@Article{iasc.2022.022972, AUTHOR = {G. Maria Jones, S. Godfrey Winster, P. Valarmathie}, TITLE = {An Advanced Integrated Approach in Mobile Forensic Investigation}, JOURNAL = {Intelligent Automation \& Soft Computing}, VOLUME = {33}, YEAR = {2022}, NUMBER = {1}, PAGES = {87--102}, URL = {http://www.techscience.com/iasc/v33n1/46149}, ISSN = {2326-005X}, ABSTRACT = {Rapid advancement of digital technology has encouraged its use in all aspects of life, including the workplace, education, and leisure. As technology advances, so does the number of users, which leads to an increase in criminal activity and demand for a cyber-crime investigation. Mobile phones have been the epicenter of illegal activity in recent years. Sensitive information is transferred due to numerous technical applications available at one’s fingertips, which play an essential part in cyber-crime attacks in the mobile environment. Mobile forensic is a technique of recovering or retrieving digital evidence from mobile devices so that it may be submitted in court for legal procedures. As a result, mobile phone data is essential for obtaining evidence in elements of mobile forensic data analysis. So, in this paper, we offer a method for detecting suspect drug-dealing patterns in mobile devices utilizing forensic and Natural Language Processing (NLP) techniques. Machine Learning algorithms are used to uncover the pattern in an original dataset, and performance measurements are used to assess the suggested system. In our approach, Logistic Regression (LR) manifests 95% of the highest accuracy in terms of count vector whereas, the BiLSTM (Bidirectional Long Short Term Memory) also achieved 95% of accuracy in terms of TFIDF.}, DOI = {10.32604/iasc.2022.022972} }