Design and analysis of integrated approach for mobile device forensic

Abstract

The study developed an integrated approach for identifying suspicious activity involved in mobile criminal cases. General flow processes in mobile forensics are Seizure, Acquisition, Analysis, and Reporting. This flow process aims to retrieve the digital evidence for legal proceedings. The amount and diversity of data available for digital forensic investigations have grown dramatically in recent years. This rise is primarily due to a dramatic rise in the usage of mobile phones, the Internet, and social network media. As a result, forensic specialists face challenges while conducting manual investigations. So, Machine Learning (ML) and Deep Learning (DL) technologies can help in digital forensic investigations. These technologies can automate the stated laborious digital forensic investigation procedures, when analyzing huge quantities and a wide range of data found in chat logs. These can also help law enforcement agencies to investigate and respond more quickly and effectively. Consequently, the evidence against the predators may be utilized in a court of law, limiting the spread of online sexual grooming. Machine learning models have recently been applied to solve social cyber-related issues in digital forensics, including intrusion detection and digital text forensics. The study obtained the detection of suspicious pattern methodology for criminal activities involved in mobile devices. Mobile forensics model supported by Natural Language Processing for pre-processing the text data, Machine Learning and Deep Learning models were used to facilitate the automatic detection of suspicious activities. It aims to investigate how an integrated approach can perform the forensics data task. Mobile forensics has been well studied, and there are numerous techniques to handle the issues. However, the methods suffer to achieve the expected level of performance in detecting cybercrimes and threats. An efficient Real-time Multi Feature Crime Suspect Analysis Model (RMFCSA) is presented in this study to handle this issue newline