Fuzzy entropy semi-supervised support vector data description

Trung Le, Dat Tran, Tien Tran, Khanh Nguyen, Wanli Ma

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

5 Citations (Scopus)


Support Vector Data Description (SVDD) is known as one of the best kernel-based methods for one-class classification problems. SVDD requires fully labelled data sets. However, in reality, an abundant amount of data can be easily collected, while the labelling process is often expensive, time-consuming, and error-prone. Therefore, partially labelled data sets are popular and easy to obtain. In this paper, we propose a semi-supervised learning method, Fuzzy Entropy Semi-supervised SVDD (FS3VDD), to extend SVDD to cope with partially labelled data sets. The learning model employs fuzzy membership and fuzzy entropy to help the labelling of the unlabeled data.

Original languageEnglish
Title of host publicationThe 2013 International Joint Conference on Neural Networks (IJCNN)
Place of PublicationPiscataway NJ USA
PublisherCurran Associates, Inc.
Number of pages5
ISBN (Electronic)9781467361293
ISBN (Print)9781467361286
Publication statusPublished - 2013
Externally publishedYes
EventIEEE International Joint Conference on Neural Networks 2013 - Dallas, United States of America
Duration: 4 Aug 20139 Aug 2013
https://ieeexplore.ieee.org/xpl/conhome/6691896/proceeding (Proceedings)


ConferenceIEEE International Joint Conference on Neural Networks 2013
Abbreviated titleIJCNN 2013
CountryUnited States of America
Internet address

Cite this