Bayesian non-parametric spatial prior for traffic crash risk mapping: A case study of Victoria, Australia

被引:2
作者
Durand, J-B [1 ]
Forbes, F. [1 ]
Phan, C. D. [2 ]
Truong, L. [2 ]
Nguyen, H. D. [2 ,3 ]
Dama, F. [1 ]
机构
[1] Univ Grenoble Alpes, INRIA, CNRS, Grenoble INP,LJK,Inria Grenoble Rhone Alpes, F-38335 Montbonnot St Martin, France
[2] La Trobe Univ, Sch Comp Engn & Math Sci, Bundoora, Vic, Australia
[3] Univ Queensland, Sch Math & Phys, St Lucia, Qld, Australia
关键词
Bayesian non-parametrics; Markov random field; risk mapping; road safety; traffic crashes; variational Bayes Expectation-Maximisation algorithm; MARKOV RANDOM-FIELD; MIXTURE-MODELS; DISEASE; FREQUENCY;
D O I
10.1111/anzs.12369
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
We develop a Bayesian non-parametric (BNP) model coupled with Markov random fields (MRFs) for risk mapping, to infer homogeneous spatial regions in terms of risks. In contrast to most existing methods, the proposed approach does not require an arbitrary commitment to a specified number of risk classes and determines their risk levels automatically. We consider settings in which the relevant information are counts and propose a so-called BNP hidden MRF (BNP-HMRF) model that is able to handle such data. The model inference is carried out using a variational Bayes expectation-maximisation algorithm and the approach is illustrated on traffic crash data in the state of Victoria, Australia. The obtained results corroborate well with the traffic safety literature. More generally, the model presented here for risk mapping offers an effective, convenient and fast way to conduct partition of spatially localised count data.
引用
收藏
页码:171 / 204
页数:34
相关论文
共 48 条
[1]   Spatial heterogeneity of the risk of BSE in France following the ban of meat and bone meal in cattle feed [J].
Abrial, D ;
Calavas, D ;
Jarrige, N ;
Ducrot, C .
PREVENTIVE VETERINARY MEDICINE, 2005, 67 (01) :69-82
[2]   Analysis of Road Crash Frequency with Spatial Models [J].
Aguero-Valverde, Jonathan ;
Jovanils, Paul P. .
TRANSPORTATION RESEARCH RECORD, 2008, (2061) :55-63
[3]   Finite Mixture Models for Mapping Spatially Dependent Disease Counts [J].
Alfo, Marco ;
Nieddu, Luciano ;
Vicari, Donatella .
BIOMETRICAL JOURNAL, 2009, 51 (01) :84-97
[4]   BAYESIAN IMAGE-RESTORATION, WITH 2 APPLICATIONS IN SPATIAL STATISTICS [J].
BESAG, J ;
YORK, J ;
MOLLIE, A .
ANNALS OF THE INSTITUTE OF STATISTICAL MATHEMATICS, 1991, 43 (01) :1-20
[5]   Variational Inference for Dirichlet Process Mixtures [J].
Blei, David M. ;
Jordan, Michael I. .
BAYESIAN ANALYSIS, 2006, 1 (01) :121-143
[6]  
Böhning D, 2000, STAT MED, V19, P2333, DOI 10.1002/1097-0258(20000915/30)19:17/18<2333::AID-SIM573>3.0.CO
[7]  
2-Q
[8]   On the Pitman-Yor process with spike and slab base measure [J].
Canale, A. ;
Lijoi, A. ;
Nipoti, B. ;
Prunster, I. .
BIOMETRIKA, 2017, 104 (03) :681-697
[9]   Fast Joint Detection-Estimation of Evoked Brain Activity in Event-Related fMRI Using a Variational Approach [J].
Chaari, Lotfi ;
Vincent, Thomas ;
Forbes, Florence ;
Dojat, Michel ;
Ciuciu, Philippe .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2013, 32 (05) :821-837
[10]  
Chandler D., 1987, INTRO MODERN STAT ME