典型文献
Dynamic road crime risk prediction with urban open data
文献摘要：
Crime risk prediction is helpful for urban safety and citizens' life quality.However,existing crime studies focused on coarse-grained prediction,and usually failed to capture the dynamics of urban crimes.The key challenge is data sparsity,since that 1) not all crimes have been recorded,and 2) crimes usually occur with low frequency.In this paper,we propose an effective framework to predict fine-grained and dynamic crime risks in each road using heterogeneous urban data.First,to address the issue of unreported crimes,we propose a cross-aggregation soft-impute (CASI) method to deal with possible unreported crimes.Then,we use a novel crime risk measure-ment to capture the crime dynamics from the perspective of influence propagation,taking into consideration of both time-varying and location-varying risk propagation.Based on the dy-namically calculated crime risks,we design contextual features(i.e.,POI distributions,taxi mobility,demographic features)from various urban data sources,and propose a zero-inflated negative binomial regression (ZINBR) model to predict future crime risks in roads.The experiments using the real-world data from New York City show that our framework can accurately predict road crime risks,and outperform other baseline meth-ods.
文献关键词：
中图分类号：
作者姓名：
Binbin ZHOU;Longbiao CHEN;Fangxun ZHOU;Shijian LI;Sha ZHAO;Gang PAN
作者机构：
College of Computer Science,Zhejiang University,Hangzhou 310027,China;Fujian Key Laboratory of Sensing and Computing for Smart Cities,School of Information Science and Engineering,Xiamen University,Xiamen 361005,China
文献出处：
引用格式：
[1]Binbin ZHOU;Longbiao CHEN;Fangxun ZHOU;Shijian LI;Sha ZHAO;Gang PAN-.Dynamic road crime risk prediction with urban open data)[J].计算机科学前沿,2022(01):105-117
A类：
ZINBR
B类：
Dynamic,prediction,urban,open,data,Crime,helpful,safety,citizens,life,quality,However,existing,studies,focused,coarse,grained,usually,failed,capture,dynamics,crimes,key,challenge,sparsity,since,that,not,have,been,recorded,occur,low,frequency,In,this,paper,propose,effective,framework,fine,risks,each,using,heterogeneous,First,address,issue,unreported,cross,aggregation,soft,impute,CASI,method,deal,possible,Then,novel,measure,from,perspective,influence,propagation,taking,into,consideration,both,varying,location,Based,namically,calculated,design,contextual,features,POI,distributions,taxi,mobility,demographic,various,sources,zero,inflated,negative,binomial,regression,model,future,roads,experiments,real,world,New,York,City,show,can,accurately,outperform,other,baseline,ods
AB值：
0.543956
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
