The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.02 - March/April (2000 vol.15)
pp: 48-56
ABSTRACT
Classification algorithms are difficult to apply to sequential examples, such as text or DNA sequences, because a vast number of features are potentially useful for describing each example. Past work on feature selection has focused on searching the space of all subsets of the available features, which is intractable for large feature sets. The authors adapt data mining techniques to act as a preprocessor to select features for standard classification algorithms such as Naive Bayes and Winnow. They apply their algorithm to a number of data sets and experimentally show that the features produced by the algorithm improve classification accuracy up to 20%.
INDEX TERMS
classification, feature extraction, feature selection, sequence mining
CITATION
Neal Lesh, Mohammed J. Zaki, Mitsunori Ogihara, "Scalable Feature Mining for Sequential Data", IEEE Intelligent Systems, vol.15, no. 2, pp. 48-56, March/April 2000, doi:10.1109/5254.850827
28 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool