Thomas C. Eskridge

Concept maps: integrating knowledge and information visualization

Information visualization has been a research topic for many years, leading to a mature field where guidelines and practices are well established. Knowledge visualization, in contrast, is a relatively new area of research that has received more attention recently due to the interest from the business community in Knowledge Management. In this paper we present the CmapTools software as an example of how concept maps, a knowledge visualization tool, can be combined with recent technology to provide integration between knowledge and information visualizations. We show how concept map-based knowledge models can be used to organize repositories of information in a way that makes them easily browsable, and how concept maps can improve searching algorithms for the Web. We also report on how information can be used to complement knowledge models and, based on the searching algorithms, improve the process of constructing concept maps.

Collaborative knowledge capture in ontologies

This paper describes a new environment, COE, for capturing and formally representing expert knowledge for use in the Semantic Web. COE exploits the ease of use and rapid knowledge construction capabilities of the CmapTools concept mapping system and extends them to support the import and export of formal, machine-interpretable knowledge representations, such as OWL, across multiple ontologies. Pragatis ExpozT tool suite complements COEs ontology construction, browsing and navigation features by providing cluster-based search capabilities that expose existing reusable concepts relevant to the users focus of attention.

Aiding knowledge capture by searching for extensions of knowledge models

Electronic concept mapping tools empower experts to play an active role in the knowledge capture process, and provide a medium for building richly connected multimedia knowledge models---sets of linked concept maps and resources about a particular domain. Knowledge models are intended to be used as a means for sharing knowledge among humans, not as carefully-crafted knowledge bases upon which machines will be performing inference. However, users must still confront the questions of what to include in a concept map and which concept maps to include in a knowledge model. This paper describes ongoing research on methods to provide content-based support to users as they extend concept maps by adding concepts and propositions, and as they select topics for new maps. The goal is to provide scaffolding for experts as they build their own concept maps, link their maps to others, and decide how to extend their knowledge models. The paper presents three approaches which start from a concept map under construction and mine related information---both from prior concept maps, and from the web---to propose information to aid the users knowledge capture and knowledge construction. The paper begins with a brief summary of the concept mapping process and the CmapTools concept mapping software. It then presents three types of implemented suggesters, to suggest concepts, propositions, concept maps, and new topics to aid experts using the CmapTools, and describes preliminary experiments to assess their performance. It closes with a discussion of next steps for testing and refining these methods.

From Tools to Teammates: Joint Activity in Human-Agent-Robot Teams

Coordination is an essential ingredient of joint activity in human-agent-robot teams. In this paper, we discuss some of the challenges and requirements for successful coordination, and briefly how we have used KAoS HART services framework to support coordination in a multi-team human-robot field exercise.

Sol: An Agent-Based Framework for Cyber Situation Awareness

In this article, we describe how we augment human perception and cognition through Sol, an agent-based framework for distributed sensemaking. We describe how our visualization approach, based on IHMC’s OZ flight display, has been leveraged and extended in our development of the Flow Capacitor, an analyst display for maintaining cyber situation awareness, and in the Parallel Coordinates 3D Observatory (PC3O or Observatory), a generalization of the Flow Capacitor that provides capabilities for developing and exploring lines of inquiry. We then introduce the primary implementation frameworks that provide the core capabilities of Sol: the Luna Software Agent Framework, the VIA Cross-Layer Communications Substrate, and the KAoS Policy Services Framework. We show how policy-governed agents can perform much of the tedious high-tempo tasks of analysts and facilitate collaboration. Much of the power of Sol lies in the concept of coactive emergence, whereby a comprehension of complex situations is achieved through the collaboration of analysts and agents working together in tandem. Not only can the approach embodied in Sol lead to a qualitative improvement in cyber situation awareness, but its approach is equally relevant to applications of distributed sensemaking for other kinds of complex high-tempo tasks.

Command and Control Requirements for Moving-Target Defense

The macrocognitive workplace is constantly changing, and a work system can never match its environment completely; there are always gaps in fitness because the work is itself a moving target. This article looks at a domain where the workplace is a moving target in three ways: cyberdefense. New technology and work methods are continually being introduced, domain constraints are not constant; the work itself is changing in terms of its new goals and requirements, and anything can be surprising. The article presents a possible sensemaking strategy and implications for the design of intelligent systems founded on human-machine interdependence, semantically rich policy governance, and having the goal of achieving resilience in the cognitive work.

MTC2: A command and control framework for moving target defense and cyber resilience

In this paper we discuss the need for a new command and control (C2) approach for the practical deployment of Moving Target Defenses (MTDs) enterprise networks. We describe some of the requirements and constraints associated with the combined use of multiple moving target defenses, and introduce a human-agent teamwork approach for the command and control of MTDs. We introduce and discuss some of the specific concepts and technologies that could play an important role in the development of this capability, and conclude by describing the implementation details of the human-agent teamwork C2 prototype, called MTC2.

A human-agent teamwork command and control framework for moving target defense (MTC2)

In this paper we discuss the need for a command and control (C2) capability for moving target (MT) defenses. We describe some of the requirements and constraints associated with such a capability, and propose a human-agent teamwork approach for MTC2. We further discuss some specific concepts and technologies that could play an important role in the development of this capability, and conclude by describing some implementation details of a prototype being developed to demonstrate and study the proposed concepts for MTC2.

Human-agent teamwork in cyber operations: supporting co-evolution of tasks and artifacts with luna

In this article, we outline the general concept of coactive emergence, an iterative process whereby joint sensemaking and decision-making activities are undertaken by analysts and software agents. Then we explain our rationale for the development of the Luna software agent framework. In particular, we focus on how we use capabilities for comprehensive policy-based governance to ensure that key requirements for security, declarative specification of taskwork, and built-in support for joint activity within mixed teams of humans and agents are satisfied.

Ontology Creation as a Sensemaking Activity

This article explores the use of diagramming to support simultaneous sensemaking and ontology development. The authors argue that tools can be developed to support a continuum of knowledge models, from initial free-form diagrams that make it easy to capture anauthorés knowledge and intent but are only interpretable by humans, to propositionally coherent concept maps that structure the free-form diagrams into independently meaningful node-link-node triples, and finally to description-logic concept maps that combine human readability and understanding with logical formalism and a machine-understandable format. The CmapTools Ontology Editor (COE) is a version of CmapTools that uses a descriptive-logic style to encode meanings. Rendering Web Ontology Language (OWL) into concept map notation may be regarded as a first marker in the territory that lies toward the formal end of a continuum of human-machine functionality. In COE-OWL diagrams, the machine reads the parts of the diagram that it can and performs allowable logical operations, while ignoring the parts of the diagram it cannot read. Conversely, humans read those parts of the diagram that make sense and can ignore the rest, knowing that the two formsóthe natural and the logicalóare linked in a way that is itself meaningful and functional. The authors call this merger of ontology creation and sensemaking ìopportunistic computation.