C4I Center


   STIDS 2012 Home

   Topic list
  Program Committee
   Venue & Local info

   Keynote Speakers  
   Best Paper Award  
   Agenda & Papers  
   Download Agenda  

   Call for Papers  
   Important dates  
   Submission details  
   Download CFP  

   C4I Home



STIDS 2012

Schedule of Events

Wednesday, October 24th
08:00 - 09:00     Registration and Breakfast
09:00 - 09:10     Initial remarks - Paulo Costa, STIDS 2012 Co-Chair
09:10 - 09:30     Welcome - Mark Pullen, Director of the C4I Center
09:30 - 10:30     Keynote Address
Mike Dean
A Pragmatic View of the Semantic Web and Ontologies

I continue to be excited about the accomplishments and potential of the Semantic Web and related technologies. In this talk, I'll review some of those accomplishments, present some applications, discuss various emerging technologies (Wikidata, GeoSPARQL, SILK, PROV, Big Data, stream processing, etc.), identify some things that are still missing, and perhaps offer some predictions for the future. (Bio)

10:30 - 11:00     Break
11:00 - 12:00     Research Session   -    Chair: Dan Maxwell, KaDSci, Inc.
11:00 - 11:30     Using Ontologies in a Cognitive-Grounded System:
Automatic Action Recognition in Video-Surveillance
Paper        Presentation
Alessandro Oltramari,
Christian Lebiere
Carnegie Mellon University

This article presents an integrated cognitive system for automatic video-surveillance: in particular, we focus on the task of classifying the actions occurring in a scene. For this purpose, we developed a semantic infrastructure on top of a hybrid computational ontology of actions. The article outlines the core features of this infrastructure, illustrating how the processing mechanisms of the cognitive system benefit from knowledge capabilities in fulfilling the recognition goal. Ultimately, the paper demonstrates that ontologies can enhance a cognitive architecture's functionalities, allowing for high-level performance in complex task execution.

11:30 - 12:00     Horizontal Integration of Warfighter Intelligence Data:
A Shared Semantic Resource for the Intelligence Community
Paper        Presentation
Barry Smith (a),
Tatiana Malyuta (b),
William S. Mandrick (b),
Chia Fu (b),
Kesny Parent ( c),
Milan Patel (c)
a. University at Buffalo,
b. Data Tactics Corp.,
c. Intelligence and Information
Warfare Directorate (I2WD)

We describe a strategy that is being used for the horizontal integration of warfighter intelligence data within the framework of the US Army's Distributed Common Ground System Standard Cloud (DSC) initiative. The strategy rests on the development of a set of ontologies that are being incrementally applied to bring about what we call the 'semantic enhancement' of data models used within each intelligence discipline. We show how the strategy can help to overcome familiar tendencies to stovepiping of intelligence data, and describe how it can be applied in an agile fashion to new data resources in ways that address immediate needs of intelligence analysts.

12:00 - 13:30     Lunch
13:30 - 15:00     Research Session   -    Chair: Robert Schrag, Digital Sandbox, Inc.
13:30 - 14:00     Constellation: A Prototype ISO/IEC 11179 Metadata Registry
Paper        Presentation
Gramm Richardson(a),
Elli Schwarz(b)
a. US DOD and
b. SRA International

Different systems across the government, as well as in the private sector, use different country names or country codes to represent the notion of a "country" within a particular problem domain. These systems may choose to represent countries using a particular standard for county names and country codes. Often times these systems find themselves interacting with other systems that may use another standard for country representation. This makes it difficult to compare and link country-related data in a consistent fashion. We describe our work on the Constellation system using the ISO/IEC 111179 metadata standard to register the various country code sets in a common metamodel. This facilitates management, querying, updating and mapping the elements within the code sets.

14:00 - 14:30     The URREF Ontology for Semantic Wide Area
Motion Imagery Exploitation
Erik Blasch(a),
Paulo Costa (b),
Kathryn Laskey (b),
Haibin Ling ( c),
Genshe Chen (d)
a. Air Force Research Lab,
b. George Mason University,
c. Temple University,
d. Information Fusion Tech

Current advances operational information fusion systems (IFSs) require common semantic ontologies for collection, storage, and access to multi intelligence information. One example is the connections between physics-based (e.g. video) and text-based (e.g. reports) describing the same situation. Situation, user, and mission awareness are enabled through a common ontology. In this paper, we utilize the uncertainty representation and reasoning evaluation framework (URREF) ontology as a basis for describing wide-area motion imagery (WAMI) analysis to determine uncertainty attributes. As part of the Evaluation of Technologies for Uncertainty Representation Working Group (ETURWG), both the URREF and a WAMI challenge problem are available for research purposes from which we describe the URREF, a exemplar schema to link physics-based and text-based uncertainty representations, and explore an example from WAMI exploitation for a common uncertainty demonstration.

