A Wasserstein Distance-Based Cost-Sensitive Framework for Imbalanced Data Classification

Simple item page
dc.contributor.authorFeng, R.
dc.contributor.authorJi, H.
dc.contributor.authorZhu, Z.
dc.contributor.authorWang, L.
dc.coverage.issue3cs
dc.coverage.volume32cs
dc.date.accessioned2023-10-11T08:00:47Z
dc.date.available2023-10-11T08:00:47Z
dc.date.issued2023-09cs
dc.description.abstractClass imbalance is a prevalent problem in many real-world applications, and imbalanced data distribution can dramatically skew the performance of classifiers. In general, the higher the imbalance ratio of a dataset, the more difficult it is to classify. However, it is found that standard classifiers can still achieve good classification results on some highly imbalanced datasets. Obviously, the class imbalance is only a superficial characteristic of the data, and the underlying structural information is often the key factor affecting the classification performance. As implicit prior knowledge, structural information has been validated to be crucial for designing a good classifier. This paper proposes a Wasserstein-based cost-sensitive support vector machine (CS-WSVM) for class imbalance learning, incorporating prior structural information and a cost-sensitive strategy. The Wasserstein distance is introduced to model the distribution of majority and minority samples to capture the structural information, which is employed to weight the majority and minority samples. Comprehensive experiments on synthetic and real-world datasets, especially on the radar emitter signal dataset, demonstrated that CS-WSVM can achieve outstanding performance in imbalanced scenarios.en
dc.formattextcs
dc.format.extent451-466cs
dc.format.mimetypeapplication/pdfen
dc.identifier.citationRadioengineering. 2023 vol. 32, č. 3, s. 451-466. ISSN 1210-2512cs
dc.identifier.doi10.13164/re.2023.0451en
dc.identifier.issn1210-2512
dc.identifier.urihttp://hdl.handle.net/11012/214338
dc.language.isoencs
dc.publisherSpolečnost pro radioelektronické inženýrstvícs
dc.relation.ispartofRadioengineeringcs
dc.relation.urihttps://www.radioeng.cz/fulltexts/2023/23_03_0451_0466.pdfcs
dc.rightsCreative Commons Attribution 4.0 International licenseen
dc.rights.accessopenAccessen
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en
dc.subjectImbalanced classificationen
dc.subjectcost-sensitiveen
dc.subjectstructural informationen
dc.subjectWasserstein distanceen
dc.subjectradar emitter signalen
dc.titleA Wasserstein Distance-Based Cost-Sensitive Framework for Imbalanced Data Classificationen
dc.type.driverarticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
eprints.affiliatedInstitution.facultyFakulta eletrotechniky a komunikačních technologiícs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
23_03_0451_0466.pdf
Size:
743.45 KB
Format:
Adobe Portable Document Format
Description:
Download
Collections
2023/3