English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Despite being very effective in several classification tasks, DynamicEnsemble Selection (DES) techniques can select classifiers that classify allsamples in the region of competence as being from the same class. The FrienemyIndecision REgion DES (FIRE-DES) tackles this problem by pre-selectingclassifiers that correctly classify at least one pair of samples from differentclasses in the region of competence of the test sample. However, FIRE-DESapplies the pre-selection for the classification of a test sample if and onlyif its region of competence is composed of samples from different classes(indecision region), even though this criterion is not reliable for determiningif a test sample is located close to the borders of classes (true indecisionregion) when the region of competence is obtained using classical nearestneighbors approach. Because of that, FIRE-DES mistakes noisy regions for trueindecision regions, leading to the pre-selection of incompetent classifiers,and mistakes true indecision regions for safe regions, leaving samples in suchregions without any pre-selection. To tackle these issues, we propose theFIRE-DES++, an enhanced FIRE-DES that removes noise and reduces the overlap ofclasses in the validation set; and defines the region of competence using anequal number of samples of each class, avoiding selecting a region ofcompetence with samples of a single class. Experiments are conducted usingFIRE-DES++ with 8 different dynamic selection techniques on 64 classificationdatasets. Experimental results show that FIRE-DES++ increases theclassification performance of all DES techniques considered in this work,outperforming FIRE-DES with 7 out of the 8 DES techniques, and outperformingstate-of-the-art DES frameworks.

FIRE-DES++: Enhanced Online Pruning of Base Classifiers for Dynamic Ensemble Selection