File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1007/978-3-642-34679-8_9
- Scopus: eid_2-s2.0-84958037455
- Find via
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Optimal combination of feature weight learning and classification based on local approximation
Title | Optimal combination of feature weight learning and classification based on local approximation |
---|---|
Authors | |
Keywords | Local hyperplane Nearest neighbor Feature weighting Discriminant analysis Classification |
Issue Date | 2012 |
Publisher | Springer. |
Citation | Third International Conference on Data and Knowledge Engineering (ICDKE 2012), Fujian, China, 21-23 November 2012. In Data and Knowledge Engineering: Third International Conference, ICDKE 2012, Wuyishan, Fujian, China, November 21-23, 2012: Proceedings, 2012, p. 86-94 How to Cite? |
Abstract | © Springer-Verlag Berlin Heidelberg 2012. Currently, most feature weights estimation methods are independent on the classification algorithms. The combination of discriminant analysis and classifiers for effective pattern classification remains heuristic. The present study address the topics of learning of feature weights by using a recently reported classification algorithm, K-Local Hyperplane Distance Nearest Neighbor (HKNN) [18], in which the data is modeled as embedded in a linear hyperplane. Motivated by the encouraging performance of the Learning Discriminative Projections and Prototypes, the feature weights are estimated by minimizing the classifier leave-one-out cross validation error of HKNN. Approximated explicit solution is obtained to give feature estimation. Therefore, the feature weighting and classification are perfectly matched. The performance of the combinational model is extensively assessed via experiments on both synthetic and benchmark datasets. The superior results demonstrate that the method is competitive compared with some state-of-art models. |
Persistent Identifier | http://hdl.handle.net/10722/276711 |
ISBN | |
ISSN | 2023 SCImago Journal Rankings: 0.606 |
Series/Report no. | Lecture Notes in Computer Science ; 7696 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Cai, Hongmin | - |
dc.contributor.author | Ng, Michael | - |
dc.date.accessioned | 2019-09-18T08:34:25Z | - |
dc.date.available | 2019-09-18T08:34:25Z | - |
dc.date.issued | 2012 | - |
dc.identifier.citation | Third International Conference on Data and Knowledge Engineering (ICDKE 2012), Fujian, China, 21-23 November 2012. In Data and Knowledge Engineering: Third International Conference, ICDKE 2012, Wuyishan, Fujian, China, November 21-23, 2012: Proceedings, 2012, p. 86-94 | - |
dc.identifier.isbn | 9783642346781 | - |
dc.identifier.issn | 0302-9743 | - |
dc.identifier.uri | http://hdl.handle.net/10722/276711 | - |
dc.description.abstract | © Springer-Verlag Berlin Heidelberg 2012. Currently, most feature weights estimation methods are independent on the classification algorithms. The combination of discriminant analysis and classifiers for effective pattern classification remains heuristic. The present study address the topics of learning of feature weights by using a recently reported classification algorithm, K-Local Hyperplane Distance Nearest Neighbor (HKNN) [18], in which the data is modeled as embedded in a linear hyperplane. Motivated by the encouraging performance of the Learning Discriminative Projections and Prototypes, the feature weights are estimated by minimizing the classifier leave-one-out cross validation error of HKNN. Approximated explicit solution is obtained to give feature estimation. Therefore, the feature weighting and classification are perfectly matched. The performance of the combinational model is extensively assessed via experiments on both synthetic and benchmark datasets. The superior results demonstrate that the method is competitive compared with some state-of-art models. | - |
dc.language | eng | - |
dc.publisher | Springer. | - |
dc.relation.ispartof | Data and Knowledge Engineering: Third International Conference, ICDKE 2012, Wuyishan, Fujian, China, November 21-23, 2012: Proceedings | - |
dc.relation.ispartofseries | Lecture Notes in Computer Science ; 7696 | - |
dc.subject | Local hyperplane | - |
dc.subject | Nearest neighbor | - |
dc.subject | Feature weighting | - |
dc.subject | Discriminant analysis | - |
dc.subject | Classification | - |
dc.title | Optimal combination of feature weight learning and classification based on local approximation | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1007/978-3-642-34679-8_9 | - |
dc.identifier.scopus | eid_2-s2.0-84958037455 | - |
dc.identifier.spage | 86 | - |
dc.identifier.epage | 94 | - |
dc.identifier.eissn | 1611-3349 | - |
dc.publisher.place | Berlin | - |
dc.identifier.issnl | 0302-9743 | - |