Creating a Large-Scale Digital Library for Georeferenced Information

Bin Zhu     bzhu@bpa.arizona.edu     (Management Information System Dept.)   Marshall Ramsey     mramsey@bpa.arizona.edu     (Management Information System Dept.)   Tobun D. Ng     tng@bpa.arizona.edu     (Management Information System Dept.)   Hsinchun Chen     hchen@bpa.arizona.edu     (Management Information System Dept.)   Bruce Schatz     schatz@canis.uiuc.edu     (CANIS LAB)

D-Lib Magazine ( web site)
(ReLIS:doi:dlibma:v:5:y:1999:i:7-8:p:2969)

Abstract:

Digital libraries with multimedia geographic content present special challenges and opportunities in today's networked information environment. One of the most challenging research issues for geospatial collections is to develop techniques to support fuzzy, concept-based, geographic information retrieval. Based on an artificial intelligence approach, this project presents a Geospatial Knowledge Representation System (GKRS) prototype that integrates multiple knowledge sources (textual, image, and numerical) to support concept-based geographic information retrieval. Based on semantic network and neural network representations, GKRS loosely couples different knowledge sources and adopts spreading activation algorithms for concept-based knowledge inferencing. Both textual analysis and image processing techniques have been employed to create textual and visual geographical knowledge structures. This paper suggests a framework for developing a complete GKRS-based system and describes in detail the prototype system that has been developed so far.

Month: July/August 1999

 (go top)