×

Feature selection for classification using an ant system approach. (English) Zbl 1202.68332

Hinchey, Mike (ed.) et al., Distributed, parallel and biologically inspired systems. 7th IFIP TC 10 working conference, DIPES 2010, and 3rd IFIP TC 10 international conference biologically-inspired collaborative computing, BICC 2010, held as part of WCC 2010, Brisbane, Australia, September 20–23, 2010. Proceedings. Berlin: Springer (ISBN 978-3-642-15233-7/hbk; 978-3-642-15234-4/ebook). IFIP Advances in Information and Communication Technology 329, 233-241 (2010).
Summary: Many applications such as pattern recognition and data mining require selecting a subset of the input features in order to represent the whole set of features. The aim of feature selection is to remove irrelevant, redundant or noisy features while keeping the most informative ones. In this paper, an ant system approach for solving feature selection for classification is presented. The results we got are promising in terms of the accuracy of the classifier and the number of selected features in all the used datasets.
For the entire collection see [Zbl 1200.68008].

MSC:

68T10 Pattern recognition, speech recognition
68T05 Learning and adaptive systems in artificial intelligence

Software:

DistAl
PDFBibTeX XMLCite
Full Text: DOI