Please use this identifier to cite or link to this item: http://hdl.handle.net/10362/134616
Title: Street luminosity influence on reported thefts from vehicles during night-time
Author: Ventura, José Mario Roberto
Advisor: Costa, Ana Cristina Marinho da
Gould, Michael
Pesch, Mario
Keywords: Spatial analysis
Crime analysis
Crime patterns
Theft from vehicle crime
Street illuminance
Street light poles
Geographically Weighted Poisson Regression
Ordinary Least Squares Regression
Vancouver
SenseBox
SDG 16 - Peace, justice and strong institutions. Target 16.3 - Promote the rule of law at the national and international levels and ensure equal access to justice for all
Defense Date: 2-Mar-2022
Abstract: Criminality across many urban settings has created the need to develop tools that help better understand the social and physical determinants of crime. One specific aspect is how certain urban characteristics may influence criminal activities. One facet of the built environment, street lighting, influences the perception of safety for a potential victim, and it also influences a perpetrator´s risk analysis, affecting how it envisions both costs and rewards for committing a crime. The study looked into the relationship between street illuminance levels, through street light pole density as a proxy, and other crime determinants and the prevalence of reported Night-Time Theft from Vehicle crimes in Vancouver, BC, Canada, through exploratory spatial data analysis and by fitting Geographically Weighted Poisson Regressions. To test if street lighting pole density is a usable proxy for street illuminance it also modeled the relationship between street lighting pole and tree densities and measured night time street illuminance by fitting an Ordinary Least Squares regression. Night time street illuminance was measured using a specially built georeferenced mobile illuminance collection station based on the senseBox. Findings suggest that while a citywide effect is evident for some of the explanatory variables, there is an evident nonstationary relation between the explanatory variables and Night-Time Theft from Vehicle crimes in Vancouver. Regarding street lighting, regressions suggest it may not be an important covariate with Night-Time Theft from Vehicle crime. Coefficients are quite heterogenous throughout with most of the study area showing a mix of weak to mild positive association, specially on the East side, and weak to mild negative associations. The OLS regression showed a moderately weak relation between light poles and tree densities to collected street illuminance. The question of street lighting pole density being a usable proxy for street illuminance could not be answered with confidence.
Description: Dissertation submitted in partial fulfilment of the requirements for the Degree of Master of Science in Geospatial Technologies
URI: http://hdl.handle.net/10362/134616
Designation: Mestrado em Tecnologias Geoespaciais
Appears in Collections:NIMS - MSc Dissertations Geospatial Technologies (Erasmus-Mundus)

Files in This Item:
File Description SizeFormat 
TGEO0276.pdf22,54 MBAdobe PDFView/Open


FacebookTwitterDeliciousLinkedInDiggGoogle BookmarksMySpace
Formato BibTex MendeleyEndnote 

Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.