Browse > Article
http://dx.doi.org/10.4218/etrij.2019-0306

A multi-dimensional crime spatial pattern analysis and prediction model based on classification  

Hajela, Gaurav (Department of Computer Science and Engineering, Maulana Azad National Institute of Technology)
Chawla, Meenu (Department of Computer Science and Engineering, Maulana Azad National Institute of Technology)
Rasool, Akhtar (Department of Computer Science and Engineering, Maulana Azad National Institute of Technology)
Publication Information
ETRI Journal / v.43, no.2, 2021 , pp. 272-287 More about this Journal
Abstract
This article presents a multi-dimensional spatial pattern analysis of crime events in San Francisco. Our analysis includes the impact of spatial resolution on hotspot identification, temporal effects in crime spatial patterns, and relationships between various crime categories. In this work, crime prediction is viewed as a classification problem. When predictions for a particular category are made, a binary classification-based model is framed, and when all categories are considered for analysis, a multiclass model is formulated. The proposed crime-prediction model (HotBlock) utilizes spatiotemporal analysis for predicting crime in a fixed spatial region over a period of time. It is robust under variation of model parameters. HotBlock's results are compared with baseline real-world crime datasets. It is found that the proposed model outperforms the standard DeepCrime model in most cases.
Keywords
classification; ensemble learning; hotspot analysis; spatiotemporal analysis;
Citations & Related Records
연도 인용수 순위
  • Reference
1 W. Bernasco and C. Vandeviver, The geography of crime and crime control, Appl. Geogr. 86 (2017), 220-225.   DOI
2 X. Hu et al., Impact of climate variability and change on crime rates in Tangshan, China, Sci. Total Environ. 609 (2017), 1041-1048.   DOI
3 D. J. Lemon and R. Partridge, Is weather related to the number of assaults seen at emergency departments?, Injury 48 (2017), 2438-2442.   DOI
4 X. Zhao and J. Tang, Crime in urban areas: A data mining perspective, available at CoRR http://arxiv.org/abs/1804.08159, preprint, 2018.
5 M. R. D'Orsogna and M. Perc, Statistical physics of crime: A review, Phys. Life Rev. 12 (2015), 1-21.   DOI
6 M. A. Andresen, Crime measures and the spatial analysis of criminal activity, Br. J. Criminol. 46 (2005), 258-285.   DOI
7 D. Vildosola et al., Crime in an affluent city: Applications of risk terrain modeling for residential and vehicle burglary in Coral Gables, Florida, 2004-2016, Appl. Spat. Anal. Policy 13 (2019), 441-459.   DOI
8 M. A. Andresen, Estimating the probability of local crime clusters: The impact of immediate spatial neighbors, J. Crim. Justice 39 (2011), 394-404.   DOI
9 L. Anselin, Local Indicators of Spatial Association-LISA, Geogr. Anal. 27 (1995), 93-115.   DOI
10 C. Cowen, E. Louderback, and S. Roy, The role of land use and walkability in predicting crime patterns: A spatiotemporal analysis of Miami-Dade County neighborhoods, 2007-2015, Secur. J. 32 (2019), 264-286.   DOI
11 C. Huang et al., Deep-Crime: Attentive hierarchical recurrent networks for crime prediction, in Proc. ACM Int. Conf. Inf. Knowledge Manag. (Torino, Italiy), Oct. 2018, pp. 1423-1432.
12 M. S. Gerber, Predicting crime using Twitter and kernel density estimation, Decis. Support Syst. 61 (2014), 115-125.   DOI
13 L. Vomfell, W. K. Hardle, and S. Lessmann, Improving crime count forecasts using Twitter and taxi data, Decis. Support Syst. 113 (2018), 73-85.   DOI
14 M. L. Williams, P. Burnap, and L. Sloan, Crime sensing with Big Data: The affordances and limitations of using open-source communications to estimate crime patterns, Br. J. Criminol. 57 (2016), 320-340.   DOI
15 G. Mohler, Marked point process hotspot maps for homicide and gun crime prediction in Chicago, Int. J. Forecast. 30 (2014), 491-497.   DOI
16 L. G. A. Alves, H. V. Ribeiro, and F. A. Rodrigues, Crime prediction through urban metrics and statistical learning, Phys. A 505 (2018), 435-443.   DOI
17 J. H. Ratcliffe, Geocoding crime and a first estimate of a minimum acceptable hit rate, Int. J. Geogr. Inf. Sci. 18 (2004), 61-72.   DOI
18 J. K. Ord and A. Getis, Local spatial autocorrelation statistics: Distributional issues and an application, Geogr. Anal. 27 (1995), 286-306.   DOI
19 G. N. Kouziokas, The application of artificial intelligence in public administration for forecasting high crime risk transportation areas in urban environment, Transp. Res. Procedia 24 (2017), 467-473.   DOI
20 A. Getis and J. K. Ord, The analysis of spatial association by use of distance statistics, Geogr. Anal. 24 (1992), 189-206.   DOI
21 K. Leong and A. Sung, A review of spatio-temporal pattern analysis approaches on crime analysis, Int. e-J. Crim. Sci. 9 (2015), 1-33.
22 A. Rummens, W. Hardyns, and L. Pauwels, The use of predictive analysis in spatiotemporal crime forecasting: Building and testing a model in an urban context, Appl. Geogr. 86 (2017), 255-261.   DOI
23 T. Lawson, R. Rogerson, and M. Barnacle, A comparison between the cost effectiveness of CCTV and improved street lighting as a means of crime reduction, Comput. Environ. Urban Syst. 68 (2018), 17-25.   DOI
24 R. Iqbal et al., An experimental study of classification algorithms for crime prediction, Indian, J. Sci. Technol. 6 (2013), 4219-4225.
25 Y. Xu et al., The impact of street lights on spatial-temporal patterns of crime in Detroit, Michigan, Cities 79 (2018), 45-52.   DOI