Evaluation of crime pattern in Khanna local government using geographic information system

Sustainable development can only take place in an atmosphere of peace and tranquility. The state of insecurity in Rivers State and Nigeria at large has been on the rise over the past decade. The Nigerian security agencies have not been able to effectively tackle and nib crime activities in the bud. This has led to the loss of lives, businesses, and other attendant socio-economic effects. The distribution of crime across the landscape is geographically random since crime is a human phenomenon, hence geography plays an important role in law enforcement and criminal justice. Geographic information system (GIS) can help the security agency in tactical planning and response; allocating resources quickly and more effectively, determine mitigation priorities, analyze historical events, and predict future trends and patterns. The main aim of this paper is crime modeling and analysis using the Geo-information system. This paper uses GIS to visualize, analyze, and explain criminal activities within Khanna local government in a spatial context. To achieve this, crime data and records covering over seven years were obtained from the Nigerian Police Force in Bori. Supplementary and attribute data were collected through fieldwork using the Global Positioning System (GPS) to provide the coordinates of crime points and scenes in the local government and other associated data. A spatial database was created using ArcGIS software. The crime hotspot map and crime density map of the study area was produced using the ArcGIS pro tool- Gi-Bin fixed 234-FDR at 99%,95%, and 90% confidence level respectively for the hot spots and cold spots respectively. The maps and results from the spatial analysis performed can help the police to carry out patterns and trends analysis across multiple jurisdictions; enlist community action, enhancing implementation of various policies to reduce crime in the study area. It can also provide tools and techniques to capture, forecast future crime occurrence in the area and reduce crime incidences.

Considerations for Developing Predictive Spatial Models of Crime and New Methods for Measuring Their Accuracy

A literature review of the important trends in predictive crime modeling and the existing measures of accuracy was undertaken. It highlighted the need for a robust, comprehensive and independent evaluation and the need to include complementary measures for a more complete assessment. We develop a new measure called the penalized predictive accuracy index (PPAI), propose the use of the expected utility function to combine multiple measures and the use of the average logarithmic score, which measures accuracy differently than existing measures. The measures are illustrated using hypothetical examples. We illustrate how PPAI could identify the best model for a given problem, as well as how the expected utility measure can be used to combine different measures in a way that is the most appropriate for the problem at hand. It is important to develop measures that empower the practitioner with the ability to input the choices and preferences that are most appropriate for the problem at hand and to combine multiple measures. The measures proposed here go some way towards providing this ability. Further development along these lines is needed.

Agent Oriented Methodology for Crime Modelling and Simulation

Agent-oriented methodology (AOM) is a comprehensive and unified agent methodology for agent-oriented software development. The potential of Agent Oriented Methodology has been revealed in domains like collaborative technology, video surveillance, and economics. However, it has not been explored in crime modelling and simulation. Although AOM is claimed to be able to cope with a complex system development, it is still not yet determined up to what extent this may be true. Therefore, it is vital to investigate to validate this methodology. This paper investigates the adoption of AOM in crime modeling and simulation. The novelty of this paper is to introduce a systematic way to model crime simulation. Through the AOM simulation, it is proven that the AOM can model the complex system in crime domain with various outcomes which supported a few existing research theories such as routine activity theory. AOM can provide a wider research platform which is useful for translating theories and micro-level behavior into models and simulation that can be studied, shared, tested and enhanced.

Neural Network based Continuous Conditional Random Field for Fine-grained Crime Prediction

Crime prediction has always been a crucial issue for public safety, and recent works have shown the effectiveness of taking spatial correlation, such as region similarity or interaction, for fine-grained crime modeling. In our work, we seek to reveal the relationship across regions for crime prediction using Continuous Conditional Random Field (CCRF). However, conventional CCRF would become impractical when facing a dense graph considering all relationship between regions. To deal with it, in this paper, we propose a Neural Network based CCRF (NN-CCRF) model that formulates CCRF into an end-to-end neural network framework, which could reduce the complexity in model training and improve the overall performance. We integrate CCRF with NN by introducing a Long Short-Term Memory (LSTM) component to learn the non-linear mapping from inputs to outputs of each region, and a modified Stacked Denoising AutoEncoder (SDAE) component for pairwise interactions modeling between regions. Experiments conducted on two different real-world datasets demonstrate the superiority of our proposed model over the state-of-the-art methods.

Crime modeling with truncated Lévy flights for residential burglary models

Statistical agent-based models for crime have shown that repeat victimization can lead to predictable crime hotspots (see e.g. M. B. Short, M. R. D’Orsogna, V. B. Pasour, G. E. Tita, P. J. Brantingham, A. L. Bertozzi and L. B. Chayes, A statistical model of criminal behavior, Math. Models Methods Appl. Sci. 18 (2008) 1249–1267.), then a recent study in one-space dimension (S. Chaturapruek, J. Breslau, D. Yazdi, T. Kolokolnikov and S. G. McCalla, Crime modeling with Lévy flights, SIAM J. Appl. Math. 73 (2013) 1703–1720.) shows that the hotspot dynamics changes when movement patterns of the criminals involve long-tailed Lévy distributions for the jump length as opposed to classical random walks. In reality, criminals move in confined areas with a maximum jump length. In this paper, we develop a mean-field continuum model with truncated Lévy flights (TLFs) for residential burglary in one-space dimension. The continuum model yields local Laplace diffusion, rather than fractional diffusion. We present an asymptotic theory to derive the continuum equations and show excellent agreement between the continuum model and the agent-based simulations. This suggests that local diffusion models are universal for continuum limits of this problem, the important quantity being the diffusion coefficient. Law enforcement agents are also incorporated into the model, and the relative effectiveness of their deployment strategies are compared quantitatively.