Rough Set (RS) and Support Vector Machine(SVM) have gradually been becoming hot spots in the territory of artificial intelligence, machine learning and data mining research. In this paper, RS and SVM theories have been discussed, a new hybrid RS-SVM model was proposed based on the attribute reduction of RS and the classification principles of SVM, which has been analyzed its possibility of application in competency assessment and has been applied in competency assessment. Firstly, the attribute reduction of RS has been applied as preprocessor to delete redundant attributes and conflicting objects without losing efficient information. Then, an SVM classification model is built to make a forecast. Finally, compared the RS-SVM model with neural network model or grade regression model. Empirical results shown that RS-SVM model obtains good classification performance, and it highly reduces the complexity in the process of SVM classification and prevents the over-fit of training model in a certain extent.
[1]
Huang Lin.
Freeway incident detection algorithm based on Rough Sets and Support Vector Machine
,
2008
.
[2]
Jiayuan Yu.
The Application of Neural Networks and Rough Set in Creativity Measurement
,
2010,
2010 International Conference on Computational Intelligence and Software Engineering.
[3]
Chih-Jen Lin,et al.
LIBSVM: A library for support vector machines
,
2011,
TIST.
[4]
Z. Pawlak.
Rough set approach to knowledge-based decision support
,
1997
.
[5]
Paul D. Nelson,et al.
Challenges to the assessment of competence and competencies.
,
2007
.
[6]
Yu Jia.
Application of Rough Set and Neural Networks in Psychological Measurement
,
2008
.
[7]
Andrzej Skowron,et al.
Rudiments of rough sets
,
2007,
Inf. Sci..