A Negative Selection Algorithm Based on Email Classification Techniques

Abstract

Aiming to develop an immune based system, the negative selection algorithm aid in solving complex problems in spam detection. This is been achieve by distinguishing spam from non-spam (self from non-self). In this paper, we propose an optimized technique for e-mail classification. This is done by distinguishing the characteristics of self and non-self that is been acquired from trained data set. These extracted features of self and non-self are then combined to make a single detector, therefore reducing the false rate. (Non-self that were wrongly classified as self). The result that will be acquired in this paper will demonstrate the effectiveness of this technique in decreasing false rate.