Title :
Deciding the Convex Separability of Pattern Sets
Author :
Takács, Gábor ; Pataki, Béla
Author_Institution :
Budapest Univ. of Technol. & Econ., Budapest
Abstract :
Deciding the convex separability of the classes is an interesting question in the data exploration phase of building classification systems. In this paper we propose an efficient algorithm for deciding the convex separability of two point sets in Rd. We compare our algorithm with conventional methods on 6 benchmark problems, and demonstrate that our algorithm is significantly faster.
Keywords :
convex programming; pattern classification; set theory; classification systems; point set convex separability; Conferences; Data acquisition; Economic forecasting; Information systems; Intelligent structures; Intelligent systems; Machine learning; Machine learning algorithms; Pattern recognition; Polynomials; Convex Hull; Data Exploration; Linear Classifiers; Pattern Recognition;
Conference_Titel :
Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, 2007. IDAACS 2007. 4th IEEE Workshop on
Conference_Location :
Dortmund
Print_ISBN :
978-1-4244-1347-8
Electronic_ISBN :
978-1-4244-1348-5
DOI :
10.1109/IDAACS.2007.4488421
