Proceeding of the Electrical Engineering Computer Science and Informatics
Vol 2: EECSI 2015

Performance Analysis on Text Steganalysis Method Using A Computational Intelligence Approach

Din, Roshidi ( University Utara Malaysia)
Yusof, Shafiz Affendi Mohd ( University Utara Malaysia)
Amphawan, Angela ( University Utara Malaysia)
Hussain, Hanizan Shaker ( Kolej Poly-Tech MARA)
Yaacob, Hanafizah ( Kolej Poly-Tech MARA)
Jamaludin, Nazuha ( Kolej Poly-Tech MARA)
Samsudin, Azman ( University Sains Malaysia)



Article Info

Publish Date
15 Aug 2015

Abstract

In this paper, a critical view of the utilization of computational intelligence approach from the text steganalysis perspective is presented. This paper proposes a formalization of genetic algorithm method in order to detect hidden message on an analyzed text. Five metric parameters such as running time, fitness value, average mean probability, variance probability, and standard deviation probability were used to measure the detection performance between statistical methods and genetic algorithm methods. Experiments conducted using both methods showed that genetic algorithm method performs much better than statistical method, especially in detecting short analyzed texts. Thus, the findings showed that the genetic algorithm method on analyzed stego text is very promising. For future work, several significant factors such as dataset environment, searching process and types of fitness values through other intelligent methods of computational intelligence should be investigated.

Copyrights © 2015






Journal Info

Abbrev

EECSI

Publisher

Subject

Computer Science & IT Electrical & Electronics Engineering

Description

Proceeding of the Electrical Engineering Computer Science and Informatics publishes papers of the "International Conference on Electrical Engineering Computer Science and Informatics (EECSI)" Series in high technical standard. The Proceeding is aimed to bring researchers, academicians, scientists, ...