Title :
Effectiveness of Multi-Perspective Representation Scheme on Support Vector Machines
Author :
Zeng, Jia ; Alhajj, Reda
Author_Institution :
Dept. of Comput. Sci., Univ. of Calgary, Calgary, AB
Abstract :
In this paper, we present a multi-perspective representation (MPR) method, which takes advantage of the synergy of multiple representations of an information object. We have provided a detailed description of how to integrate the MPR scheme with support vector machines (MPR-SVM). The results of the experiments conducted on two benchmark data sets have shown the applicability and effectiveness of using the MPR-SVM scheme for classification purposes.
Keywords :
classification; support vector machines; benchmark data sets; classification; information object; multiperspective representation; support vector machines; Artificial neural networks; Biometrics; Computer science; Data mining; Decision trees; Machine learning; Machine learning algorithms; Supervised learning; Support vector machine classification; Support vector machines; classification; multi-perspective representation method.; support vector machine;
Conference_Titel :
Advanced Information Networking and Applications Workshops, 2007, AINAW '07. 21st International Conference on
Conference_Location :
Niagara Falls, Ont.
Print_ISBN :
978-0-7695-2847-2
DOI :
10.1109/AINAW.2007.163
