Detection of Irregularities and Abnormal Behaviour in Extreme-Scale Data Streams

In the last few years, terrorism, organized crime and cybercrime have gained more ground as society is becoming increasingly digitized. In this landscape, Law Enforcement Agencies (LEAs) should adapt by applying cross-domain expertise and follow an integrated approach that supersedes the traditional barriers in policing practices. In this light, the authors propose a novel approach that provides near real-time advanced behaviour analytics by using abnormal detection based on extracted historical patterns. In particular, appropriate tools are used to correlate different pieces of data leading to the discovery and recording of forensic evidence. Then, the collected data are combined to handle inconsistencies, and machine learning techniques are applied, in order to detect trends. It is expected that the current system will assist the LEA officers in their daily workload by minimizing the time to detect and solve a crime.