Agent-Based Knowledge Discovery for Modeling and Simulation
Abstract
This paper describes an approach to using agent technology to extend the automated discovery mechanism of the Knowledge Encapsulation Framework (KEF). KEF is a suite of tools to enable the linking of knowledge inputs (relevant, domain-specific evidence) to modeling and simulation projects, as well as other domains that require an effective collaborative workspace for knowledge-based tasks. This framework can be used to capture evidence (e.g., trusted material such as journal articles and government reports), discover new evidence (covering both trusted and social media), enable discussions surrounding domain-specific topics and provide automatically generated semantic annotations for improved corpus investigation. The current KEF implementation is presented within a semantic wiki environment, providing a simple but powerful collaborative space for team members to review, annotate, discuss and align evidence with their modeling frameworks. The novelty in this approach lies in the combination of automatically tagged and user-vetted resources, which increases user trust in the environment, leading to ease of adoption for the collaborative environment.
- Authors:
- Publication Date:
- Research Org.:
- Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 967217
- Report Number(s):
- PNNL-SA-66191
TRN: US200923%%188
- DOE Contract Number:
- AC05-76RL01830
- Resource Type:
- Conference
- Resource Relation:
- Conference: 2009 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology, September 15-18, 2009, Milan, Italy, 3:543-546
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICAL METHODS AND COMPUTING; 99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; K CODES; KNOWLEDGE BASE; MATHEMATICAL MODELS; COMPUTERIZED SIMULATION; agents; knowledge encapsulation
Citation Formats
Haack, Jereme N, Cowell, Andrew J, Marshall, Eric J, Fligg, Alan K, Gregory, Michelle L, and McGrath, Liam R. Agent-Based Knowledge Discovery for Modeling and Simulation. United States: N. p., 2009.
Web.
Haack, Jereme N, Cowell, Andrew J, Marshall, Eric J, Fligg, Alan K, Gregory, Michelle L, & McGrath, Liam R. Agent-Based Knowledge Discovery for Modeling and Simulation. United States.
Haack, Jereme N, Cowell, Andrew J, Marshall, Eric J, Fligg, Alan K, Gregory, Michelle L, and McGrath, Liam R. 2009.
"Agent-Based Knowledge Discovery for Modeling and Simulation". United States.
@article{osti_967217,
title = {Agent-Based Knowledge Discovery for Modeling and Simulation},
author = {Haack, Jereme N and Cowell, Andrew J and Marshall, Eric J and Fligg, Alan K and Gregory, Michelle L and McGrath, Liam R},
abstractNote = {This paper describes an approach to using agent technology to extend the automated discovery mechanism of the Knowledge Encapsulation Framework (KEF). KEF is a suite of tools to enable the linking of knowledge inputs (relevant, domain-specific evidence) to modeling and simulation projects, as well as other domains that require an effective collaborative workspace for knowledge-based tasks. This framework can be used to capture evidence (e.g., trusted material such as journal articles and government reports), discover new evidence (covering both trusted and social media), enable discussions surrounding domain-specific topics and provide automatically generated semantic annotations for improved corpus investigation. The current KEF implementation is presented within a semantic wiki environment, providing a simple but powerful collaborative space for team members to review, annotate, discuss and align evidence with their modeling frameworks. The novelty in this approach lies in the combination of automatically tagged and user-vetted resources, which increases user trust in the environment, leading to ease of adoption for the collaborative environment.},
doi = {},
url = {https://www.osti.gov/biblio/967217},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Tue Sep 15 00:00:00 EDT 2009},
month = {Tue Sep 15 00:00:00 EDT 2009}
}