14:30 - 15:00     Developing an Ontology of the Cyber Security Domain
Paper        Presentation
Leo Obrst, Penny Chase,
Richard Markeloff
The MITRE Corporation

This paper reports on a trade study we performed to support the development of a Cyber ontology from an initial malware ontology. The goals of the Cyber ontology effort are first described, followed by a discussion of the ontology development methodology used. The main body of the paper then follows, which is a description of the potential ontologies and standards that could be utilized to extend the Cyber ontology from its initially constrained malware focus. These resources include, in particular, Cyber and malware standards, schemas, and terminologies that directly contributed to the initial malware ontology effort. Other resources are upper (sometimes called 'foundational') ontologies. Core concepts that any Cyber ontology will extend have already been identified and rigorously defined in these foundational ontologies. However, for lack of space, this section is profoundly reduced. In addition, utility ontologies that are focused on time, geospatial, person, events, and network operations are briefly described. These utility ontologies can be viewed as specialized super-domain or even mid-level ontologies, since they span many, if not most, ontologies -- including any Cyber ontology. An overall view of the ontological architecture used by the trade study is also given. The report on the trade study concludes with some proposed next steps in the iterative evolution of the Cyber ontology.

15:00 - 15:30     Break
15:30 - 17:00     Research Session   -   Chair: Charles Twardy, George Mason University
15:30 - 16:00     Ontological Considerations for Uncertainty Propagation
in High Level Information Fusion
Paper        Presentation
Mark Locher(a,b),
Paulo Costa(a)
a. GMU and
b. SRA International

Uncertainty propagation in a level 2 high level information fusion (HLIF) process is affected by a number of considerations. These include the varying complexities of the various types of level 2 HLIF. Five different types are identified, ranging from simple entity attribute refinement using situation status data to the development of a complete situation assessment assembled from applicable situational fragment data. Additional considerations include uncertainty handling in the input data, uncertainty representation, the effects of the reasoning technique used in the fusion process, and output considerations. Input data considerations include the data's relevance to the situation, its credibility, and its force or weight. Uncertainty representation concerns follow the uncertainty ontology developed by the W3C Incubator Group on Uncertainty Reasoning. For uncertainty effects of the fusion process, a basic fusion process model is presented, showing the impacts of uncertainty in four areas. Finally, for output uncertainty, the significance of a closed-world versus open-world assumption is discussed.

16:00 - 16:30     A Semantic Approach to Evaluate the Impact
of Cyber Actions to the Physical Domain
Paper        Presentation
Alexandre Barreto (a,b),
Paulo Costa (a),
Edgar Yano (b)
a. C4I Center,
George Manson University and
b. Inst. Technológico
de Aeronáutica, Brazil

Evaluating the impact that events within the cyber domain inflict to a military operation and its critical infrastructure is a non-trivial question, which remains unanswered so far in spite of the various research efforts addressing it. The key issue underlying this question is the difficulty in correlating cyber and physical behaviors in an integrated view, thus allowing for real-time task evaluation. This paper addresses the issue with the development of an ontology-based framework in which the cyber and physical behaviors are integrated in a consolidated view, using a combination of open standards protocols and semantic technologies. In our approach, the mission and its physical aspects are modeled using a business process language (e.g., BPMN) and an information infrastructure based on Simple Network Management Protocol (SNMP). In this scheme, changes in the environment are captured using the output of sensor components existing in the infrastructure. In order to ensure a complete and integrated analysis of the accruing data, we have developed a Cyber Situation ontology (in OWL language) and a methodology for mapping the cyber and the physical domains. In this framework, mission data from the environment is retrieved and fused using an engine based on the semantic rule language (SWRL). The output of this process is then presented to an analyst in a way that only the most important information needed to support his/her decisions is shown. To validate our approach, a fictitious air traffic scenario was modeled and many simulated flights were generated in support to our experiments.

16:30 - 17:00     Intrinsically Resilient Energy Control Systems
Paper        Presentation
Frederick Sheldon (a),
Jingshan Huang (b),
Jiangbo Dang( c),
Daniel Fetzer (a),
Stuart Goose( c),
Jonathan Kirsch ( c),
David Manz (d),
Thomas Morris (e),
Dong Wei (c)
a. Oak Ridge Natl Laboratory,
b. University of S. Alabama,
c. Siemens Corporation,
d. Pacific NW Natl Laboratory,
e. Mississippi St. University


To preserve critical energy control functions while under attack, it is necessary to perform comprehensive analysis on the root cause and impact of an ongoing cyber intrusion without sacrificing the availability of energy delivery. In this position paper, we present a proof of concept of an intrinsically resilient energy control system, with the ultimate goal of ensuring availability/resiliency of energy delivery functions, along with the capability to assess root causes and impacts of cyber intrusions.

