Hybrid Approach for Solving the Q3AP

Metaheuristics algorithms are competitive methods for solving assignment problems. This paper reports on nature inspired algorithms approach which is the particle swarm optimization (PSO) method hybrid with a local search (LS) algorithm for solving the quadratic three-dimensional assignment problem (Q3AP) where population-based metaheuristics like PSO or GA failed to solve. Q3AP is one of the combinatorial problems proven to be NP-Hard. It is an extension of the quadratic assignment problem (QAP). Solving the Q3AP consists of finding an optimal symbol mapping over two vectors, whereas solving the QAP consists of finding an optimal symbol mapping over one vector only. The authors tested the proposed hybrid algorithm on many instances where some of them haven't been used in the previous works for solving Q3AP. The results show that compared with the PSO algorithm and the genetic algorithm (GA), the proposed hybrid PSO-ILS(TS) algorithm is promising for finding the optimal/best known solution.

Crime mapping features

In this paper tools, organization and tactics of crime mapping are analyzed. The directions of application of mapping for maintenance of public safety and order, in criminal intelligence process, etc. are outlined. The domestic experience of mapping is briefly analyzed. The main goals that are achieved with the use of mapping are defined. Features of visualization of criminogenic cells are revealed. Pin mapping features (when points which symbolize a certain event are placed on the map on the corresponding coordinates) are outlined. Kernel density mapping is described, which makes it much easier to detect criminogenic foci, as hot-spot maps clearly reflect the concentration of certain events in the region. A method of mapping using proportional symbol mapping is disclosed when the increase in the size of the symbol denoting a point on the map is proportional to the increase in the number of events or other parameters at these coordinates. The building of geographical profiles of criminals is briefly described. The theoretical basis of mapping for the prediction of crimes is outlined. Prediction strategies based on equations and machine calculations and actuarial strategies based on expertise and clinical strategy are analyzed. Considerations are given to the appropriateness of applying appropriate strategies in different countries. The phenomenon of near repeat patterns is studied. Some software solutions for the implementation of the tasks of mapping criminal manifestations and the use of artificial intelligence systems for this purpose are described. Examples are given. It is noted that the use of cartography to prevent and predict crimes in Ukraine is in its infancy. Some solutions are proposed that could improve the situation in the field of crime mapping in Ukraine.