地球信息科学学报 ›› 2021, Vol. 23 ›› Issue (1): 43-57.doi: 10.12082/dqxxkx.2021.200247
收稿日期:
2020-05-19
修回日期:
2020-06-29
出版日期:
2021-01-25
发布日期:
2021-03-25
通讯作者:
顾海硕,陈鹏
作者简介:
顾海硕(1995—),男,硕士生,浙江嘉兴人,研究方向为警务大数据分析。E-mail: 基金资助:
GU Haisuo1,*, CHEN Peng1(), LI Huibo2
Received:
2020-05-19
Revised:
2020-06-29
Online:
2021-01-25
Published:
2021-03-25
Contact:
GU Haisuo,CHEN Peng
Supported by:
摘要:
犯罪时空预测作为预测警务的核心支撑技术,自2000年左右至今得到了快速的发展。本文介绍了犯罪时空预测的实践背景和理论基础,将犯罪时空预测解构为利用历史案件的时空位置、时空环境和个体行为等要素,结合相应的算法模型预测未来案件时空分布的过程。然后,从输入要素的视角对当前的犯罪时空预测方法进行了总结和归纳,将其划分为基于案件时空位置信息的犯罪时空预测、基于时空环境要素的犯罪时空预测,以及融合行为轨迹和时空环境要素的犯罪时空预测3种类型,详细总结了不同类型犯罪时空预测的方法原理,并从适应场景和预测效果等方面对不同的方法模型进行了比较。最后,结合当前的大数据技术发展趋势,对未来的犯罪时空预测进行了展望。本文认为犯罪时空预测未来需要从数据角度重点解决输入数据的体系融合、粒度细化和新型数据融合等问题,从模型优化角度应着重提高多源异构数据融合能力,平衡模型的可解释性与预测效果。
顾海硕, 陈鹏, 李慧波. 犯罪时空预测方法研究综述与展望[J]. 地球信息科学学报, 2021, 23(1): 43-57.DOI:10.12082/dqxxkx.2021.200247
GU Haisuo, CHEN Peng, LI Huibo. Overview and Prospect for Spatial-Temporal Prediction of Crime[J]. Journal of Geo-information Science, 2021, 23(1): 43-57.DOI:10.12082/dqxxkx.2021.200247
表1
犯罪时空预测方法分类(按照输入变量复杂程度排序)"
方法类型 | 输入变量 | 主要模型 | 提出时间 |
---|---|---|---|
基于案件时空位置信息的犯罪时空预测 | 案件时空位置信息(主要为空间栅格数据) | 犯罪临近重复模型 核密度估计模型 自激点震荡模型 机器学习模型 | 20世纪90年代 |
基于时空环境要素的犯罪时空预测 | 案件时空位置信息,时空环境背景要素(分为空间栅格数据和网络数据) | 风险地形建模 贝叶斯预测模型 离散选择模型 张量模型 机器学习模型 图传播模型 时空搜索窗模型 | 20世纪90年代 |
融合行为轨迹和时空环境要素的犯罪时空预测 | 案件时空位置信息,时空环境背景要素,主体行为轨迹 (主要为空间栅格数据) | 离散选择模型 机器学习模型 | 2015年前后 |
表2
机器学习模型及其预测效果"
方法 | 预测效果 | 提出/使用者 | 研究时间/年 |
---|---|---|---|
逻辑回归与神经网络结合的模型 | 神经网络模型相比逻辑回归模型有更高的直接命中率但收效甚微,二者结合的模型能平衡预测精度和直接命中率[ | Rummens等[ | 2017 |
DeepCrime | DeepCrime模型在多种预测场景下均表现出了相比支持向量机(SVR)、ARIMA、逻辑回归、多层感知机、TriMine、GRU、Wide&Deep等7种模型更佳的预测效果[ | Huang等[ | 2018 |
GSRNN时空预测模型 | GSRNN时空预测模型兼顾了时空关联性,相比仅基于LSTM的神经网络模型具有更好的预测效果[ | Wang等[ | 2018 |
基于随机森林的模型 | 加入环境协变量的模型相比未加入的模型预测效果更佳[ | Liu等[ | 2019 |
基于LSTM的时空预测模型 | 基于LSTM的神经网络时空预测模型相比ARIMA和随机森林模型预测效果更佳[ | Pan[ | 2019 |
表3
图传播模型及其预测效果"
方法 | 预测效果 | 提出/使用者 | 研究时间/年 |
---|---|---|---|
基于网络的K邻近法(Network K-function) | 基于网络的K邻近法相比基于平面的方法更加符合实际案件时空分布[ | Lu等[ | 2007 |
