Abstract
SVM algorithm has a great advantage when it deals with small sample data set. However, In the process of large sample data set classification, it always has to face to the problems of slowly learning and large storage space. This paper puts forward the process of space edge detection, designs and implements the space edge detection based SVM algorithm. The result of simulation experiments shows that the model can effectively reduce the SVM training set, improve the speed of SVM training, save the storage space and the accuracy of the classification also has a good performance.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Lang, J.: Research on Several Problems in Support Vector Machine and Support Vector Domain Description. XiDian University, Xian (2009)
Li, H., Wang, C., Yuan, B.: An Improved SVM: NN-SVM. Chinese Journal of Computers 26, 1015–1020 (2003)
Zhang, Z., Dong, C., Chen, Z., He, X.: Improved fast classifier based on SVM and density clustering. Computer Engineering and Applications 47, 136–138 (2011)
Wang, J., Neskovic, P., Cooper, L.N.: Selecting Data for Fast Support Vector Machines Training. Studies in Computational Intelligence, vol. 35, pp. 61–84 (2007)
Deng, N., Tian, Y.: A new method of data mining - support vector machine. Science Press, Beijing (2004)
Chang, C.C., Lin, C.-J.: LIBSVM A Library for Support Vector Machines [EB/OL]
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Meng, F., Lin, W., Wang, Z. (2011). Space Edge Detection Based SVM Algorithm. In: Deng, H., Miao, D., Lei, J., Wang, F.L. (eds) Artificial Intelligence and Computational Intelligence. AICI 2011. Lecture Notes in Computer Science(), vol 7004. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-23896-3_81
Download citation
DOI: https://doi.org/10.1007/978-3-642-23896-3_81
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-23895-6
Online ISBN: 978-3-642-23896-3
eBook Packages: Computer ScienceComputer Science (R0)