TY  - JOUR
T1  - SVM Based Multilevel Classifier Using Ontology
AU - , V. Uma AU - , G. Aghila 
JO  - Research Journal of Applied Sciences
VL  - 2
IS  - 4
SP  - 431
EP  - 434
PY  - 2007
DA  - 2001/08/19
SN  - 1815-932x
DO  - rjasci.2007.431.434
UR  - https://makhillpublications.co/view-article.php?doi=rjasci.2007.431.434
KW  - Document classification
KW  -support vector machine
KW  -Ontology
AB  - A classical multilevel document classification system is vital in many contexts. This study explores the development of a multilevel document classification system based on Support Vector Machine (SVM) using ontology. SVMs have advantage over conventional statistical learning algorithms with features such as high generalization performance, prevention of over fitting, less computational complexity, high accuracy and robustness whereas the support of domain ontology further sharpens the classification by providing accurate required results. In this research SVM is used for implementing high level classification of the document and multi-level classification of the document is provided using Ontology. The comparison graph shows that the developed system based on ontology outperforms the existing system.
ER  -