基于网络的入室盗窃模型 | 基于网络的模型明显优于非网络模型[ | Davies等[ | 2013 |
基于网络的时空核密度估计(NTKDE) | 基于网络的模型在预测精度及效果上明显强于基于平面的模型[ | Rosser等[ | 2017 |
NTKDE 门控局部扩散网络模型(GLDNet) | 门控局部扩散网络模型预测效果优于基于网络的时空核密度估计模型[ | Zhang等[ | 2019 |
表4
时空搜索窗模型及其预测效果"
方法 | 预测效果 | 提出/使用者 | 研究时间/年 |
---|---|---|---|
基于网络的犯罪时空分析 (NT-STAC) 基于网络的空间扫描统计 (NT-SaTScan) | 其他条件相同情况下,基于网络的方法总体强于基于平面的方法[ | Shiode等[ | 2011 |
基于网络的空间搜索窗犯罪时空分析模型(SNT-STAC) 基于网络的时空搜索窗犯罪时空分析模型(STNT-STAC) | 其他条件相同情况下,预测效果上,基于时空的模型优于基于空间的模型[ | Shiode等[ | 2013 |
时间搜索窗犯罪分析模型(TAC) 基于网络的犯罪空间搜索窗分析模型(SACNT) 基于网络的犯罪时空搜索窗分析模型(STACNT) | 其他条件相同情况下,基于网络的方法总体强于基于平面的方法;其他条件相同情况下,在预测效果上,基于时空的模型优于基于空间的模型优于基于时间的模型[ | Shiode等[ | 2015 |
表5
不同研究人员所采用的输入变量、模型、对比形式及预测效果"
输入变量 | 模型 | 对比形式 | 效果 | 提出/使用者 | 研究时间/年 |
---|---|---|---|---|---|
案件:犯罪数据 时空静态类:POI数据 时空动态类:浮动车数据 | 线性回归模型 负二项回归模型 GWNBR | 模型间对比 | 基于地理加权回归的负二项回归模型效果最佳[ | Wang等[ Wang等[ | 2016 2017 |
案件:犯罪数据 时空静态类:POI数据 时空动态类:签到数据 | 负二项回归模型 线性回归模型 随机森林模型 | 模型间对比 | 随机森林模型预测效果最佳[ | Shakila Khan Rumi等[ | 2019 |
案件:盗窃案件数据 时空静态类:POI数据 空间静态时间动态类:基站信令数据 | 离散选择模型 | 是否增加非时空静态类数据 | 增加非时空静态类数据可以提升预测精度[ | Song等[ | 2019 |
案件:侵财类案件数据 时空静态类:警务对策数据、土地利用数据、人口普查数据、经济普查数据 空间静态时间动态类:流动人口数据 | BP神经网络模型 GA-BP神经网络模型 | 模型间对比 | 改进的GA-BP模型预测效果更佳[ | Li等[ | 2017 |
案件:单类犯罪数据、公共服务投诉数据 空间静态时间动态类:气象数据 时空动态类:浮动车数据、POI签到数据 | TCP CSI ARMA LASSO 线性回归模型 时空多任务学习模型 | 模型间对比 | TCP能取得最优预测效果[ | Zhao等[ | 2017 |
案件:警情数据 时空静态类:人口网格数据 空间静态时间动态类:基站信令数据 时空动态类:浮动车数据、地铁刷卡数据 | 负二项回归模型 | 是否增加非时空静态类数据 | 增加非时空静态类数据可以提升预测精度[ | Song等[ | 2018 |
案件:多种类犯罪案件数据 时空静态类:人口统计数据 空间静态时间动态类:场馆使用数据 时空动态类:浮动车数据、地铁刷卡数据 | 随机森林模型 梯度提升模型 Extra-Tree模型 | 不同数据对结果作用效果对比;模型间对比 | 不同类型案件对增加非时空静态类数据的敏感度不同,但都能提升预测效果;不同犯罪类型预测并没有一个完全最优的模型[ | Kadar等[ | 2018 |
[1] | Perry W L . Predictive policing: The role of crime forecasting in law enforcement operations[M]. Rand Corporation, 2013. |
[2] | Ratcliffe J . What is the futureof predictive policing[J]. Practice, 2015,6(2):151-166. |
[3] | 魏平雄, 赵宝成, 王顺安 . 犯罪学教程[M]. 北京: 中国政法大学出版社, 1998. |
[ Wei P X, Zhao B C, Wang A S. The criminology tutorial[M]. Beijing: China University of Political Science and Law Press, 1998.] | |
[4] |
