ON RECOGNITION OF CIPHER BIT STREAM FROM DIFFERENT SOURCES USING MAJORITY VOTING FUSION RULE

Abstract

In the present paper, majority-voting rule has been investigated for its possible application in cryptological sciences. A novel approach is proposed to address the complex identification problem of overlapping classes. The method for representing patterns using different measurements has been discussed and the majority voting rule is used to fuse the results obtained in different measurement spaces. The proposed approach is quite natural and simple to implement in comparison with usual fusion strategies. The scheme has been implemented for three-class problem and results were tabulated and presented graphically.

Keywords

• Decision fusion, Representation space, Pattern space, Expert classifiers, Majority logic, Stream ciphers and Cryptology.