Proposal Summary

Abstract (max. 1000 characters incl. blanks)

The main objective of the SPIN! project is to support statistical offices in their timely and cost effective dissemination of statistical data and to offer exciting new possibilities for the scientific analysis of georeferenced data. To this end a Spatial Data Mining Ssystem, SPIN, is developed. It integrates state of the art Geographic Information Systems (GIS) and Data Mining Systems (DMS) functionality in an open, highly extensible, internet-enabled plug-in architecture. The state of the art in Data Mining will be advanced bBy adapting methods from Machine Learning and Bayesian Statistics to spatial data analysis will advance the state of the art in Data Mining will be advanced. The state of the art in GIS will also be advanced by developing new methods for the visualiszation of spatial and temporal information. The SPIN! spatial mining system will be tested and evaluated by

in applications to seismic and volcano data analysis and to the web-based dissemination of census data.

Objectives (max. 1000 characters incl. blanks)

  • To dDevelop a generic system architecture that integrate state of the art GIS and Data MSining functionality in an open, extensible, internet- enabled plug-in architecture.
  • To aAdapt Machine learning methods, especially first-order learning methods to spatial data mining.
  • To aAdapt Bayesian Markov Chain Monte Carlo to spatial data mining.
  • To aAdapt and integrate methods for spatial pattern analysis using techniques from exploratory spatial data analysis, statistics and artificial intelligence.
  • To dDevelop new methods for the visualiszation of temporal and spatial data.
  • To dDevelop new methods for visualizsingation ofDdata Mmining results within GIS.

To aApply SPINsystemto web-based dissemination of census data and the analysis ofto seismic and volcano data.analysis.

  • To aApply system to web-based dissemination of census data
  • To dDevelop an innovative business model for web- based information and service brokering with georeferenced data.

Description of Work (max. 2000 characters incl. blanks)

Data mining systems (DMS) and GIS are complementary tools for describing, transforming, analysing and modelling data about real world systems. The rapidly expanding market for theseDMS and GIS technologies is driven by pressure from the public sector, environmental agencies and industry to provide innovative solutions to a wide range of different problems. Most contemporary GIS have only very basic spatial analysis and data mining functionality and many are confined to analysis that involves comparing maps and descriptive statistical displays, such as like histograms or pie charts. Data mining techniques offer great potential benefits for the applied GIS based decision making that takes place in public and private sector organisations. An integrated, user friendly SDMS available on the internet offers exciting new possibilities for spatial decision making and geographical researchexploratory spatial data analysis and modelling for to a wide range of potential users involved in spatial analysis and decision making.

The overall objective of this proposal is to develop a web-based SDMS by integrating state of the art GIS and DMS functionality in a closely coupled open and extensible system architecture. In recent years, a number of project partners have developed the technological components and scientific tools required at the kernel for the core of such a system. During SPIN!this project these individual efforts and the associated expertise and experience will be united in a joint European effort. In itthis we will develop the missing pieces and build a truly integrated, internet enabled GIS-DMS platform, SPIN!, a comprehensive, coherent, Sspatial Ddata Mmining Ssystem (SDMS) for data of public interest. Partners from statistical offices and seismic research centres will use the system in applied research and provide feedback to direct the development efforts. These applied uses of the technology willshould demonstrate the generic utility and benefits of this type of system such a SDMS over contemporary technology. Industrial partners will develop a business model for web-based information brokering with georeferenced statistical data, and estimate the likely economic impact of the technology. The benefits of such a generic spatial data analysis system are wide ranging offering advantages to statistical analysts, environmental decision makers, seismic data experts, biodiversity researchers and the like.

Milestones and expected results (max. 500 characters incl. blanks)

The main result of the project will be a Spatial Data Mining System offering an unprecedented variety of visualiszation and spatial analysis tools. The aAdaption of Data Mining methods to spatial analysis will open up

new research and application domains and . Nnew visualization methods will advance the state of the art in GIS.

Milestones:

M1 Developer’s version of a SDMSspatial mining system (month 12)

M2First prototype (month 18)

M3Second prototype (month 30)

M4Dissemination workshop targeting additional user groups (36)