全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...
-  2017 

基于地理信息的密度估计方法 Density Estimation Based on Geographic Information

Keywords: 地理信息,总变差,最大罚似然估计法

Full-Text   Cite this paper   Add to My Lib

Abstract:

对于给定的离散事件数据,可以生成一个概率密度分布图来刻画此类事件发生区域的相对概率.普通的方法如核密度估计法并不考虑与之对应的地理信息.在应用中这类方法会导致离散事件的概率密度出现在不切实际的地理位置.因此,本文提出了新的基于总变差的修正最大罚似然估计方法,不仅可以保证概率估计密度分布的光滑特性,还能确保事件的概率密度不会出现在无效区域.文中运用模拟的离散数据对现有的以及新的方法进行比较来验证新方法的优越性,之后结合真实的地理信息,将该方法运用到某城市的犯罪密度估计当中,验证其对于解决具体问题的可行性并给警方布控以指导

References

[1]  ROSSMO D K.Geographic Profiling[C]//Encyclopedia of Criminology and Criminal Justice.New York:Springer-Verlag,2014:1934-1942.DOI:10.1007/978-1-4614-5690-2_678.
[2]  GRIMM V,MCLACHLAN R I,MCLAREN D,et al.The Use of Discrete Gradient Methods for Total Variation Type Regularization Problems in Image Processing[DB/OL].[2016-09-13].https://arxiv.org/abs/1603.07515.
[3]  MAAS J,RUMPF M,SCHNLIEB C,et al.A generalized model for optimal transport of images including dissipation and density modulation[J].ESAIM:Mathematical Modelling and Numerical Analysis,2015,49(6):1745-1769.DOI:10.1051/m2an/2015043.
[4]  COMPTON R,JURGENS D,Allen D.Geotagging One Hundred Million Twitter Accounts with Total Variation Minimization[DB/OL].[2016-10-13].http://cs.stanford.edu/~jurgens/docs/compton-jurgens-allen_bigdata-2014.pdf.DOI:10.1109/BigData.2014.7004256.
[5]  MOHLER G O,SHORT M B.Geographic profiling from kinetic models of criminal behavior[J].SIAM Journal on Applied Mathematics,2012,72(1):163-180.DOI:10.1137/100794080.
[6]  BAUDAINS P J.Spatio-temporal Modelling of Civil Violence:Four Frameworks for Obtaining Policy-relevant Insights[D].London:UCL(University College London),2015.
[7]  EGGERMONT P P B,LARICCIA V N,LARICCIA V N.Maximum Penalized Likelihood Estimation[M].New York:Springer,2001.DOI:10.1007/b12285.
[8]  WOODWORTH J T,MOHLER G O,BERTOZZI A L,et al.Non-local crime density estimation incorporating housing information[J].Phil Trans R.Soc A,2014,372(2028):20130403.DOI:10.1098/rsta.2013.0403
[9]  MOHLER G O,BERTOZZI A L,GOLDSTEIN T A,et al.Fast TV regularization for 2d maximum penalized likelihood estimation[J].Journal of Computational and Graphical Statistics,2011,20(2):479-491.DOI:10.1198/jcgs.2010.09048.
[10]  SMITH L M,KEEGAN M S,WITTMAN T,et al.Improving density estimation by incorporating spatial information[J].EURASIP Journal on Advances in Signal Processing,2010,2010(1):1.DOI:10.1155/2010/265631.
[11]  CHAMBOLLE A.An algorithm for total variation minimization and applications[J].Journal of Mathematical Imaging and Vision,2004,20(1-2):89-97.DOI:10.1023/B:JMIV.0000011325.36760.1e.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133