Hardyns W, Rummens A . Predictive policing as a new tool for law enforcement? Recent developments and challenges[J]. European Journal on Criminal Policy and Research, 2018,24(3):201-218.
doi: 10.1007/s10610-017-9361-2 |
[5] |
Sherman L W, Gartin P R, Buerger M E . Hot spots of predatory crime: Routine activities and the criminology of place[J]. Criminology, 1989,27(1):27-56.
doi: 10.1111/crim.1989.27.issue-1 |
[6] | Farrell G, K Pease . Once Bitten, Twice Bitten: Repeat Victimisation and Its Implications for Crime Prevention[M]. London: Police Research Group, 1993. |
[7] |
Clarke R V, Cornish D B . Modeling offenders' decisions: A framework for research and policy[J]. Crime and Justice, 1985,6:147-185.
doi: 10.1086/449106 |
[8] |
Cohen L E, Felson M . Social change and crime rate trends: A routine activity approach[J]. American Sociological Review, 1979,44(4):588-608.
doi: 10.2307/2094589 |
[9] | Clarke R V, Cornish D B. Crime control in Britain: A review of policy research[M]. New York: SUNY Press, 1983. |
[10] | Brantingham P J, Brantingham P L . Environmental criminology[M]. Beverly Hills, C A: Sage Publications, 1981. |
[11] |
Brantingham P L, Brantingham P J . Nodes, paths and edges: Considerations on the complexity of crime and the physical environment[J]. Journal of Environmental Psychology, 1993,13(1):3-28.
doi: 10.1016/S0272-4944(05)80212-9 |
[12] | 李国军 . 预测警务的理论基础与技术路径研究[J]. 湖北警官学院学报, 2016,29(5):79-86. |
[ Li G J . Research on theoretical basis and technical path of predictive policing[J]. Journal of Hubei University of Police, 2016,29(5):79-86.] | |
[13] | Richard Wortley, Michael Townsley . Environmental criminology and crime analysis[M]. New York: Taylor& Francis, 2016. |
[14] |
Polvi N, Looman T, Humphries C , et al. The time course of repeat burglary victimization[J]. The British Journal of Criminology, 1991,31(4):411-414.
doi: 10.1093/oxfordjournals.bjc.a048138 |
[15] |
Townsley M, Homel R, Chaseling J . Infectious burglaries. A test of the near repeat hypojournal[J]. British Journal of Criminology, 2003,43(3):615-633.
