi Üniv. Müh. Mim. Fak. Der. Journal of the Faculty of Engineering and Architecture of Gazi University, Cilt 29, No 3, 477-486, 2014.
- Hsu, H.H., Hsieh, C.W., “Feature Selection via Correlation Coefficient Clustering”, Journal of software, Cilt 5, No 12, 1371-1377, 2010.
- Deisy, C., Subbulakshmi, B., Baskar, S., Ramaraj, N., “Efficient Dimensionality Reduction Approaches for Feature Selection,” International Conference on Computational Intelligence and Multimedia Applications, 121- 127, 2007.
- Guyon, I., Nikravesh, M., Gunn, S., Zadeh, L.A., Feature Extraction Foundations and Applications, Springer Berlin Heidelberg, 2006.
- Nixon, M., Aguado, A., Feature Extraction and Image Processing, Academic Press is an Imprint of Elsevier, 2008.
- Kohavi, R., John, G., “Wrappers for Feature Subset Selection,” Artificial Intelligence, Cilt 97, 273-324, 1997.
- Quinlan, J.R., Discovering Rules from Large Collections of Examples: A Case Study, In Michie, D. ed., Expert Systems in the Microelectronic Age, Scotland: Edinburgh University Press, Edinburgh, 1979.
- Liu, Y., Yin, Y.F., Gao, J.J., Tan, C. G., “Wrapper Feature Selection Optimized SVM Model for Demand Forecasting,” The International Conference on Young Computer Scientists, 953-958, 2008.
- Qian, L., Honggang, Q., Jun, M, Wentao, Z, Guiping, S., “One-Class Classification with Extreme Learning Machine,” Mathematical Problems in Engineering, Article ID 412957, in press.
- Rodgers, J.L., Nicewander, W.A., “Thirteen ways to look at the correlation coefficient”, The American Statistician, Cilt 42, No 1, 59–66, 1988.
- Park, S., Bera, Y. Anil, K. "Maximum Entropy Autoregressive Conditional Heteroskedasticity Model", Journal of Econometrics (Elsevier), Cilt 150, No 2, 219–230, 2009.
- Frank, A., Asuncion, A., UCI Machine Learning Repository., 2014, http://www.archive.ics.uci.edu/ml
- Babich, G.A., “Weighted Parzen windows for pattern classification”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Cilt 18 No 5, 567-570, 2002.
- Wanga, S., Chungb, F., Xionga, F., “A novel image thresholding method based on Parzen window estimate”, Pattern Recognition, Cilt 41, No 1, 117-129, 2008.
- Erdogmus, D., Hild, K.E., Principe, J.C., Lazaro, M., Santamaria, I., “Adaptive Blind Deconvolution of Linear Channels Using Renyi’s Entropy with Parzen Window Estimation”, IEEE Transactions on Signal Processing, Cilt 52, No 6, 1489-1498, 2004.
- Veon, K.L. “Dept. of Electr. & Comput. Localized support vector machines using Parzen window for incomplete sets of categories”, Applications of Computer Vision (WACV), IEEE Workshop on, 448-454, 2011.
- Yuichi T., Paul, J. Choi, G.L., Huiyi C., Mohan, B., Jeremy, H., Andrew, E.X., Sunney, X, “Quantifying E. coli Proteome and Transcriptome with Single-Molecule Sensitivity in Single Cells”, Science, Cilt 329, No 5991, 533-538, 2010.
There are 18 citations in total.
Details
| Journal Section | Makaleler |
|---|---|
| Authors | |
| Publication Date | December 25, 2015 |
| Submission Date | January 12, 2015 |
| Published in Issue | Year 2015 Volume: 30 Issue: 4 |