Bridging the gap between data acquisition and inference ontologies: toward ontology-based link discovery

Michel L. Goldstein; Steven A. Morris; Gary G. Yen

doi:10.1117/12.488853

22 September 2003 Bridging the gap between data acquisition and inference ontologies: toward ontology-based link discovery

Michel L. Goldstein, Steven A. Morris, Gary G. Yen

Author Affiliations +

Proceedings Volume 5071, Sensors, and Command, Control, Communications, and Intelligence (C3I) Technologies for Homeland Defense and Law Enforcement II; (2003) https://doi.org/10.1117/12.488853
Event: AeroSense 2003, 2003, Orlando, Florida, United States

Abstract

Bridging the gap between low level ontologies used for data acquisition and high level ontologies used for inference is essential to enable the discovery of high-level links between low-level entities. This is of utmost importance in many applications, where the semantic distance between the observable evidence and the target relations is large. Examples of these applications would be detection of terrorist activity, crime analysis, and technology monitoring, among others. Currently this inference gap has been filled by expert knowledge. However, with the increase of the data and system size, it has become too costly to perform such manual inference. This paper proposes a semi-automatic system to bridge the inference gap using network correlation methods, similar to Bayesian Belief Networks, combined with hierarchical clustering, to group and organize data so that experts can observe and build the inference gap ontologies quickly and efficiently, decreasing the cost of this labor-intensive process. A simple application of this method is shown here, where the co-author collaboration structure ontology is inferred from the analysis of a collection of journal publications on the subject of anthrax. This example uncovers a co-author collaboration structures (a well defined ontology) from a scientific publication dataset (also a well defined ontology). Nevertheless, the evidence of author collaboration is poorly defined, requiring the use of evidence from keywords, citations, publication dates, and paper co-authorship. The proposed system automatically suggests candidate collaboration group patterns for evaluation by experts. Using an intuitive graphic user interface, these experts identify, confirm and refine the proposed ontologies and add them to the ontology database to be used in subsequent processes.

Citation Download Citation

Michel L. Goldstein, Steven A. Morris, and Gary G. Yen "Bridging the gap between data acquisition and inference ontologies: toward ontology-based link discovery", Proc. SPIE 5071, Sensors, and Command, Control, Communications, and Intelligence (C3I) Technologies for Homeland Defense and Law Enforcement II, (22 September 2003); https://doi.org/10.1117/12.488853

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available