doi: 10.1093/bjc/43.3.615 |
[16] | ChaineyS, Ratcliffe J . Identifying crime hotspots[M]. England: John Wiley & Sons Ltd, 2013. |
[17] | Kalinic M, Krisp J M. Kernel Density Estimation (KDE) vs. hot-spot analysis-detecting criminal hot spots in the city of San Francisco [C]. Proceeding of the 21 Conference on Geo-Information Science, 2018. |
[18] |
Bowers K J, Johnson S D, Pease K . Prospective hot-spotting: the future of crime mapping?[J]. British Journal of Criminology, 2004,44(5):641-658.
doi: 10.1093/bjc/azh036 |
[19] |
徐冲, 柳林, 周素红 . 基于临近相似性考虑的犯罪热点密度图预测准确性比较——以DP半岛街头抢劫犯罪为例[J]. 地理科学, 2016,36(1):55-62.
doi: 10.1329/j.cnki.sgs.2016.01.007 |
[ Xu C, Liu L, Zhou S H . The comparison of predictive accuracy of crime hotspot density maps with the consideration of the near similarity:acase study of robberies at DP peninsula[J]. Scientia Geographica Sinica, 2016,36(1):55-62.] | |
[20] | Daley D J, Vere-Jones D . An introduction to the theory of point processes[M]. New York: Springer, 2003. |
[21] |
Zhuang J . Second order residual analysis of spatiotemporal point processes and applications in model evaluation[J]. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 2006,68(4):635-653.
doi: 10.1111/rssb.2006.68.issue-4 |
[22] |
Marsan D, Lengline O . Extending earthquakes' reach through cascading[J]. Science, 2008,319(5866):1076-1079.
doi: 10.1126/science.1148783 pmid: 18292339 |
[23] |
Mohler G O, Short M B, Brantingham P J , et al. Self-exciting point process modeling of crime[J]. Journal of the American Statistical Association, 2011,106(493):100-108.
doi: 10.1198/jasa.2011.ap09546 |
[24] |
D'Orsogna M R, Perc M . Statistical physics of crime: A review[J]. Physics of Life Reviews, 2015,12:1-21.
doi: 10.1016/j.plrev.2014.11.001 pmid: 25468514 |
[25] | Olligschlaeger A M . Artificial neural networks and crime mapping[J]. Crime Mapping and Crime Prevention, 1997,8(3):313-348. |
[26] |
Corcoran J J, Wilson I D, Ware J A . Predicting the geo-temporal variations of crime and disorder[J]. International Journal of Forecasting, 2003,19(4):623-634.
doi: 10.1016/S0169-2070(03)00095-5 |
[27] |
Gorr W L, Lee Y J . Early warning system for temporary crime hot spots[J]. Journal of Quantitative Criminology, 2015,31(1):25-47.
