Eta Correlation Coefficient Based Feature Selection Algorithm for Machine Learning: E-Score Feature Selection Algorithm

UÇAR, Muhammed Kürşad

Eta Correlation Coefficient Based Feature Selection Algorithm for Machine Learning: E-Score Feature Selection Algorithm

Muhammed Kürşad UÇAR (Sakarya Üniversitesi, Mühendislik Fakültesi, Elektrik Elektronik Mühendisliği, Sakarya, Türkiye)

Zeki sistemler teori ve uygulamaları dergisi (Online)

10 0

Yıl: 2019 Cilt: 2 Sayı: 1 Sayfa Aralığı: 7 - 12 Metin Dili: İngilizce İndeks Tarihi: 12-10-2020

Eta Correlation Coefficient Based Feature Selection Algorithm for Machine Learning: E-Score Feature Selection Algorithm

Öz:

Feature selection algorithms are great importance in the field of machine learning. The primary function of feature selection algorithmsis to select features in a meaningful way. Features Selection Algorithms methods are still being developed today. The reason for this isthat data quantities are growing day by day. As the data increases, more advanced, better performance, feature selection algorithms areneeded. In this study, Eta Correlation Coefficient based E-Score Feature selection algorithm was developed. Two versions wereprepared for E-Score. We tested the performance of the E-Score method with three classifiers and compared with conventional F-ScoreFeature Selection Algorithm. According to the results, both versions of the E-Score feature selection algorithm have improvedperformance and is better than the F-Score. According to these results, it is thought that the E-Score Feature Selection Algorithm canbe used in the field of machine learning.

Anahtar Kelime:

Makine Öğrenmesi için Eta Korelasyon Katsayısı Tabanlı Özellik Seçme Algoritması: E-Score Özellik Seçme Algoritması

Öz:

Makine öğrenmesi alanında özellik seçme algoritmaları büyük öneme sahiptir. Çok büyük verilerin anlamlı bir şekilde azaltılması özellik seçme algoritmalarının temel işlevidir. Bu yöntemler günümüzde hala geliştirilmeye devam etmektedir. Bunun sebebi her geçen gün daha büyük verilerle çalışıyor olmasıdır. Veriler arttıkça daha gelişmiş, performansı daha iyi özellik seçme algoritmalarına ihtiyaç duyulacaktır. Bu çalışmada Eta Korelasyon Katsayısı tabanlı E-Score Özellik seçme algoritması geliştirilmiştir. Geliştirilen yöntem için iki farklı versiyon hazırlanmıştır. E-Score yönteminin performansı üç sınıflandırıcı ile test edilmiştir. Ayrıca literatürde bulunan F-Score Özellik Seçme Algoritması ile de kıyaslanmıştır. Elde edilen sonuçlara göre E-Score özellik seçme algoritmasının her iki versiyonu da performansı arttırmıştır. Ayrıca F-Score ile kıyaslandığında daha iyi başarı oranı elde etmiştir. Bu sonuçlara E-Score Özellik Seçme Algoritmasının makine öğrenmesi alanında kullanılabileceği düşünülmektedir.

Anahtar Kelime:

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

Alpar, R. (2010) Applied Statistic and Validation - Reliability. Detay Publishing. Available at: https://books.google.com.tr/books/about/Uygulamalı_ista tistik_ve_geçerlik_güv.html?id=ITk1MwEACAAJ&pgis =1 (Accessed: 11 January 2016).
Andrzejak, R. G. et al. (2001) ‘Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: Dependence on recording region and brain state’, Physical Review E - Statistical Physics, Plasmas, Fluids, and Related Interdisciplinary Topics, 64(6), p. 8. doi: 10.1103/PhysRevE.64.061907.
Andrzejak RG, Lehnertz K, Rieke C, Mormann F, David P, E. C. (2001) UCI Machine Learning Repository: Epileptic Seizure Recognition Data Set, UCI. Available at: https://archive.ics.uci.edu/ml/datasets/Epileptic+Seizure+ Recognition (Accessed: 14 August 2018).
Cai, J. et al. (2018) ‘Feature selection in machine learning: A new perspective’, Neurocomputing. Elsevier, 300, pp. 70– 79. doi: 10.1016/J.NEUCOM.2017.11.077.
Elghazel, H. and Aussem, A. (2015) ‘Unsupervised feature selection with ensemble learning’, Machine Learning. Springer US, 98(1–2), pp. 157–180. doi: 10.1007/s10994- 013-5337-8.
Goltsev, A. and Gritsenko, V. (2012) ‘Investigation of efficient features for image recognition by neural networks’, Neural Networks. Pergamon, 28, pp. 15–23. doi: 10.1016/J.NEUNET.2011.12.002.
Guan, D. et al. (2014) ‘A Review of Ensemble Learning Based Feature Selection’, IETE Technical Review, 31(3), pp. 190–198. doi: 10.1080/02564602.2014.906859.
Huang, D.-S. (1999) ‘Radial Basis Probabilistic Neural Networks: Model and Application’, International Journal of Pattern Recognition and Artificial Intelligence. World Scientific Publishing Company, 13(07), pp. 1083–1101. doi: 10.1142/S0218001499000604.
Kavsaoğlu, A. R., Polat, K. and Bozkurt, M. R. (2014) ‘A novel feature ranking algorithm for biometric recognition with PPG signals.’, Computers in biology and medicine, 49, pp. 1–14. doi: 10.1016/j.compbiomed.2014.03.005.
Khoshgoftaar, T. et al. (2012) ‘First Order Statistics Based Feature Selection: A Diverse and Powerful Family of Feature Seleciton Techniques’, in 2012 11th International Conference on Machine Learning and Applications. IEEE, pp. 151–157. doi: 10.1109/ICMLA.2012.192.
Khotanzad, A. and Hong, Y. H. (1990) ‘Rotation invariant image recognition using features selected via a systematic method’, Pattern Recognition. Pergamon, 23(10), pp. 1089–1101. doi: 10.1016/0031-3203(90)90005-6.
Koch, R. (2014) The 80/20 Principle and 92 Other Powerful Laws of Nature: The Science of Success. Available at: https://www.amazon.com/80-20-Principle-SecretAchieving/dp/1486213421 (Accessed: 23 September 2018).
Li, Y., Gao, S.-Y. and Chen, S. (2012) ‘Ensemble Feature Weighting Based on Local Learning and Diversity’, AAAI. Available at: https://www.semanticscholar.org/paper/EnsembleFeature-Weighting-Based-on-Local-Learning-LiGao/733e4973aec6d9de139781a76ca2f6b3f05b293b (Accessed: 24 September 2018).
Polat, K. and Güneş, S. (2009) ‘A new feature selection method on classification of medical datasets: Kernel Fscore feature selection’, Expert Systems with Applications, 36(7), pp. 10367–10373. doi: 10.1016/j.eswa.2009.01.041.
Tsang-Hsiang Cheng, Chih-Ping Wei and Tseng, V. S. (2006) ‘Feature Selection for Medical Data Mining: Comparisons of Expert Judgment and Automatic Approaches’, in 19th IEEE Symposium on Computer-Based Medical Systems (CBMS’06). IEEE, pp. 165–170. doi: 10.1109/CBMS.2006.87.

