Title :
A new framework for an adaptive classifier model
Author :
Lee, Iltae ; Kianmehr, Keivan ; Koochakzadeh, Negar ; Alhajj, Reda ; Rokne, Jon
Author_Institution :
Dept of Comput. Sci., Univ. of Calgary, Calgary, AB, Canada
Abstract :
In this paper, a new framework to build an adaptive classifier is introduced. At first, a clustering algorithm, density-based spatial clustering of applications with noise (DBSCAN) is applied to a set of sample data to form initial set of clusters. The clusters are represented as classes. Using support vector machine (SVM), a classifier model is generated. In real world application, data comes in continuously. Therefore, if the model does not learn from the new data, the model may not perform as well with the new data especially when the model´s training data is different from the test data. The new framework proposed in this paper rebuilds the classifier model using selected data from test data set to improve the accuracy of the model.
Keywords :
learning (artificial intelligence); pattern classification; pattern clustering; support vector machines; DBSCAN; SVM; adaptive classifier model learning; density-based spatial clustering-of-application-with-noise; support vector machine; Application software; Classification tree analysis; Clustering algorithms; Computer science; Data mining; Databases; Partitioning algorithms; Support vector machine classification; Support vector machines; Testing; Clustering; DBSCAN; adaptive classifiers; classification; support vector machine;
Conference_Titel :
Information Reuse & Integration, 2009. IRI '09. IEEE International Conference on
Conference_Location :
Las Vegas, NV
Print_ISBN :
978-1-4244-4114-3
Electronic_ISBN :
978-1-4244-4116-7
DOI :
10.1109/IRI.2009.5211540