doi: 10.1007/s10940-014-9223-8 |
[28] | 柳林, 刘文娟, 廖薇薇 , 等. 基于随机森林和时空核密度方法的不同周期犯罪热点预测对比[J]. 地理科学进展, 2018,37(6):25-35. |
[ Liu L, Liu W J, Liao W W , et al. Comparison of random forest algorithm and space-time kernel density mapping for crime hotspot prediction[J]. Progress in Geography, 2018,37(6):761-771.] | |
[29] | 柳林, 纪佳楷, 宋广文 , 等. 基于犯罪空间分异和建成环境的公共场所侵财犯罪热点预测[J]. 地球信息科学学报, 2019,21(11):1655-1668. |
[ Liu L, Ji J K, Song G W , et al. Hotspot prediction of public property crime based on spatial differentiation of crime and built environment[J]. Journal of Geo-information Science, 2019,21(11):1655-1668.] | |
[30] | Duan L, Hu T, Cheng E , et al. Deep convolutional neural networks for spatiotemporal crime prediction[C]. Proceedings of the International Conference on Information and Knowledge Engineering (IKE). The Steering Committee of The World Congress in Computer Science, Computer Engineering and Applied Computing (WorldComp), 2017. |
[31] | Stec A, Klabjan D . Forecasting crime with deep learning[J]. arXiv preprint arXiv:1806.01486, 2018. |
[32] | Yi F, Yu Z, Zhuang F , et al. Neural network based continuous conditional random field for fine-grained crime prediction [C]. Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI, 2019. |
[33] | Cortez B, Carrera B, Kim Y J , et al. An architecture for emergency event prediction using LSTM recurrent neural networks[J]. Expert Systems with Applications, 2018,97(1):315-324. |
[34] | 沈寒蕾, 张虎, 张耀峰 , 等. 基于长短期记忆模型的入室盗窃犯罪预测研究[J]. 统计与信息论坛, 2019,34(11):107-115. |
[ Shen H L, Zhang H, Zhang Y F , et al. Prediction of burglary crime based on LSTM[J]. Statistics & Information Forum, 2019,34(11):107-115.] | |
[35] | Wortley R K, Mazerolle L A . Environmental criminology and crime analysis: situating the theory, analytic approach and application[J]. Crime Prevention & Community Safety, 2009,11(2):1-15. |
[36] | 陈鹏, 李欣, 胡啸峰 , 等. 北京市长安街沿线的扒窃案件高发区分析及防控对策[J]. 地理科学进展, 2015,34(10):1250-1258. |
[ Chen P, Li X, Hu X F , et al. Clustering pattern analysis and prevention strategies to pickpocketing offence along the Chang'an Street in Beijing[J]. Progress In Geography, 2015,34(10):1250-1258.] | |
[37] | Caplan J M, Kennedy L W . Risk terrain modeling manual: Theoretical framework and technical steps of spatial risk assessment for crime analysis[M]. New Jersey: Rutgers Center on Public Security, 2010. |
[38] | Kennedy L W, Caplan J M, Piza E . Risk clusters, hotspots, and spatial intelligence: Risk terrain modeling as an algorithm for police resource allocation strategies[J]. Journal of Quantitative Criminology, 2011,27(3):339-362. |
[39] | 张宁, 王大为 . 基于风险地形建模的毒品犯罪风险评估和警务预测[J]. 地理科学进展, 2018,37(8):1131-1139. |
[ Zhang N, Wang D W . Drug-related crime risk assessment and predictive policing based on risk terrain modeling[J]. Progress in Geography, 2018,37(8):1131-1139.] | |
[40] | Fotheringham A S, Rogerson P A . The SAGE handbook of spatial analysis[M]. New York: Sage, 2009. |
[41] | Cohen J, Nagin D, Wallstrom G , et al. Hierarchical bayesian analysis of arrest rates[J]. Journal of the American Statistical Association, 1998,93(444):1260-1270. |
[42] | Berry D A, Evett I W, Pinchin R . Statistical inference in crime investigations using deoxyribonucleic acid profiling[J]. Applied Statistics, 1992,41(3):499-531. |
[43] | Law J, Haining R . A Bayesian approach to modeling binary data: The case of high-intensity crime areas[J]. Geographical Analysis, 2004,36(3):197-216. |
[44] | Wheeler D C, Waller L A . Comparing spatially varying coefficient models: a case study examining violent crime rates and their relationships to alcohol outlets and illegal drug arrests[J]. Journal of Geographical Systems, 2009,11(1):1-22. |
[45] | Law J, Quick M . Exploring links between juvenile offenders and social disorganization at a large map scale: A Bayesian spatial modeling approach[J]. Journal of Geographical Systems, 2013,15(1):89-113. |
[46] | Marchant R, Haan S, Clancey G , et al. Applying machine learning to criminology: semi-parametric spatial-demographic Bayesian regression[J]. Security Informatics, 2018,7(1):1-19. |
[47] | Law J, Quick M, Chan P . Bayesian spatio-temporal modeling for analysing local patterns of crime over time at the small-area level[J]. Journal of Quantitative Criminology, 2014,30(1):57-78. |
