Eigenclassifiers for combining correlated classifiers
Yükleniyor...
Dosyalar
Tarih
2012-03-15
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Elsevier Science Inc
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
In practice, classifiers in an ensemble are not independent. This paper is the continuation of our previous work on ensemble subset selection [A. Ulas, M. Semerci, O.T. Yildiz, E. Alpaydin, Incremental construction of classifier and discriminant ensembles, Information Sciences, 179 (9) (2009) 1298-1318] and has two parts: first, we investigate the effect of four factors on correlation: (i) algorithms used for training, (ii) hyperparameters of the algorithms, (iii) resampled training sets, (iv) input feature subsets. Simulations using 14 classifiers on 38 data sets indicate that hyperparameters and overlapping training sets have higher effect on positive correlation than features and algorithms. Second, we propose postprocessing before fusing using principal component analysis (PCA) to form uncorrelated eigenclassifiers from a set of correlated experts. Combining the information from all classifiers may be better than subset selection where some base classifiers are pruned before combination, because using all allows redundancy.
Açıklama
Anahtar Kelimeler
Classifier correlation, Classifier design and evaluation, Machine learning, Stacked generalization, Principal components, Ensemble, Systems, Algorithms, Base classifiers, Data sets, Hyperparameters, Incremental construction, Input features, Machine-learning, Positive correlations, Subset selection, Training sets, Principal component analysis, Classification (of information)
Kaynak
Information Sciences
WoS Q Değeri
N/A
Scopus Q Değeri
Q1
Cilt
187
Sayı
1
Künye
Ulaş, A. & Yıldız, O. T. & Alpaydın, A. İ. E. (2012). Eigenclassifiers for combining correlated classifiers. Information Sciences, 187(1), 109-120. doi:10.1016/j.ins.2011.10.024
