In the past, digital forensic, with its exploration techniques, are a lane to the data recovery as well as the examination of different investigation techniques. It is a line of investigation which includes many stages. In this, the foremost assignment is data collection later than that the outcome amount produced predicted with the dataset. Some authors proposed several supervised machine learning techniques that have not obtained much better results. Therefore, the goal of our study was to perform an investigational work on a forensics dataset task for class-based classification methods like three-layer CNN classifiers, five-layer CNN classifiers, and seven-layer CNN classifiers. The classifiers evaluated with classification performance and accuracy. The experimental plan has been done with fivefold cross-validation with fifty repetitions for deep learning algorithms in order to obtain consistent results. Matching accuracy values for the next to next pixels in the classes are calculated with the class-based predicted labels. There are four classes assigned on CNN, and the four classes are segmented and separated with the same region of interest. Then the same class-based region of interests is segregated, and these four class-based regions are next given to CNN with the clusters. Further, the comparison results are made with the used three algorithms.
- DFIR Resources
- Data mining approach for digital forensics task with deep learning techniques
Data mining approach for digital forensics task with deep learning techniquesHot
Research and Documentation
White Papers & Journals
Analysis - Devices & OSs