Publication: Suspect tracking based on call logs analysis and visualization
2
Issued Date
2017-02-21
Resource Type
Other identifier(s)
2-s2.0-85016215467
Rights
Mahidol University
Rights Holder(s)
SCOPUS
Bibliographic Citation
20th International Computer Science and Engineering Conference: Smart Ubiquitos Computing and Knowledge, ICSEC 2016. (2017)
Suggested Citation
Yosawee Longtong, Lalita Narupiyakul Suspect tracking based on call logs analysis and visualization. 20th International Computer Science and Engineering Conference: Smart Ubiquitos Computing and Knowledge, ICSEC 2016. (2017). doi:10.1109/ICSEC.2016.7859900 Retrieved from: https://repository.li.mahidol.ac.th/handle/123456789/42355
Research Projects
Organizational Units
Authors
Journal Issue
Thesis
Title
Suspect tracking based on call logs analysis and visualization
Author(s)
Other Contributor(s)
Abstract
© 2016 IEEE. In Thailand, investigator can track and find the suspects by using call logs from suspects' phone numbers and their contacts. In many cases, the suspects changed their phone numbers to avoid tracking. The problem is that the investigators have difficulty to track these suspects from their call logs. Our hypothesis is that each user has a unique calling behavior pattern. The calling pattern is importance for tracking suspect's telephone number. To compare the calling patterns, we consider common contact groups. Thus, the aim of this project is to develop a call logs tracking system which can predict a set of new possible suspect's phone numbers and present their contacts' connection with our network diagram visualization based on Graph database (Neo4j). This system will be very necessary for investigators because it can save investigators' time from analyzing excessive call logs data. The system can predict the possible suspect's phone numbers. Furthermore, our visualization can enhance human's sight ability to connect the relation among related phone numbers. Finally, the experimental results on real call logs demonstrate that our method can track telephone number approximately 69% of single possible suspect phone number's matching while 89% of multiple possible suspect phone numbers' matching.