Ole J. Mengshoel

CoRAVEN: modeling and design of a multimedia intelligent infrastructure for collaborative intelligence analysis

Intelligence analysis is one of the major functions performed by an Army staff in battlefield management. In particular, intelligence analysts develop intelligence requirements based on the commanders information requirements, develop a collection plan, and then monitor messages from the battlefield with respect to the commanders information requirements. The goal of the CoRAVEN project is to develop an intelligent collaborative multimedia system to support intelligence analysts. Key ingredients of our design approach include: (1) significant knowledge engineering activities with domain experts, (2) representation of an explicit model of reasoning and activity to drive design, (3) the use of Bayesian belief networks as a way to structure inferences that relate observable data to the commanders information requirements, (4) collaborative graphical user interfaces to provide flexible support for the multiple tasks in which analysts are engaged, (5) sonification of data streams and alarms to support enhanced situation awareness, (6) detailed psychological studies of reasoning and judgment under uncertainty, and (7) iterative prototyping of candidate designs with domain experts for both formative and summative evaluation. The paper discusses our current progress on all these fronts.

Genetic Algorithms for Belief Network Inference: The Role of Scaling and Niching

Belief networks encode joint probability distribution functions and can be used as fitness functions in genetic algorithms. Individuals in the genetic algorithms population then represent instantiations, or explanations, in the belief network. Computing the most probable explanations (belief revision) is thus cast as a genetic algorithm search in the joint probability distribution space. At any time, the best fit individual in the genetic algorithm population is an estimate of the most probable explanation. This paper argues that joint probability distribution functions represented by belief networks typically are multimodal and highly variable. Thus the genetic algorithm techniques known as sharing and scaling should be of help. It is shown empirically that this is indeed the case, in particular that niching combined with scaling significantly improves the quality of a genetic algorithms estimate of the most probable explanations. A novel scaling approach, root scaling, is also introduced.

Collaborative decision making and intelligent reasoning in judge advisor systems

This paper applies judgment and decision making research to collaborative problem solving. This analysis is done with respect to the Raven and CoRaven decision-making tools for filtering, interpreting, and visualizing large amounts of uncertain data in the domain of intelligence analysis. Raven and CoRaven are multimodal advisory decision aids and their inferential reasoning is based on Bayesian networks. Human decision makers and information sources interact with these decision making systems in many ways during their design, construction, refinement and usage. This paper analyzes the collaborative aspects of the use of Raven and CoRaven using the judge advisor system model.

Visual reasoning instructional software system

Abstract Visual reasoning is an essential skill for an engineer to possess, particularly as computer-aided design tools become more prevalent. In this paper, we describe an innovative interactive multimedia application that provides a student with the tools to build a strong foundation in visual reasoning. The system, called the Visual Reasoning Tutor, exploits the missing view problem as a mechanism to develop the visual reasoning abilities of students. The Visual Reasoning Tutor provides a student with interactive, graphical operations to construct 3-D geometric objects, varying levels of intelligent critiques throughout the solution process, and a graphical user interface which supports multimedia capabilities aimed to enhance the learning process. This paper presents an overview of the system components, a complete sample exercise, and testing results of several prototypes that have been used in the classroom.

Multimedia instructional software for visual reasoning: Visual Reasoning Tutor (VRT)

Visual reasoning is an essential skill for an engineer to possess, particularly as computer-aided design tools become more prevalent. We describe an innovative multimedia application that provides a student with the tools to build a strong foundation in visual reasoning. The system, called the Visual Reasoning Tutor, exploits the missing view problem as a mechanism to develop the visual reasoning abilities of students, and utilizes multimedia capabilities to enhance the learning process. The Visual Reasoning Tutor provides a student with interactive, geometric operations and intelligent critiques at varying levels of help throughout the steps of a students solution.