Security

Spam Detection System Combining Cellular Automata and Naive Bayes Classifier

Free registration required

Executive Summary

In this paper, the authors focus on the problem of spam detection. Based on a cellular automaton approach and naive Bayes technique which are built as individual classifiers they evaluate a novel method combining multiple classifiers diversified both by feature selection and different classifiers to determine whether they can more accurately detect Spam. This approach combines decisions from three cellular automata diversified by feature selection with that of naive Bayes classifier. Experimental results show that the proposed combination increases the classification performance as measured on LingSpam dataset.

  • Format: PDF
  • Size: 304.7 KB