Return to search

A Geographical Knowledge Representation System (GKRS)for Multimedia Geospatial Retrieval and Analysis

Artificial Intelligence Lab, Department of MIS, University of Arizona / Digital libraries serving multimedia information
that may be accessed in terms of geographic content
and relationships are creating special challenges and
opportunities for networked information systems. An
especially challenging research issue concerning collections
of geo-referenced information relates to the development
of techniques supporting geographic information
retrieval (GIR) that is both fuzzy and concept-based.
Viewing the meta-information environment of a digital
library as a heterogeneous set of services that support
users in terms of GIR, we define a geographic knowledge
representation system (GKRS) in terms of a core set of
services of the meta-information environment that is
required in supporting concept-based access to collections
of geospatial information. In this paper, we describe
an architecture for a GKRS and its implementation in
terms of a prototype system. Our GKRS architecture
loosely couples a variety of multimedia knowledge
sources that are in part represented in terms of the
semantic network and neural network representations
developed in artificial intelligence research. Both textual
analysis and image processing techniques are employed
in creating these textual and iconic geographcal knowledge
structures. The GKRS also employs spreading
activation algorithms in support of concept-based knowledge
retrieval. The- paper describes implementational
details of several of the components of the GKRS as well
as discussing both the lessons learned from, and future
directions of, our research.

Identiferoai:union.ndltd.org:arizona.edu/oai:arizona.openrepository.com:10150/105551
Date09 1900
CreatorsChen, Hsinchun, Smith, Terrence R., Larsgaard, Mary L., Hill, Linda L., Ramsey, Marshall C.
PublisherSpringer-Verlag
Source SetsUniversity of Arizona
LanguageEnglish
Detected LanguageEnglish
TypeJournal Article (Paginated)

Page generated in 0.0028 seconds