Maximum Margin Learning of t-SPNs for Cell Classification With Filtered Input

Cited 1 time in webofscience Cited 2 time in scopus
  • Hit : 721
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorKang, Haeyongko
dc.contributor.authorYoo, Chang-Dongko
dc.contributor.authorNa, Yongcheonko
dc.date.accessioned2016-06-07T09:00:01Z-
dc.date.available2016-06-07T09:00:01Z-
dc.date.created2015-11-24-
dc.date.created2015-11-24-
dc.date.issued2016-02-
dc.identifier.citationIEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, v.10, no.1, pp.130 - 139-
dc.identifier.issn1932-4553-
dc.identifier.urihttp://hdl.handle.net/10203/207673-
dc.description.abstractAn algorithm based on a deep probabilistic architecture referred to as tree-structured sum-product network (t-SPN) is considered for cells classification. The t-SPN is a rooted acyclic graph constructed as a tree of several sum-product networks where each network is constructed over a subset of most confusing class features. The constructed t-SPN architecture is learned by maximizing the margin which is defined to be the difference in the conditional probability between the true and the most competitive false labels. To enhance generalization, l(2)-regularization (REG) is considered along with the maximum margin (MM) criterion in the learning process. To highlight cell features, this paper investigates the effectiveness of two generic high-pass filters: ideal high-pass filtering and the Laplacian of Gaussian (LOG) filtering. On both HEp-2 and Feulgen benchmark datasets, the t-SPN architecture learned based on the max-margin criterion with regularization produced the highest accuracy rate compared to other state-of-the-art algorithms that include convolutional neural network (CNN) based algorithms. Ideal high-pass filter was more effective on the HEp-2 dataset which is based on immunofluorescence staining while the LOG was more effective on Feulgen dataset which is based on Feulgen staining.-
dc.languageEnglish-
dc.publisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC-
dc.subjectHEP-2 CELLS-
dc.subjectRECOGNITION-
dc.subjectFEATURES-
dc.titleMaximum Margin Learning of t-SPNs for Cell Classification With Filtered Input-
dc.typeArticle-
dc.identifier.wosid000369495900011-
dc.identifier.scopusid2-s2.0-84962815402-
dc.type.rimsART-
dc.citation.volume10-
dc.citation.issue1-
dc.citation.beginningpage130-
dc.citation.endingpage139-
dc.citation.publicationnameIEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING-
dc.identifier.doi10.1109/JSTSP.2015.2502542-
dc.contributor.localauthorYoo, Chang-Dong-
dc.contributor.nonIdAuthorNa, Yongcheon-
dc.description.isOpenAccessN-
dc.type.journalArticleArticle-
dc.subject.keywordAuthort-SPNs-
dc.subject.keywordAuthorsub-SPNs-
dc.subject.keywordAuthormaximum margin-
dc.subject.keywordAuthorconfusing classes-
dc.subject.keywordPlusHEP-2 CELLS-
dc.subject.keywordPlusRECOGNITION-
dc.subject.keywordPlusFEATURES-
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 1 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0