A model of suspected activity detection and application using big data analytics

This study proposes a big data analytics methodology to analyse data that are available from many institutions for providing safety to the citizens in their daily life. In the traditional protection system approach, tactics are mainly dependent on the experience of the law enforcements. However, it is really difficult to generalize their experiences for applying solutions in the real world. Also, the conventional approach usually loses its prevention capability because it would take more time to react to the incidents. If the crime happened, the damage would already be done to the victims. So, the best interest for the law enforcements is to prevent a crime before happening. We believe that in order to have effective criminal activity prevention, law enforcement needs to implement data driven approaches, solutions and real time processing of data. In this study we suggested to use CDR (Call Detail Records), ANPR (Automatic Number Plate Recognition), API/PNR (Advanced Passenger Information/Passenger Name Records) data. While combining these we have a methodology that is a force multiplier for law enforcement in their duty to counter criminal activities. This study presents sample scenarios, use cases and methodologies while using big data for detecting suspected activities of individuals and objects for safety purposes. Hence, this study presents a model to analyze CDR, API/PNR and ANPR data using big data analytics for law enforcement usage to protect people from malicious activities.