Feature Selection for Data and Pattern Recognition: An Introduction

Stańczyk, Urszula; Jain, Lakhmi C.

doi:10.1007/978-3-662-45620-0_1

Cited by 46 publications

(53 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A detailed discussion of feature filters and wrappers can be easily found in literature [3,4]. When the expert knowledge is available it can be used to make some preliminary feature selection [5,6].…”

Section: Feature Selection Before Network Learningmentioning

confidence: 99%

Data Selection for Neural Networks

Kordos

2017

View full text Add to dashboard Cite

Abstract. Several approaches to joined feature and instance selection in neural network leaning are discussed and experimentally evaluated in respect to classification accuracy and dataset compression, considering also their computational complexity. These include various versions of feature and instance selection prior to the network learning, the selection embedded in the neural network and hybrid approaches, including solutions developed by us. The advantages and disadvantages of each approach are discussed and some possible improvements are proposed.

show abstract

Section: Feature Selection Before Network Learningmentioning

confidence: 99%

Data Selection for Neural Networks

Kordos

2017

View full text Add to dashboard Cite

show abstract

“…Bu yöntemde, başlangıç öznitelik kümesi boş küme seçilmekte ve sırasıyla öznitellikler eklendikçe kriter değeri hesaplanmaktadır [6]. Bu yöntemde ilk seçilen en önemli öznitelik olmaktadır.…”

Section: 1 Sıralı İleri Seçim (Si̇s) (Sequential Forward Selection-sfs)unclassified

“…Ayrık Fourier Dönüşümü (AFD), Kısa Zamanlı Fourier Dönüşümü (KZFD), Dalgacık Dönüşümü (DD), Stockwell Dönüşümü (SD), Hilbert Dönüşümü (HD) ve Gabor Dönüşümü (GD) [4,5] gibi sinyal işleme yöntemleri GK bozulmalarından özniteliklerin çıkartılması için kullanılmaktadır. Sınıflandırma aşamasında oluşturulacak modelin karmaşıklığını azaltmak ve sınıflandırma başarımını yükseltmek amacıyla çıkartılan özniteliklerden en uygun olanları seçilmektedir [5,6]. Makine öğrenmesinde filtreleme ve sarmalama gibi öznitelik seçme yaklaşımları mevcuttur [7].…”

Section: Gi̇ri̇ş (Introduction)unclassified

“…Literatürde Bilgi Kazancı, Ki-Kare, ReliefF, F-Skor gibi filtreleme yöntemleri ile Sıralı İleri Seçim (SİS), Sıralı Geri Seçim (SGS), Genetik Algoritma (GA), Parçacık Sürü Optimizasyonu (PSO), Karınca Koloni Optimizasyonu (KKO) gibi sarmalama tabanlı öznitelik seçme yöntemleri bulunmaktadır [5][6][7]. Karar Ağaçları (KA), Naive Bayes (NB), k-En Yakın Komşu (k-EYK), Destek Vektör Makineleri (DVM), Yapay Sinir Ağları (YSA) [18], Hibrid ve Kolektif Öğrenme yaklaşımları gibi sınıflandırma yöntemleri mevcuttur [8,9].…”

Section: Gi̇ri̇ş (Introduction)unclassified

See 1 more Smart Citation

Güç Kalitesi Bozulmalarının 2 Boyutlu Ayrık Dalgacık Dönüşümü ve Torbalama Karar Ağaçları Yöntemi ile Sınıflandırılması

Karasu¹,

Saraç²

2018

Journal of Polytechnic

View full text Add to dashboard Cite

“…Hence, no feature selection method that terminates in a reasonable amount of time performs optimally in all situations (Kohavi and John, 1997;Bolón-Canedo et al, 2015). It is, therefore, not surprising that an immense and ever growing number of different heuristic strategies exist (Bolón-Canedo et al, 2015;Stańczyk and Jain, 2015), so many in fact that it makes choosing one of them difficult since it requires a relatively deep understanding not only of the mechanism of available feature selection methods, but also and in particular, the functionality of the underlying classifier.…”

Section: Previous Workmentioning

confidence: 99%

Variable Selection for Road Segmentation in Aerial Images

Warnke

Bulatov

2017

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:For extraction of road pixels from combined image and elevation data, Wegner et al. (2015) proposed classification of superpixels into road and non-road, after which a refinement of the classification results using minimum cost paths and non-local optimization methods took place. We believed that the variable set used for classification was to a certain extent suboptimal, because many variables were redundant while several features known as useful in Photogrammetry and Remote Sensing are missed. This motivated us to implement a variable selection approach which builds a model for classification using portions of training data and subsets of features, evaluates this model, updates the feature set, and terminates when a stopping criterion is satisfied. The choice of classifier is flexible; however, we tested the approach with Logistic Regression and Random Forests, and taylored the evaluation module to the chosen classifier. To guarantee a fair comparison, we kept the segment-based approach and most of the variables from the related work, but we extended them by additional, mostly higher-level features. Applying these superior features, removing the redundant ones, as well as using more accurately acquired 3D data allowed to keep stable or even to reduce the misclassification error in a challenging dataset.

show abstract

Feature Selection for Data and Pattern Recognition: An Introduction

Cited by 46 publications

References 17 publications

Data Selection for Neural Networks

Data Selection for Neural Networks

Güç Kalitesi Bozulmalarının 2 Boyutlu Ayrık Dalgacık Dönüşümü ve Torbalama Karar Ağaçları Yöntemi ile Sınıflandırılması

Variable Selection for Road Segmentation in Aerial Images

Contact Info

Product

Resources

About