Density Weighted Core Support Vector Machine
Abstract
Core Vector Machine (CVM) can be used to deal with large data sets classification problem, but CVM do not consider the density distribution of the data. In order to obtain the optimal description of the data, we propose a density weighted core support vector machine (DWCVM). In the proposed DWCVM, the relative density of each data point is based on the density distribution of the target data using the k-nearest neighbor (k-NN) approach. Experimental results on several benchmark data sets show that the performance of DWCVM is much better than CVM.
Keywords
Full Text:
PDFReferences
C. C. Chang, and C. J. Lin, “Training v-support vector classifiers: theory and algorithms”, Neural Computation, Vol.14, 2002, pp. 43-54.
M. D. Marizio, and C. C. Taylor, “Kernel density classification and boosting: an L2 analysis, Statistics and Computing”, Vol. 15, No. 2, 2005, pp.13-123.
D. M.J. Tax, and R. P. W. Duin, “Support vector data description”, Machine Learning, Vol. 54, No. 1, 2004, pp: 45-66.
M. R. Wu, and J. P. Ye, “A small sphere and large margin approach for novelty detection using training data with outlier”, IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol. 31, No. 11, 2009, pp. 2088-2092
W. J. Hu, F. L. Chung, and S. T. Wang, “The maximum vector angular margin classifier and its fast training on large datasets using a core vector machine”, Neural Networks, Vol. 27, 2012, pp. 60-73.
N. Takahashi, and T. Nishi, “Rigorous proof of termination of SMO algorithm for support vector machines”, IEEE Transaction on Neural Networks, Vol. 16, No. 3, 2005, pp. 774-776.
I. W. Tsang, J. T. Kwok, and P. M. Cheung, “Core Vector Machine: Fast SVM training on very large data sets”, Journal of Machine Learning Research, Vol. 6, 2005, pp. 363-392.
I. W. Tsang, J. T. Kwok, and J. M. Zurada, “Generalized core vector machines”, IEEE Transactions on Neural Networks, Vol. 17, No. 5, 2006, pp. 1126-1140.
C. Myungraee, S. K. Jun, and B. Jun-Geol, “Density weighted support vector data description”, Expert Systems with Applications, Vol. 41, 2014, pp. 3343–3350.