2020/07/31 by Shakila Khan Rumi, Rumi, Shakila Khan, Kyle K. Qin +3
Social Sciences · Computer Science · Engineering · #Human Mobility and Location-Based Analysis #Mobile and Web Applications #Vehicular Ad Hoc Networks (VANETs)
paper · pdf · doi:10.48550/arxiv.2008.00113
A well-crafted police patrol route design is vital in providing community\nsafety and security in the society. Previous works have largely focused on\npredicting crime events with historical crime data. The usage of large-scale\nmobility data collected from Location-Based Social Network, or check-ins, and\nPoint of Interests (POI) data for designing an effective police patrol is\nlargely understudied. Given that there are multiple police officers being on\nduty in a real-life situation, this makes the problem more complex to solve. In\nthis paper, we formulate the dynamic crime patrol planning problem for multiple\npolice officers using check-ins, crime, incident response data, and POI\ninformation. We propose a joint learning and non-random optimisation method for\nthe representation of possible solutions where multiple police officers patrol\nthe high crime risk areas simultaneously first rather than the low crime risk\nareas. Later, meta-heuristic Genetic Algorithm (GA) and Cuckoo Search (CS) are\nimplemented to find the optimal routes. The performance of the proposed\nsolution is verified and compared with several state-of-art methods using\nreal-world datasets.\n