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/

Global: Zendy Plus annual

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

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Data Science and Machine Learning have become fundamental assets forcompanies and research institutions alike. As one of its fields, supervisedclassification allows for class prediction of new samples, learning from giventraining data. However, some properties can cause datasets to be problematic toclassify.  In order to evaluate a dataset a priori, data complexity metrics have beenused extensively. They provide information regarding different intrinsiccharacteristics of the data, which serve to evaluate classifier compatibilityand a course of action that improves performance. However, most complexitymetrics focus on just one characteristic of the data, which can be insufficientto properly evaluate the dataset towards the classifiers' performance. In fact,class overlap, a very detrimental feature for the classification process(especially when imbalance among class labels is also present) is hard toassess.  This research work focuses on revisiting complexity metrics based on datamorphology. In accordance to their nature, the premise is that they provideboth good estimates for class overlap, and great correlations with theclassification performance. For that purpose, a novel family of metrics havebeen developed. Being based on ball coverage by classes, they are named afterOverlap Number of Balls. Finally, some prospects for the adaptation of theformer family of metrics to singular (more complex) problems are discussed.

knowledge and information systems

Revisiting Data Complexity Metrics Based on Morphology for Overlap and  Imbalance: Snapshot, New Overlap Number of Balls Metrics and Singular  Problems Prospect