Please use this identifier to cite or link to this item:
Title: AIB2
Authors: Ougiaroglou, Stefanos
Evangelidis, Georgios
Type: Conference Paper
Subjects: FRASCATI::Natural sciences::Computer and information sciences
Keywords: k-NN classification
Data Reduction
Issue Date: 2013
First Page: 13
Volume Title: Proceedings of the 6th Balkan Conference in Informatics on - BCI '13
Abstract: Data reduction improves the efficiency of k-NN classifier on large datasets since it accelerates the classification process and reduces storage requirements for the training data. IB2 is an effective data reduction technique that selects some training items form the initial dataset and uses them as representatives (prototypes). Contrary to many other data reduction techniques, IB2 is a very fast, one-pass method that builds its reduced (condensing) set in an incremental manner. New training data can update the condensing set without the need of the "old" removed items. This paper proposes AIB2, a variation of IB2, which generates new prototypes instead of selecting them. AIB2 attempts to improve the efficiency of IB2 by positioning the prototypes in the center of the data areas they represent. The experimental study shows that AIB2 performs better than IB2.
ISBN: 9781450318518
Other Identifiers: 10.1145/2490257.2490260
Appears in Collections:Department of Applied Informatics

Files in This Item:
File Description SizeFormat 
2013_BCI.pdf144,92 kBAdobe PDFView/Open

This item is licensed under a Creative Commons License Creative Commons