17:00 - 18:30     Poster Session / Social Event
    Study of MEBN Learning for Relational Model
Paper        Presentation
Cheol Young Park,
Kathryn Blackmond Laskey,
Paulo Costa,
Shou Matsumoto
George Mason University

In the past decade, Statistical Relational Learning (SRL) has emerged as a new branch of machine learning for representing and learning a joint probability distribution over relational data. Relational representations have the necessary expressive power for important real-world problems, but until recently have not supported uncertainty. Statistical relational models fill this gap. Among the languages recently developed for statistical relational representations is Multi-Entity Bayesian Networks (MEBN). MEBN is the logical basis for Probabilistic OWL (PR-OWL), a language for uncertainty reasoning in the Semantic Web. However, until now there has been no implementation of MEBN learning. This paper describes the first implementation of MEBN learning. The algorithm learns a MEBN theory for a domain from data stored in a relational Database. Several issues are addressed such as aggregating influences, optimization problem, and so on. In this paper, as our contributions, we will provide a MEBN-RM (Relational Model) Model which is a bridge between MEBN and RM, and suggest a basic structure learning algorithm for MEBN. And the method was applied to a test case of a maritime domain in order to prove our basic method.

    Social Sifter:
An Agent-Based Recommender System to Mine the Social Web
M. Omar Nachawati,
Rasheed Rabbi,
Genong (Eugene) Yu,
Larry Kerschberg,
Alexander Brodsky
George Mason University

With the recent growth of the Social Web, an emerging challenge is how can we integrate information from the heterogeneity of current Social Web sites to improve semantic access to the information and knowledge across the entire World Wide Web. While each individual Social Web site may provide its own semantic facilities, when it comes to interoperability across the Social Web in its entirety, even the simplest of inferences based on data from different sites can appear intractable without the Ňsemantic training wheelsÓ pioneered by the Semantic Web effort. Even if such data were interoperable across multiple Social Web sites, the ability of a system of collective intelligence to make meaningful inferences, depends largely on both its ability to marshal such semantic data as well as its ability to understand accurately and respond precisely to queries from its users.

Applications of collective intelligence systems are numerous, and can be used, for instance, to build social semantic search engines and recommender systems. In this paper we present the architecture for Social Sifter, an agent-based, collective intelligence system for assimilating information and knowledge across the Social Web. As a proof-of-concept, we have prototyped a health recommender system, using the Social Sifter architecture, which recommends treatments, prevention advice, and therapies for ailments; it also recommends doctors and hospitals based on shared experiences available on the Social Web.

This paper discusses in more detail the challenges of assimilating the Social Web and query classification and enrichment, and describes the general architecture of the Social Sifter and our proof-of-concept health recommender system, as well as presents our experimental findings.


Thursday, October 25th
08:30 - 09:00     Breakfast
09:00 - 10:00     Keynote Speaker
Jay Holcomb
An Insider Perspective of how Semantic Technologies are supporting the DHS efforts in Cybersecurity

U.S. Computer Emergency Readiness Team
National Cyber Security Division (NCSD)
U.S. Department of Homeland Security

10:00 - 10:30     Break
10:30 - 12:00     Research Session   Chair:   -    Richard Lee, Booz Allen Hamilton
10:30 - 11:00     D2RCrime: A Tool for Helping to Publish Crime Reports
on the Web from Relational Data
Paper        Presentation
Julio Tavares, Vasco Furtado,
Henrique Santos,
Eurico Vasconcelos
Universidade de Fortaleza, Brazil

In the Law Enforcement context more and more data about crime occurrences are becoming available to the general public. For an effective use of open data, it is desirable that the different sources of information follow a pattern, which allows reliable comparisons. In addition, it is expected that the task of creating a correspondence between the pattern and the internal representations of each source of information is not a steep learning curve. These two conditions are hardly found in the actual stage where open data about crime occurrences is referred to as the data opened by each police department in its own way. This paper proposes an interactive tool, called D2RCrime, that assists the designer/DBA of relational crime databases to make the correspondence between the relational data and the classes and properties of a crime ontology. The ontology plays the role of a pattern to represent the crime concepts and crime report and is also the interface to publish on-the-fly relational crime data. This correspondence allows the automatic generation of mapping rules between the two representations, what allows for accessing relational data from SPARQL. An evaluation of D2RCrime is done with DBA/System analysts who used the tool for establishing correspondences between relational data and the ontology.

11:00 - 11:30     Exploiting inference to improve temporal RDF
annotations and queries for machine reading
Paper        Presentation
Robert Schrag
Digital Sandbox, Inc.

