Use this URL to cite or link to this record in EThOS: http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.565549
Title: Towards real-time geodemographic information systems : design, analysis and evaluation
Author: Adnan, M.
Awarding Body: University College London (University of London)
Current Institution: University College London (University of London)
Date of Award: 2011
Availability of Full Text:
Access through EThOS:
Access through Institution:
Abstract:
Geodemographic classifications provide discrete indicators of the social, economic and demographic characteristics of people living in small neighbourhood areas. They have been regarded as products, which are the final 'best' outcome that can be achieved using available data and algorithms. However, reduction in the cost of geocomputation, increased network bandwidths and increasingly accessible spatial data infrastructures have together created the potential for the creation of classifications in near real-time within distributed environments. Current geodemographic classifications are said to be 'closed' in nature due to the data and algorithms used. This thesis is a step towards an open geodemographic information system that allows users to specify the importance of their selected variables and then perform a range of statistical analysis functions which are necessary to create classifications tailored to user requirements. This thesis discusses the socio-economic data sources currently used in the creation of geodemographic classifications, and explains the work towards the creation of a non-conventional data sources arising out of the UCL's surname database. Such data sources are seen as key to the creation of tailor made classifications. The thesis explains and compares different cluster analysis techniques for the segmentation of geodemographic classifications. The development of an online information system employs an optimisation of k-means clustering algorithm. This optimisation uses CUDA (Computer Unified Development Architecture) for parallel processing of computationally expensive k-means on NVIDIA's graphics cards. The concluding chapters of the thesis set out the architecture of a real-time geodemographic information system. The thesis also presents the results of the creation of bespoke local area classifications. The developmental work culminates in a pilot real-time geodemographic information system for the specification, estimation and testing of classifications on the fly.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID: uk.bl.ethos.565549  DOI: Not available
Share: