Spam Detection Approach Based on C-Support Vector Machine and Kernel Principal-Component Analysis
Authors:
- Shu GengSGShu Geng
- Liu LvLLLiu Lv
- Rongjun LiuRLRongjun Liu
- 1 August 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 231-234
Abstract
Current spam detection algorithms have poor generalization ability as given small samples and less priority knowledge. This paper proposed a spam filtering detection protocol based on Kernel principal-component analysis (KPCA) and C-Support Vector Machines (C-SVM) which can solve and implement the mentioned problem. Compared with the traditional algorithms this method can achieve higher detection rate and improve detection efficiency, and be easily generalized in practice. At last the experiment on data set shows the effectiveness and excellent performance of this method.Keywords
This publication has 7 references indexed in Scilit:
- Efficient Revised Simplex Method for SVM TrainingIEEE Transactions on Neural Networks, 2011
- Comparison of scaling behavior between fuzzy c-means based classifier with many parameters and LibSVM2011
- An Improved Algorithm for the Solution of the Regularization Path of Support Vector MachineIEEE Transactions on Neural Networks, 2010
- An efficient active set method for SVM training without singular inner problems2009
- A Convergent Hybrid Decomposition Algorithm Model for SVM TrainingIEEE Transactions on Neural Networks, 2009
- Fault identification for process monitoring using kernel principal component analysisChemical Engineering Science, 2005
- Nonlinear process monitoring using kernel principal component analysisChemical Engineering Science, 2004