Method PPC for Precise Piecewise Correlation after Histogram Segmentation

dc.citation.spage472
dc.citation.volume16
dc.contributor.authorOgnjenovic, Visnja
dc.contributor.authorStojanov, Jelena
dc.contributor.authorBrtka, Vladimir
dc.contributor.authorBlazic, Marko
dc.contributor.authorBrtka, Eleonora
dc.contributor.authorBerkovic, Ivana
dc.date.accessioned2024-11-12T11:41:16Z
dc.date.available2024-11-12T11:41:16Z
dc.date.issued2024
dc.description.abstractCorrelation, functioning as a symmetric relation, is very powerful indicator of the mutual association between two attributes. The problem of weak correlation indicates a lack of linearity in the observed range. This paper presents the precise piecewise correlation method, which overcomes the problem by determining the segments where the linear association will be present. The determination was achieved using the histogram segmentation method. The conditions of the application and analysis of the method are presented, as well as the application of the method to the representative datasets. The obtained results confirm the existence of stronger linear associations on the segments. Detected correlations reveal the strength and nature of the symmetric association between two attributes on each of the separated segments.
dc.identifier.doi10.3390/sym16040472
dc.identifier.urihttps://vaseljena.ues.rs.ba/handle/123456789/1279
dc.language.isoen
dc.publisherMDPI
dc.sourceSymmetry
dc.subjectcorrelation; histogram segmentation; gain ratio; kernel density estimation
dc.titleMethod PPC for Precise Piecewise Correlation after Histogram Segmentation
dc.typeArticle
Датотеке
Оригинални завежљај
Сада се приказује 1 - 1 од 1
Учитавање...
Сличица
Име:
Method PPC for Precise Piecewise Correlation after Histogram.pdf
Величина:
7.09 MB
Формат:
Adobe Portable Document Format
Опис:
Свежањ лиценце
Сада се приказује 1 - 1 од 1
Учитавање...
Сличица
Име:
license.txt
Величина:
1.71 KB
Формат:
Item-specific license agreed to upon submission
Опис: