Please use this identifier to cite or link to this item: http://hdl.handle.net/10077/3752
Title: Identification with iterative nearest neighbors using domain knowledge
Authors: Grosser, David
Conruyt, Noël
Ralambondrainy, Henri
Keywords: identificationSimilarityK-Nearest-NeighborsDecision Treesstructured dataknowledge baselife science
Issue Date: 2010
Publisher: EUT Edizioni Università di Trieste
Source: David Grosser, Noël Conruyt, Henri Ralambondrainy, in Pier Luigi Nimis and Régine Vignes Lebbe (eds.): “Tools for Identifying Biodiversity: Progress and Problems. Proceedings of the International Congress, Paris, September 20-22, 2010”, Trieste, EUT Edizioni Università di Trieste, 2010, pp. 71-76.
Abstract: A new iterative and interactive algorithm called CSN (Classification by Successive Neighborhood) to be used in a complex descriptive objects identification approach is presented. Complex objects are those designed by experts within a knowledge base to describe taxa (monography species) and also real organisms (collection specimens). The algorithm consists of neighborhoods computations from an incremental basis of characters using a dissimilarity function which takes into account structures and values of the objects. A discriminant power function is combined with domain knowledge on the features set at each iteration. It is shown that CSN consistently outperforms methods such as identification trees and simplifies interactive classification processes comparatively to search for K-Nearest-Neighbors method.
URI: http://hdl.handle.net/10077/3752
ISBN: 978-88-8303-295-0
Appears in Collections:Tools for Identifying Biodiversity: Progress and Problems

Files in This Item:
File Description SizeFormat 
Grosser, Conruyt, Ralambondrainy bioidentify.pdf562.46 kBAdobe PDFView/Open
Show full item record


CORE Recommender

Page view(s)

952
checked on Feb 24, 2018

Download(s)

568
checked on Feb 24, 2018

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.