Deep Learning for Real-Time Crime Forecasting and Its Ternarization  

作　　者：Bao WANG Penghang YIN Andrea Louise BERTOZZI P.Jeffrey BRANTINGHAM Stanley Joel OSHER Jack XIN 

机构地区：[1]Department of Mathematics,University of California,Los Angeles,Westwood,Los Angeles,CA 90095,USA [2]Department of Anthropology,University of California,Los Angeles,Westwood,Los Angeles,CA 90095,USA [3]Department of Mathematics,University of California,Irvine,Irvine,CA 92697,USA

出　　处：《Chinese Annals of Mathematics,Series B》2019年第6期949-966,共18页数学年刊（B辑英文版）

基　　金：supported by ONR Grants N00014-16-1-2119,N000-14-16-1-2157;NSF Grants DMS-1417674,DMS-1522383,DMS-1737770 and IIS-1632935

摘　　要：Real-time crime forecasting is important.However,accurate prediction of when and where the next crime will happen is difficult.No known physical model provides a reasonable approximation to such a complex system.Historical crime data are sparse in both space and time and the signal of interests is weak.In this work,the authors first present a proper representation of crime data.The authors then adapt the spatial temporal residual network on the well represented data to predict the distribution of crime in Los Angeles at the scale of hours in neighborhood-sized parcels.These experiments as well as comparisons with several existing approaches to prediction demonstrate the superiority of the proposed model in terms of accuracy.Finally,the authors present a ternarization technique to address the resource consumption issue for its deployment in real world.This work is an extension of our short conference proceeding paper[Wang,B.,Zhang,D.,Zhang,D.H.,et al.,Deep learning for real time Crime forecasting,2017,ar Xiv:1707.03340].Real-time crime forecasting is important. However, accurate prediction of when and where the next crime will happen is difficult. No known physical model provides a reasonable approximation to such a complex system. Historical crime data are sparse in both space and time and the signal of interests is weak. In this work, the authors first present a proper representation of crime data. The authors then adapt the spatial temporal residual network on the well represented data to predict the distribution of crime in Los Angeles at the scale of hours in neighborhood-sized parcels. These experiments as well as comparisons with several existing approaches to prediction demonstrate the superiority of the proposed model in terms of accuracy. Finally, the authors present a ternarization technique to address the resource consumption issue for its deployment in real world. This work is an extension of our short conference proceeding paper [Wang, B., Zhang, D., Zhang,D. H., et al., Deep learning for real time Crime forecasting, 2017,ar Xiv:1707.03340].

关 键 词：Crime representation Spatial-temporal deep learning Real-time forecasting Ternarization 

分 类 号：G23[文化科学]