Sökning: id:"swepub:oai:DiVA.org:hh-100" >
A feature selection...
A feature selection technique for generation of classification committees and its application to categorization of laryngeal images
-
- Bacauskiene, Marija (författare)
- Department of Applied Electronics, Kaunas University of Technology, Lithuania
-
- Verikas, Antanas (författare)
- Högskolan i Halmstad,Halmstad Embedded and Intelligent Systems Research (EIS)
-
- Gelzinis, Adas (författare)
- Department of Applied Electronics, Kaunas University of Technology, Lithuania
-
visa fler...
-
- Valincius, Donatas (författare)
- Department of Applied Electronics, Kaunas University of Technology, Lithuania
-
visa färre...
-
(creator_code:org_t)
- New York : Pergamon Press, 2009
- 2009
- Engelska.
-
Ingår i: Pattern Recognition. - New York : Pergamon Press. - 0031-3203 .- 1873-5142. ; 42:5, s. 645-654
- Relaterad länk:
-
https://hh.diva-port... (primary) (Raw object)
-
visa fler...
-
http://hh.diva-porta...
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- This paper is concerned with a two phase procedure to select salient features (variables) for classification committees. Both filter and wrapper approaches to feature selection are combined in this work. In the first phase, definitely redundant features are eliminated based on the paired t-test. The test compares the saliency of the candidate and the noise features. In the second phase, the genetic search is employed. The search integrates the steps of training, aggregation of committee members, selection of hyper-parameters, and selection of salient features into the same learning process. A small number of genetic iterations needed to find a solution is the characteristic feature of the genetic search procedure developed. The experimental tests performed on five real-world problems have shown that significant improvements in Classification accuracy can be obtained in a small number of iterations if compared to the case of using all the features available.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences (hsv//eng)
Nyckelord
- Feedfoward neural networks
- Feature subset-selection
- Support vector machine
- Evolutionary ensembles
- Negative correlation
- Genetic algorithms
- Classifiers
- Recognition
- Accuracy
- Systems
- Information technology
- Informationsteknik
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
Till lärosätets databas