Preface

Japkowicz, Nathalie; Shah, Mohak

doi:10.1017/cbo9780511921803.001

Cited by 67 publications

(89 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For their definitions see, e.g. [8,10]. They are estimated in stratified 10-fold cross-validation repeated several times to reduce variance.…”

Section: Methodsmentioning

confidence: 99%

“…The average values of the sensitivity measure are presented in Table 1. The last row contains averaged ranks calculated as in the Friedman test [10]. The test with post-hoc analysis (the critical difference CD = 1.61) shows that EBBag and RBBag leads to significantly better sensitivity than all other bagging variants.…”

Section: Comparison Of Known Bagging Extensionmentioning

confidence: 99%

See 1 more Smart Citation

Extending Bagging for Imbalanced Data

Błaszczyński

Stefanowski

Idkowiak

2013

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Various modifications of bagging for class imbalanced data are discussed. An experimental comparison of known bagging modifications shows that integrating with undersampling is more powerful than oversampling. We introduce Local-and-Over-All Balanced bagging where probability of sampling an example is tuned according to the class distribution inside its neighbourhood. Experiments indicate that this proposal is competitive to best undersampling bagging extensions.

show abstract

“…For their definitions see, e.g. [8,10]. They are estimated in stratified 10-fold cross-validation repeated several times to reduce variance.…”

Section: Methodsmentioning

confidence: 99%

Section: Comparison Of Known Bagging Extensionmentioning

confidence: 99%

Extending Bagging for Imbalanced Data

Błaszczyński

Stefanowski

Idkowiak

2013

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

show abstract

“…The Wilcoxon signed-rand test is a nonparametric pairwise comparison test with the assumption that the distribution of the difference scores is symmetric about the median. 28 The lower-sided Wilcoxon test is performed with the null hypothesis that the median of the difference scores of the compared two variables is equal to zero, while the alternative hypothesis that the median is less than zero, where the …”

Section: Statistical Significance Testingmentioning

confidence: 99%

“…The generalization loss 28 at epoch t is defined as the relative increase of the validation error over the minimum so far (in percentage):…”

Section: Appendix a Definitions And Stopping Criteriamentioning

confidence: 99%

Neural Incremental Attribute Learning in Groups

Liu¹,

Wang²,

Guan³

et al. 2015

IJCIS

View full text Add to dashboard Cite

Incremental Attribute Learning (IAL) is a feasible approach for solving high-dimensional pattern recognition problems. It gradually trains features one by one. Previous research indicated that supervised machine learning with input attribute ordering can improve classification results. Moreover, input space partitioning can also effectively reduce the interference among features. This study proposed IAL based on Grouped Feature Ordering, which fused feature partitioning with feature ordering. The experimental results show that this approach is not only applicable for pattern classification improvement, but also efficient to reduce interference among features.

show abstract

“…They were obtained using a k-fold cross-validation strategy (k 5) over the training set. The figure of merit used for the assessment of the classification quality (over the test set) is the Overall Accuracy measure, defined as the total number of correctly classified samples divided by the total number of test samples [24].…”

mentioning

confidence: 99%