Flinders University Flinders Academic Commons

Flinders Academic Commons >
Research Publications >
ERA 2010 >
05 - Mathematics, Information and Communication Sciences >
0801 - Artificial Intelligence and Image Processing >

Please use this identifier to cite or link to this item: http://hdl.handle.net/2328/9631

Title: A unifying semantic distance model for determining the similarity of attribute values
Authors: Roddick, John Francis
de Vries, Denise Bernadette
Hornsby, Kathleen
Issue Date: 2003
Publisher: Australian Computer Society
Citation: Roddick, J.F., Hornsby, K., & de Vries, D.B., 2003. A unifying semantic distance model for determining the similarity of attribute values. Computer Science 2003: Proceedings of the Twenty-Sixth Australasian Computer Science Conference, 111-118.
Abstract: The relative difference between two data values is of interest in a number of application domains including temporal and spatial applications, schema versioning, data warehousing (particularly data preparation), internet searching, validation and error correction, and data mining. Moreover, consistency across systems in determining such distances and the robustness of such calculations is essential in some domains and useful in many. Despite this, there is no generally adopted approach to determining such distances and no accommodation of distance within SQL or any commercially available DBMS. For non-numeric data values calculating the difference between values often requires application-specific support but even for numeric values the practical distance between two values may not simply be their numeric difference or Euclidean distance. In this paper, a model of semantic distance is developed in which a graph-based approach is used to quantify the distance between two data values. The approach facilitates a notion of distance, both as a simple traversal distance and as weighted arcs. Transition costs, as an additional expense of passing through a node, are also accommodated. Furthermore, multiple distance measures can be incorporated and a method of ‘localisation’ is discussed which allows relevant information to take precedence over less relevant information. Some results from our investigations, including our SQL based implementation, are presented.
URI: http://hdl.handle.net/2328/9631
ISBN: 0909925941
Appears in Collections:0801 - Artificial Intelligence and Image Processing

Files in This Item:

File Description SizeFormat
Roddick Unifying.pdf322.77 kBAdobe PDFView/Open

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


Valid XHTML 1.0! DSpace Software Copyright © 2002-2010  Duraspace - Feedback