[48] | Hu T, Zhu X, Duan L , et al. Urban crime prediction based on spatio-temporal Bayesian model[J]. PloS One, 2018,13(10):1-18. |
[49] | 何晓群 . 现代统计分析方法与应用[M]. 北京: 中国人民大学出版社, 2016. |
[ He X Q. Modern statistical analysis methods and applications[M]. Beijing: China Renmin University Press, 2016.] | |
[50] | Bernasco W, Nieuwbeerta P . How do residential burglars select target areas? A new approach to the analysis of criminal location choice[J]. British Journal of Criminology, 2005,45(3):296-315. |
[51] | Bernasco W, Block R . Where offenders choose to attack: A discrete choice model of robberies in Chicago[J]. Criminology, 2009,47(1):93-130. |
[52] | Bernasco W . Modeling micro-level crime location choice: Application of the discrete choice framework to crime at places[J]. Journal of Quantitative Criminology, 2010,26(1):113-138. |
[53] | Baudains P, Braithwaite A, Johnson S D . Target choice during extreme events: A discrete spatial choice model of the 2011 London riots[J]. Criminology, 2013,51(2):251-285. |
[54] | Picasso E, Cohen M A . Valuing the public's demand for crime prevention programs: A discrete choice experiment[J]. Journal of Experimental Criminology, 2019,15(4):529-550. |
[55] | Ge L, Liu J, Zhou A , et al. Crime rate inference using tensor decomposition [C]. Guangdong: IEEE, 2018. |
[56] | Kolda T G, Bader B W . Tensor decompositions and applications[J]. SIAM Review, 2009,51(3):455-500. |
[57] | 段炼, 党兰学, 胡涛 , 等. 融合历史犯罪数据的疑犯社会活动位置预测[J]. 地球信息科学学报, 2018,20(7):929-938. |
[ Duan L, Dang L X, Hu T , et al. Mobility prediction of suspect based on historical crime records[J]. Journal of Geo-information Science, 2018,20(7):929-938.] | |
[58] | Rummens A, Hardyns W, Pauwels L . The use of predictive analysis in spatiotemporal crime forecasting: building and testing a model in an urban context[J]. Applied Geography, 2017,86(1):255-261. |
[59] | Huang C, Zhang J, Zheng Y , et al. DeepCrime: Attentive hierarchical recurrent networks for crime prediction [C]. Torino: Proceedings of the 27 th ACM International Conference on Information and Knowledge Management , 2018. |
[60] | Wang B, Luo X, Zhang F , et al. Graph-based deep modeling and real time forecasting of sparse spatio-temporal data[J]. ArXiv Preprint ArXiv: 1804.00684, 2018. |
[61] | 潘仲赢 . 基于机器学习算法的犯罪预警系统设计与实现[D]. 成都:电子科技大学, 2019. |
[ Pan Z Y . Design and implementation of crime early warning system based on machine learning algorithm[D]. Chendu: University of Electronic Science and Technology of China, 2019.] | |
[62] | Bevis C, Nutter J B . Changing street layouts to reduce residential burglary[M]. Minnesota: Minnesota Crime Prevention Center, 1977. |
[63] | Beavon D J K, Brantingham P L, Brantingham P J . The influence of street networks on the patterning of property offenses[J]. Crime Prevention Studies, 1994,2:115-148. |
[64] | Shu S, Huang J . Spatial configuration and vulnerability of residential burglary: A case study of a city in Taiwan [C]. London: International Space Syntax Symposium, 2003. |
[65] | Davies T, Johnson S D . Examining the relationship between road structure and burglary risk via quantitative network analysis[J]. Journal of Quantitative Criminology, 2015,31(3):481-507. |
[66] | Hillier B, Shu S C . Crime and urban layout: the need for evidence [C]. London: IPPR, 2000. |
[67] | Hillier B . Can streets be made safe?[J]. Urban Design International, 2004,9(1):31-45. |
[68] | Hillier B, Sahbaz O . An evidence based approach to crime and urban design, or, can we have vitality, sustainability and security all at once[R]. London:Routledge, 2008. |
[69] | Johnson S D, Bowers K J . Permeability and burglary risk: are cul-de-sacs safer?[J]. Journal of Quantitative Criminology, 2010,26(1):89-111. |
[70] | Summers L, Johnson S D . Does the configuration of the street network influence where outdoor serious violence takes place? using space syntax to test crime pattern theory[J]. Journal of Quantitative Criminology, 2017,33(2):397-420. |
[71] | Kim H J, Choi Y . A study on the influence of the space syntax and the urban characteristics on the incidence ofcrime using negative binomial regression[J]. Journal of The Korean Society of Civil Engineers, 2016,36(2):333-340. |
[72] |
Rosser G, Davies T, Bowers K J , et al. Predictive crime mapping: arbitrary grids or street networks?[J]. Journal of Quantitative Criminology, 2017,33(3):569-594.
