Intelligent spatial decision support systems

摘要

This thesis investigates the conceptual and methodological issues for the development ofudIntelligent Spatial Decision Support Systems (ISDSS). These are spatial decision supportudsystems (SDSS) integrating intelligent systems techniques (Genetic Algorithms, NeuraludNetworks, Expert Systems, Fuzzy Logic and Nonlinear methods) with traditional modelling andudstatistical methods for the analysis of spatial problems.udThe principal aim of this work is to verify the feasibility of heterogeneous systems forudspatial decision support derived from a combination of traditional numerical techniques andudintelligent techniques in order to provide superior performance and functionality to that achievedudthrough the use of traditional methods alone.udThis thesis is composed of four distinct sections: (i) a taxonomy covering theudemployment of intelligent systems techniques in specific applications of geographicaludinformation systems and SDSS; (ii) the development of a prototype ISDSS; (iii) application ofudthe prototype ISDSS to modelling the spatiotemporal dynamics of high technology industry inudthe South-East of England; and (iv) the development of ISDSS architectures utilisingudinterapplication communication techniques.udExisting approaches for implementing modelling tools within SDSS and GIS generallyudfall into one of two schemes - loose coupling or tight coupling - both of which involve a tradeoffudbetween generality and speed of data interchange. In addition, these schemes offer little useudof distributed processing resources.udA prototype ISDSS was developed in collaboration with KPMG Peat Marwick's HighudTechnology Practice as a general purpose spatiotemporal analysis tool with particular regard toudmodelling high technology industry. The GeoAnalyser system furnishes the user with animationudand time plotting tools for observing spatiotemporal dynamics; such tools are typically not foundudin existing SDSS or GIS. Furthermore, GeoAnalyser employs the client/server model ofuddistributed computing to link the front end client application with the back end modellingudcomponent contained within the server application. GeoAnalyser demonstrates a hybrid approachudto spatial problem solving - the application utilises a nonlinear model for the temporal evolutionudof spatial variables and a genetic algorithm for calibrating the model in order to establish a goodudfit for the dataset under investigation.udSeveral novel architectures are proposed for ISDSS based on existing distributed systemsudtechnologies. These architectures are assessed in terms of user interface, data and functionaludintegration. Implementation issues are also discussed.udThe research contributions of this work are four-fold: (i) it lays the foundation for ISDSSudas a distinct type of system for spatial decision support by examining the user interface,udperformance and methodological requirements of such systems; (ii) it explores a new approachudfor linking modelling techniques and SDSS; (iii) it investigates the possibility of modelling highudtechnology industry; and (iv) it details novel architectures for ISDSS based on distributedudsystems.