File fragment recognition based on content and statistical features

Nowadays, the speed up development and use of digital devices such as smartphones have put people at risk internet crimes. The evidence present crimes in a computer file can be easily unreachable by changing prefix or other algorithms. In more complex cases, either divided into different parts that has information about type are deleted, where fragment recognition issue is discussed. known files fragments, classification algorithms used to solve problems recognition. identifying due its importance cybercrime issues well antivirus been highly emphasized addressed many articles. Increasing accuracy this field on types widely sensitivity subject recognizing under study main goal researchers field. Failure identify correct will lead deviations results from failure conclude. paper, first, fragments. Then, features, which obtained Binary Frequency Distribution, reduced 2 feature reduction algorithms; Sequential Forward Selection algorithm Floating delete sparse features result increased speed. Finally, given 3 Multiclass classifier algorithms, Multilayer Perceptron, Support Vector Machines, K-Nearest Neighbor for comparison results. proposed recognize 6 useful may distinguish fragments with higher than similar works done.