pmid: 32025086 |
[73] | Davies T P, Bishop S R . Modelling patterns of burglary on street networks[J]. Crime Science, 2013,2(1):1-14. |
[74] | Zhang Y, Cheng T . Graph deep learning model for network-based predictive hotspot mapping of sparse spatio-temporal events[J]. Computers, Environment and Urban Systems, 2020,79(1):1-12. |
[75] | Lu Y, Chen X . On the false alarm of planar K-function when analyzing urban crime distributed along streets[J]. Social Science Research, 2007,36(2):611-632. |
[76] | Godwin A, Stasko J T . Nodes, paths, and edges: using mental maps to augment crime data analysis in urban spaces [C]. Barcelona: Eurographics/IEEE VGTC Conference on Visualization, 2017. |
[77] | Shiode S . Street-level spatial scan statistic and STAC for analysingstreet crime concentrations[J]. Transactions in GIS, 2011,15(3):365-383. |
[78] | Shiode S, Shiode N . Network-based space-time search-window technique for hotspot detection of street-level crime incidents[J]. International Journal of Geographical Information Science, 2013,27(5):866-882. |
[79] | Shiode S, Shiode N, Block R , et al. Space-time characteristics of micro-scale crime occurrences: an application of a network-based space-time search window technique for crime incidents in Chicago[J]. International Journal of Geographical Information Science, 2015,29(5):697-719. |
[80] | Song G, Bernasco W, Liu L , et al. Crime feeds on legal activities: daily mobility flows help to explain thieves’ target location choices[J]. Journal of Quantitative Criminology, 2019,35(4):831-854. |
[81] | Song G, Liu L, Bernasco W , et al. Testing indicators of risk populations for theft from the person across space and time: the significance of mobility and outdoor activity[J]. Annals of the American Association of Geographers, 2018,108(5):1370-1388. |
[82] |
Kadar C, Pletikosa I . Mining large-scale human mobility data for long-term crime prediction[J]. EPJ Data Science, 2018,7(1):1-27.
doi: 10.1140/epjds/s13688-017-0128-2 |
[83] | Zhao X, Tang J . Modeling temporal-spatial correlations for crime prediction [C]. New York: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, 2017. |
[84] | Wang H, Kifer D, Graif C , et al. Crime rate inference with big data [C]. San Francisco, Calif: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. 2016: 635-644. |
[85] |
Wang H, Yao H, Kifer D , et al. Non-stationary model for crime rate inference using modern urban data[J]. IEEE Transactions on Big Data, 2017,5(2):180-194.