APA	UÇAR M (2019). Eta Correlation Coefficient Based Feature Selection Algorithm for Machine Learning: E-Score Feature Selection Algorithm. , 7 - 12.
Chicago	UÇAR Muhammed Kürşad Eta Correlation Coefficient Based Feature Selection Algorithm for Machine Learning: E-Score Feature Selection Algorithm. (2019): 7 - 12.
MLA	UÇAR Muhammed Kürşad Eta Correlation Coefficient Based Feature Selection Algorithm for Machine Learning: E-Score Feature Selection Algorithm. , 2019, ss.7 - 12.
AMA	UÇAR M Eta Correlation Coefficient Based Feature Selection Algorithm for Machine Learning: E-Score Feature Selection Algorithm. . 2019; 7 - 12.
Vancouver	UÇAR M Eta Correlation Coefficient Based Feature Selection Algorithm for Machine Learning: E-Score Feature Selection Algorithm. . 2019; 7 - 12.
IEEE	UÇAR M "Eta Correlation Coefficient Based Feature Selection Algorithm for Machine Learning: E-Score Feature Selection Algorithm." , ss.7 - 12, 2019.
ISNAD	UÇAR, Muhammed Kürşad. "Eta Correlation Coefficient Based Feature Selection Algorithm for Machine Learning: E-Score Feature Selection Algorithm". (2019), 7-12.

APA	UÇAR M (2019). Eta Correlation Coefficient Based Feature Selection Algorithm for Machine Learning: E-Score Feature Selection Algorithm. Zeki sistemler teori ve uygulamaları dergisi (Online), 2(1), 7 - 12.
Chicago	UÇAR Muhammed Kürşad Eta Correlation Coefficient Based Feature Selection Algorithm for Machine Learning: E-Score Feature Selection Algorithm. Zeki sistemler teori ve uygulamaları dergisi (Online) 2, no.1 (2019): 7 - 12.
MLA	UÇAR Muhammed Kürşad Eta Correlation Coefficient Based Feature Selection Algorithm for Machine Learning: E-Score Feature Selection Algorithm. Zeki sistemler teori ve uygulamaları dergisi (Online), vol.2, no.1, 2019, ss.7 - 12.
AMA	UÇAR M Eta Correlation Coefficient Based Feature Selection Algorithm for Machine Learning: E-Score Feature Selection Algorithm. Zeki sistemler teori ve uygulamaları dergisi (Online). 2019; 2(1): 7 - 12.
Vancouver	UÇAR M Eta Correlation Coefficient Based Feature Selection Algorithm for Machine Learning: E-Score Feature Selection Algorithm. Zeki sistemler teori ve uygulamaları dergisi (Online). 2019; 2(1): 7 - 12.
IEEE	UÇAR M "Eta Correlation Coefficient Based Feature Selection Algorithm for Machine Learning: E-Score Feature Selection Algorithm." Zeki sistemler teori ve uygulamaları dergisi (Online), 2, ss.7 - 12, 2019.
ISNAD	UÇAR, Muhammed Kürşad. "Eta Correlation Coefficient Based Feature Selection Algorithm for Machine Learning: E-Score Feature Selection Algorithm". Zeki sistemler teori ve uygulamaları dergisi (Online) 2/1 (2019), 7-12.