UNIVERSITY AT BUFFALO - STATE UNIVERSITY OF NEW YORK
The Department of Computer Science & Engineering
cse@buffalo
SNeRG home page

SNePS Information Fusion Projects

Information fusion is a process for associating, correlating, and combining data and information from single and multiple sources to achieve refined estimates of characteristics, events, and behaviors for observed entities in an observed field of view. Several joint projects have been undertaken by SNePS researchers and information fusion researchers at the Center for Multisource Information Fusion. These projects have typically focused on introducing reasoning techniques to information fusion processes in order to draw conclusions about entities observed from an information fuion process. Recent, projects have started to focus on aiding soft information fusion by automatically creating SNePS propositiona graphs from natural language data.
Contents
Cyber Security Project
Counterinsurgency Projects

Cyber Security Project

The Cyber Security Project used information fusion techniques on network analysis sensors in order to produce refined data estimates about network traffic. Databases about network attack types and identifiers were used to create knowledge bases that could be used to reason about similarities between attack types in order to perform connonicalization. SNePS research focused on utilizing Topbraid as knowledge base and Pellet as a reasoner over SNePS. An efficiency report for SNePS was also conducted in order to address working with large-scale knowledge repositories.

Relevant Publications:

  1. Michael Kandefer, Stuart Shapiro, Adam Stotz, and Moises Sudit, Symbolic Reasoning in the Cyber Security Domain, Proceedings of MSS 2007 National Symposium on Sensor and Data Fusion McLean, VA, June 2007.

  2. Michael Kandefer and Stuart C. Shapiro, Comparing SNePS with Topbraid/Pellet, SNeRG Technical Note 42, State University of New York at Buffalo, Buffalo, NY, July 18, 2008.

  3. A. Patrice Seyed, Michael Kandefer, and Stuart C. Shapiro, SNePS Efficiency Report, SNeRG Technical Note 43, State University of New York at Buffalo, Buffalo, NY, July 18, 2008.

  4. Michael Kandefer, A. Patrice Seyed, and Stuart C. Shapiro, The Use of SNePS for Cyber Security Reasoning, SNeRG Technical Note 44, State University of New York at Buffalo, Buffalo, NY, July 18, 2008.

Counterinsurgency Projects

The counter insurgency (COIN) projects have focused on taking sensor data, using information techniques on that data, and then using the SNePS reasoner to conclude information about the domain using the "fused" information. The first COIN project involved reasoning about anomalous behavior in shipping lanes using sonar data. The goal was to conclude whether swarms of small boats may be engaged in an attack against the shipping lanes. To aid in this process large-scale ontologies were employed as background information and a method for managing large scale knowledge sources using context was developed, called context-based information retrieval (CBIR).

The second, ongoing project, part of the project called Unified Research on Network-based Hard+Soft Information Fusion, has focused on processing natural language utterances in a COIN domain in order to produce SNePS propositional graph representations of those messages. The messages are taken from field operatives and generally indicate the activities of suspected insurgents. The raw messages are processed using the GATE text processing suite. The propositional graphs created are enhanced by CBIR with relevant background knowledge from VerbNet, WordNet, and the NGA GEOnet Names Server (GNS). The goal is to use these graphs to reason about insurgent activity and aid cross-message reference resolution.

Relevant Publications:

  1. Geoff A. Gross, Ketan Date, Daniel R. Schlegel, Jason J. Corso, James Llinas, Rakesh Nagi, and Stuart C. Shapiro, Systemic Test and Evaluation of a Hard+Soft Information Fusion Framework: Challenges and Current Approaches, Proceedings of the 17th International Conference on Information Fusion (Fusion 2014), IFIP, July, 2014, unpaginated, 8 pages.

  2. Stuart C. Shapiro, and Daniel R. Schlegel, Natural Language Understanding for Soft Information Fusion, Proceedings of the 16th International Conference on Information Fusion (Fusion 2013), IFIP, July, 2013, 9 pages, unpaginated.

  3. Geoff A. Gross, Rakesh Nagi, Kedar Sambhoos, Daniel R. Schlegel, Stuart C. Shapiro, and Gregory Tauer, Towards Hard+Soft Data Fusion: Processing Architecture and Implementation for the Joint Fusion and Analysis of Hard and Soft Intelligence Data, Proceedings of the 15th International Conference on Information Fusion (Fusion 2012), ISIF, 2012, 955-962.

  4. Michael Prentice and Stuart C. Shapiro, Using Propositional Graphs for Soft Information Fusion, Proceedings of the 14th International Conference on Information Fusion (Fusion 2011), ISIF, 2011, 522-528.

  5. Michael Kandefer and Stuart C. Shapiro, Evaluating Spreading Activation for Soft Information Fusion, Proceedings of the 14th International Conference on Information Fusion (Fusion 2011), ISIF, 2011, 498-505.

  6. Michael Prentice, Michael Kandefer, & Stuart C. Shapiro, Tractor: A Framework for Soft Information Fusion, Proceedings of the 13th International Conference on Information Fusion (Fusion 2010), ISIF, 2010, Th3.2.2, 8 pages, unpaginated.

  7. Juan Gómez-Romero, Jesús Garcia, Michael Kandefer, James Llinas, Jose Manuel Molina, Miguel Angel Patricio, Michael Prentice, & Stuart C. Shapiro, Strategies and Techniques for Use and Exploitation of Contextual Information in High-Level Fusion Architectures, Proceedings of the 13th International Conference on Information Fusion (Fusion 2010), ISIF, 2010, TH1.7.3, 8 pages, unpaginated.

  8. Michael Kandefer and Stuart C. Shapiro, An F-Measure for Context-Based Information Retrieval. In Gerhard Lakemeyer, Leora Morgenstern, and Mary-Anne Williams, Eds., Commonsense 2009: Proceedings of the Ninth International Symposium on Logical Formalizations of Commonsense Reasoning, The Fields Institute, Toronto, CA, 2009, 79-84.

  9. Michael Kandefer and Stuart C. Shapiro, A Categorization of Contextual Constraints. In Alexei Samsonovich, Ed., Biologically Inspired Cognitive Architectures: Papers from the AAAI Fall Symposium, Technical Report FS-08-04, AAAI Press, Menlo Park, CA, 2008, 88-93.

  10. Michael Kandefer and Stuart C. Shapiro, An F-Measure for Context-Based Information Retrieval. In Gerhard Lakemeyer, Leora Morgenstern, and Mary-Anne Williams, Eds., Commonsense 2009: Proceedings of the Ninth International Symposium on Logical Formalizations of Commonsense Reasoning, The Fields Institute, Toronto, CA, 2009, 79-84.

  11. Juan Gómez-Romero, Jesús Garcia, Michael Kandefer, James Llinas, Jose Manuel Molina, Miguel Angel Patricio, Michael Prentice, & Stuart C. Shapiro, Strategies and Techniques for Use and Exploitation of Contextual Information in High-Level Fusion Architectures, Proceedings of the 13th International Conference on Information Fusion, 2010, TH1.7.3, 8 pages, unpaginated.

  12. Michael Prentice, Michael Kandefer, & Stuart C. Shapiro, Tractor: A Framework for Soft Information Fusion, Proceedings of the 13th International Conference on Information Fusion, 2010, Th3.2.2, 8 pages, unpaginated.

Last modified: Thu Oct 23 15:04:28 2014
Michael W. Kandefer <mwk3@buffalo.edu>
TOP | BIBLIOGRAPHY | SCHEDULE | SNeRG HOME | HomeHOME