DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Won-Jo | ko |
dc.contributor.author | Lim, Chae-Gyun | ko |
dc.contributor.author | Kang, U | ko |
dc.contributor.author | Choi, Ho-Jin | ko |
dc.date.accessioned | 2015-06-24T02:06:41Z | - |
dc.date.available | 2015-06-24T02:06:41Z | - |
dc.date.created | 2015-06-10 | - |
dc.date.created | 2015-06-10 | - |
dc.date.issued | 2015-02-11 | - |
dc.identifier.citation | The 2nd International Conference on Big Data and Smart Computing (BigComp2015) | - |
dc.identifier.uri | http://hdl.handle.net/10203/198908 | - |
dc.description.abstract | There are numerous 2-dimensional matrix data for clustering including a set of documents, citation networks, web graphs, etc. However, many real-world datasets have more than three modes which require at least 3-dimensional matrices or tensors. Focusing on the clustering algorithm known as crossassociation, we extend the algorithm to deal with a 3-dimensional matrix. Our proposed method is fully automated, and simultaneously discovers clusters of both row, column, and tube groups. Experiments on real and synthetic datasets show that our method is effective. Through the proposed method, useful information can be obtained even from sparse datasets. | - |
dc.language | English | - |
dc.publisher | Korean Institute of Information Scientists and Engineers | - |
dc.title | An Extension to the Automatic Cross-Association Method with 3-dimensional Matrices | - |
dc.type | Conference | - |
dc.identifier.scopusid | 2-s2.0-84928156955 | - |
dc.type.rims | CONF | - |
dc.citation.publicationname | The 2nd International Conference on Big Data and Smart Computing (BigComp2015) | - |
dc.identifier.conferencecountry | KO | - |
dc.identifier.conferencelocation | Jeju KAL Hotel, Jeju Island | - |
dc.embargo.liftdate | 9999-12-31 | - |
dc.embargo.terms | 9999-12-31 | - |
dc.contributor.localauthor | Choi, Ho-Jin | - |
dc.contributor.nonIdAuthor | Lee, Won-Jo | - |
dc.contributor.nonIdAuthor | Lim, Chae-Gyun | - |
dc.contributor.nonIdAuthor | Kang, U | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.