doi: 10.1109/TBDATA.2017.2786405 pmid: 31172020 |
[86] | Rumi S K, Luong P, Salim F D . Crime rate prediction with region risk and movement patterns[J]. arXiv preprint arXiv: 1908.02570, 2019. |
[87] | 李卫红, 闻磊, 陈业滨 . 改进的GA-BP神经网络模型在财产犯罪预测中的应用[J]. 武汉大学学报·信息科学版, 2017,42(8):1110-1116,1171. |
[ Li H W, Wen L, Chen Y B . Property crime forecast based on improved GA-BP neural network model[J]. Geomatics and Information Science of Wuhan University, 2017,42(8):1110-1116,1171.] | |
[88] | 徐志刚 . 专论:公安大数据应用期待观念更新[J]. 人民公安, 2019,68(10):13-13. |
[ Xu Z G . Characteristic analysis of police big data[J]. People's Police, 2019,68(10):13-13.] |
[1] | 李晓恩, 周亮, 肖杨, 吴文周, 苏奋振, 石伟. 基于渔船AIS数据的南海北部海洋渔业捕捞强度空间特征挖掘[J]. 地球信息科学学报, 2021, 23(5): 850-859. |
[2] | 刘亚溪, 宋辞, 刘起勇, 张知新, 王席, 马佳, 陈晓, 裴韬. 重庆市新型冠状病毒肺炎流行时空特征及其与人群活动性的关系[J]. 地球信息科学学报, 2021, 23(2): 222-235. |
[3] | 王志华, 杨晓梅, 周成虎. 面向遥感大数据的地学知识图谱构想[J]. 地球信息科学学报, 2021, 23(1): 16-28. |
[4] | 宋关福, 陈勇, 罗强, 武梦瑶. GIS基础软件技术体系发展及展望[J]. 地球信息科学学报, 2021, 23(1): 2-15. |
[5] | 邬明权, 王标才, 牛铮, 黄文江. 工程项目地球大数据监测与分析理论框架及研究进展[J]. 地球信息科学学报, 2020, 22(7): 1408-1423. |
[6] | 黄洁, 王姣娥. 交通大数据在人文与经济地理学的应用及学科影响[J]. 地球信息科学学报, 2020, 22(6): 1180-1188. |
[7] | 姚可桢, 岳书平. 网络大数据下的中国现代食甜习惯空间分布特征及其影响因素研究[J]. 地球信息科学学报, 2020, 22(6): 1202-1215. |
[8] | 孙威, 林晓娜. 柳州市汽车制造业企业的空间格局与影响因素[J]. 地球信息科学学报, 2020, 22(6): 1216-1227. |
[9] | 李涛, 王姣娥, 黄洁. 基于腾讯迁徙数据的中国城市群国庆长假城际出行模式与网络特征[J]. 地球信息科学学报, 2020, 22(6): 1240-1253. |
[10] | 赵韶雅, 杨星斗, 戴特奇, 张超. 基于刷卡数据的公共汽车客流网络复杂性日内变化研究[J]. 地球信息科学学报, 2020, 22(6): 1254-1267. |
[11] | 杜德林, 黄洁, 王姣娥. 基于多源数据的中国智慧城市发展状态评价[J]. 地球信息科学学报, 2020, 22(6): 1294-1306. |
[12] | 陈芳淼, 黄慧萍, 贾坤. 时空大数据在城市群建设与管理中的应用研究进展[J]. 地球信息科学学报, 2020, 22(6): 1307-1319. |
[13] | 湛东升, 谢春鑫, 张文忠, 丁亮, 许婧雪, 甄茂成. 基于累计机会可达性的北京城市公共服务设施复合功能识别[J]. 地球信息科学学报, 2020, 22(6): 1320-1329. |
[14] | 杨雅萍, 姜侯, 孙九林. 科学数据共享实践:以国家地球系统科学数据中心为例[J]. 地球信息科学学报, 2020, 22(6): 1358-1369. |
[15] | 赵耀龙, 巢子豪. 历史GIS的研究现状和发展趋势[J]. 地球信息科学学报, 2020, 22(5): 929-944. |
|