We describe existing and anticipated future benefits of an end-to-end methodology for annotating formal RDF statements representing temporal knowledge to be extracted from text, as well as for authoring and validating test and/or application queries to exercise that knowledge. Extraction is driven by a target ontology of temporal and domain concepts supporting an intelligence analystŐs timeline tool. Both the tool and the methodology are supported at several points by an implemented temporal reasoning engine, in a way that we argue ultimately advances machine reading technology by increasing both sophistication and quality expectations about temporal annotations and extraction.

11:30 - 12:00     Best-practice Time Point Ontology for
Event Calculus-based Temporal Reasoning
Paper        Presentation
Robert Schrag
Digital Sandbox, Inc.

We argue for time points with zero real-world duration as a best ontological practice in point and interval-based temporal representation and reasoning. We demonstrate anomalies that unavoidably arise in the event calculus when real-world time intervals corresponding to finest anticipated calendar units (e.g., days or seconds, per application granularity) are taken (naively or for implementation convenience) to be time "points." Our approach to eliminating the undesirable anomalies admits durations of infinitesimal extent as the lower and/or upper bounds that may constrain two time points' juxtaposition. Following Dean and McDermott, we exhibit axioms for temporal constraint propagation that generalize corresponding na•ve axioms by treating infinitesimals as orthogonal first-class quantities and we appeal to complex number arithmetic (supported by programming languages such as Lisp) for straightforward implementation. The resulting anomaly-free operation is critical to effective event calculus application in commonsense understanding applications, like machine reading.

12:00 - 13:30     Lunch
13:30 - 14:45     Panel   -   Moderator: Leo Obrst
    Cyber Ontology: Is it the World Squared?

Panelists Info     Obrst intro
Presentation - Mike Dean
Presentation - Duminda Wijesekera
Presentation - Brian Haugh

Mike Dean - Raytheon BBN Technologies
Duminda Wijesekera - C4I Center - GMU
Brian Haugh - Institute for Defense Analyses
Bill Mandrick - Data Tactics
Randall Dipert - University at Buffalo
14:45 - 15:15     Break
15:15 - 16:45     Research Session   -   Chair: Richard Markeloff, MITRE Corp
15:15 - 15:45     The Why Agent:
Enhancing user trust in automation
through explanation dialog
Paper        Presentation
Rob Cole(a), Jim Jacobs(a),
Michael Hirsch(a),
Robert L. Sedlmeyer(b, c)
a. Raytheon Company,
b. Indiana University,
c. Purdue University

Lack of trust in autonomy is a recurrent issue that is becoming more and more acute as manpower reduction pressures increase. We address the socio-technical form of this trust problem through a novel decision explanation approach. Our approach employs a semantic representation to capture decision-relevant concepts as well as other mission-relevant knowledge along with a reasoning approach that allows users to pose queries and get system responses that expose decision rationale to users. This representation enables a natural, dialog-based approach to decision explanation. It is our hypothesis that the transparency achieved through this dialog process will increase user trust in autonomous decisions. We tested our hypothesis in an experimental scenario set in the maritime autonomy domain. Participant responses on psychometric trust constructs were found to be significantly higher in the experimental group for the majority of constructs, supporting our hypothesis. Our results suggest the efficacy of incorporating a decision explanation facility in systems for which a socio-technical trust problem exists or might be expected to develop.

15:45 - 16:15     Rapid Argumentation Capture from Analysis Reports:
The Case Study of Aum Shinrikyo
Paper        Presentation
Mihai Boicu,
Gheorghe Tecuci,
Dorin Marcu
Learning Agents Center,
George Mason University


The availability of subject matter experts has always been a challenge for the development of knowledge-based cognitive assistants incorporating their expertise. This paper presents an approach to rapidly develop cognitive assistants for evidence-based reasoning by capturing and operationalizing the expertise that was already documented in analysis reports. It illustrates the approach with the development of a cognitive assistant for assessing whether a terrorist organization is pursuing weapons of mass destruction, based on a report on the strategies followed by Aum Shinrikyo to develop and use biological and chemical weapons.

16:15 - 16:45     A Policy-Based Dialogue System for Physical Access Control
Paper        Presentation
Mohammad Ababneh (a),
Duminda Wijesekera(a),
James Bret Michael(b)
a. George Mason University
b. Naval Postgraduate School

We prototype a policy-based dialog system for providing physical access control to secured facilities and smart buildings. In our prototype system, physical access control policies are specified using the eXtensible Access Control Markup Language. Based on the policy and the user's presence information, our dialog system automatically produces a series of questions and answers that, if correctly answered, permit the requester to enter the secure facility or smart building. The novelty of this work is the system's ability to generate questions appropriate to the physical location, time of day, and the requester's attributes.

16:45 - 17:00            Best Paper Award   -   Chair: Daniel Maxwell
17:00 - 17:15            Wrap Up   -   Paulo Costa

Last updated: 07/29/2013