Xiaohua Liu and Juan F. Beltran and Nishant Mohanchandra and Godfried T. Toussaint On Speeding Up Support Vector Machines Proximity Graphs Versus Random Sampling for PreSelection Condensation
133 - 140
2013
7
1
International Journal of Computer, Electrical, Automation, Control and Information Engineering http://waset.org/publications/5928
http://waset.org/publications/73
World Academy of Science, Engineering and Technology
Support vector machines (SVMs) are considered to be
the best machine learning algorithms for minimizing the predictive
probability of misclassification. However, their drawback is that for
large data sets the computation of the optimal decision boundary is a
time consuming function of the size of the training set. Hence several
methods have been proposed to speed up the SVM algorithm. Here
three methods used to speed up the computation of the SVM
classifiers are compared experimentally using a musical genre
classification problem. The simplest method preselects a random
sample of the data before the application of the SVM algorithm. Two
additional methods use proximity graphs to preselect data that are
near the decision boundary. One uses kNearest Neighbor graphs and
the other Relative Neighborhood Graphs to accomplish the task.
International Science Index 73, 2013