Abstract
The global optimal, robust feature, and high generation ability of support vector machine (SVM) has been providing increasingly important tools in many fields, however, they are considerably slower in test phase than other leaning approaches due to the test procedure of SVMs usually requires huge memory space and significant computation time due to the enormous amounts of support vectors. Some researchers proposed to reduce the number of support vectors to lessen computational complexity and preserve generalization performance. In this paper, we proposed a new reduced support vector method, first, k nearest SV coalition was used to made a new support vector, second, the weight of the new support vector was obtain by an iterating method. So the computational complexity of improved method is lessen. Experimental results on power quality disturbance dataset show that the proposed method is effective in reducing number of support vectors and preserving machine 's generalization performance.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.