S-truncated Functions and Rough Sets in Approximation and Classification of Bottleneck Polygons

Document type: Conference Papers
Peer reviewed: Yes
Full text:
Author(s): Elisabeth Rakus-Andersson
Title: S-truncated Functions and Rough Sets in Approximation and Classification of Bottleneck Polygons
Conference name: Modeling Decisions for Artificial Intelligence - MDAI 2005
Year: 2005
Pagination: NIPO: 653-05-031-4, CD-ROM paper nr 049
ISBN: 84-00-08306-7
Publisher: Consejo Superior de Investigaciones Cientificas
City: Tsukuba, Japan
Organization: Blekinge Institute of Technology
Department: School of Engineering - Dept. Mathematics and Science (Sektionen för teknik – avd. för matematik och naturvetenskap)
School of Engineering S- 371 79 Karlskrona
+46 455 38 50 00
Authors e-mail: Elisabeth.Andersson@bth.se
Language: English
Abstract: Some collections of two-dimensional points form very irregular shapes, which cannot be approximated by standard curves without making large errors. We approximate the sets of points to introduce formal mathematical expressions giving rise for future predictions for other points, which are not placed in data sets. To accomplish the thorough approximation of finite point sets we test parametric s-truncated functions piecewise, which warrants a high accuracy of approximating. By operating with the functions, which represent samples of points obtained during experiments carried out, and by adopting the rough set technique, we attempt a classification of curves. Even if the curves are stretched and shaped differently we will divide them in classes gathering similar objects. To confirm availability and correctitude of the approximation and the classification proposed, we consider an examination of Internet packet streams, especially a bottleneck distribution based on throughput values.
Subject: Computer Science\Artificial Intelligence
Keywords: s-functions, approximation of point sets by s-functions, rough sets, classification by rough sets