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 geo-referenced data. To this end a Spatial Data Mining System, 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. By adapting methods from Machine Learning and Bayesian Statistics to spatial data analysis 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 visualisation of spatial and temporal information. SPIN will be tested and evaluated by applications to seismic and volcano data analysis and to the web-based dissemination of census data.
- To develop a generic system architecture that integrate state of the art GIS and DMS functionality in an open, extensible, internet-enabled plug-in architecture.
- To adapt Machine learning methods, especially first-order learning methods to spatial data mining.
- To adapt Bayesian Markov Chain Monte Carlo to spatial data mining.
- To adapt and integrate methods for spatial pattern analysis using techniques from exploratory spatial data analysis, statistics and artificial intelligence.
- To develop newmmethods for the visualisation of temporal and spatial data.
- To develop new methods for visualising data mining results in GIS .
- To apply SPIN to web-based dissemination of census data and the analysis of seismic and volcano data.
- To develop an innovative business model for web-based information and service brokering with geo-referenced data.