This paper describes how pedigree is used to support and enhance situation and threat assessment. It is based on the findings of the technology group of the Data Fusion Levels Two and Three Workshop sponsored by the Office of Naval Research held in Arlington, VA from 15-18 Nov. 2005. It identifies areas that need improvement in situation assessment and threat assessment, such as interoperability, automation, pedigree management, system usability, reliability, and uncertainty. The concept of pedigree must include "standard" metadata, lineage, plus a computational model of the quality of the information. The system must automatically propagate changes and update to derived products when source information or source-pedigree information changes. Several other processes must be automated: generate pedigree, identify and auto fill gaps, fuse pedigree, update pedigree, display of information quality and confidence. The paper concludes with suggestions for future research and development.

Knowledge management for distributed-tracking (KMDT) is a U.S. Naval research and development project to improve military-communications and information functions in the battle space. These functions include command, control, data fusion, and decision support. It features a scenario for modeling and simulation that shows how knowledge-management technologies, such as ontologies and intelligent agents can improve battle-space awareness and the decision-making process in command centers with respect to distributed tracking and threat identification of targets. Data on cross lines of bearings can be acquired from sensors using a secure network. These data and their associated pedigree metadata from multiple platforms in the battle space can be fused to reduce the uncertainty in platform detection, localization, classification and identification (level-one data-fusion object refinement). The pedigree metadata can affect how data are used in fusion tasks

In this paper we discuss the need for real-time data mining for many applications in government and industry and describe resulting research issues. We also discuss dependability issues including incorporating security, integrity, timeliness and fault tolerance into data mining. Several different data mining outcomes are described with regard to their implementation in a real-time environment. These outcomes include clustering, association-rule mining, link analysis and anomaly detection. The paper describes how they would be used together in various parallel-processing architectures. Stream mining is discussed with respect to the challenges of performing data mining on stream data from sensors. The paper concludes with a summary and discussion of directions in this emerging area.

This paper describes conceptual work in dynamic three-value logic (3VL) with a view toward applications in decentralized time-critical domains, such as a sensor field. The completeness and computability of 3VLs also are discussed, including an algorithm to illustrate the use of heuristics. The military services deploy systems of heterogeneous sensors to detect and classify platforms. The paper provides a brief overview of the heterogeneous, decentralized sensor field used for military target classification as hostile, neutral or friendly. In an example, three-value logic is used to characterize the movement of a ship through a sensor field in terms of relevance and conclusiveness of the aggregate of sensor information. The paper concludes with a discussion of directions for future research and development.

This paper explores challenges facing information system professionals in the management of data and knowledge in the Department of Defense (DOD), particularly in the information systems utilized to support command, control, communications, computers, and intelligence (C/sup 4/ I). These information systems include operational tactical systems, decision-support systems, modeling and simulation systems, and nontactical business systems, all of which affect the design, operation, interoperation, and application of C/sup 4/ I systems. Specific topics include issues in integration and interoperability, joint standards, data access, data aggregation, information system component reuse, and legacy systems. Broad technological trends, as well as the use of specific developing technologies are discussed in light of how they may enable the DOD to meet the present and future information-management challenges.

Whereas much of the previous work on data mining has focused on mining data in relational databases, we discuss mining objects. Object models are very popular for representing multimedia data, and therefore we need to mine object databases to extract useful information from the large quantities of multimedia data. We first describe the motivation for multimedia data mining with examples and then discuss object mining with focus on text, image, video and audio mining. We also address the need for real time data mining for multimedia applications.

This paper describes Disciple, an Artificial Intelligence based decision aid which subject-matter experts can train and use when making decisions under stressful, complex, and constrained conditions. The tool was developed and used under the Defense Advanced Research Projects Agency's High Performance Knowledge Base and Rapid Knowledge Formation programs. Some domains in which the tool would be applicable are described, with particular emphasis on military battle planning. The paper concludes with a discussion of future trends in decision-support application tools.

This paper describes Proton-Exchange Membrane (PEM) fuel cells, their importance to military applications, and how their design can be enhanced using computational techniques. We extend the logic of plausible reasoning given by Collins and Michalski in two directions. First, it uses a context-free grammar for the operations of generalization and specialization. Second, it uses granular computing to put analogical reasoning on a fuzzy basis. Finally, it demonstrates in the context of fuel cell design that a paradigm for computing with words can achieve common-sense reasoning.

The Web provides a forum in which AI systems can be demonstrated and compared. This paper addresses a fuzzy method for context-sensitive textual matching. We are investigating two key approaches. Knowledge on the Web must be retrieved and structured to facilitate mining operations. Case-based filtering allows the algorithm to adapt dynamically to changes in content or efficiency of expression. Our approach is to design sub-optimal mining algorithms that sacrifice completeness for speed, tractability and breadth of coverage. The mined knowledge is fed back to serve as a heuristic filter.

The paper describes data mining and the various ways in which it can be applied to command, control, communications and intelligence. It begins with an overview of data mining and the various steps in the data mining process. Examples of data mining outcomes are cited and an example of a text mining scenario for intelligence applications is described. Problems associated with data mining are described, including the conflict between security and privacy and the challenges of distributed mining. The paper concludes with a discussion of future trends in data mining.

The paper documents progress to date on a research project, the goal of which is wartime event prediction. It describes the operational concept, the data mining environment, and data mining techniques that use Bayesian networks for classification. Key steps in the research plan are as follows: (1) implement machine learning; (2) test the trained networks; and (3) use the technique to support a battlefield commander by predicting enemy attacks. Data for training and testing the technique can be extracted from the object oriented database that supports the Integrated Marine Multi-Agent Command and Control System (IMMACCS). These data were derived from message traffic generated during US Marine Corps exercises. The class structure in the IMMACCS data model is especially well suited to support attack classification.

This paper describes the relationship between data mining (DM) and artificial intelligence (AI) and how both can improve future military information systems. As these information systems take advantage of the technology trends, they will derive their upgrades from expert systems, knowledge-bases (KBs), inference engines, robotics, natural language, remote sensing, knowledge discovery (KD), and data mining over networks. This will result in an expansion to all echelons of present capabilities that now are available to warfighters only at the higher echelons. Moreover, it will result in an improved battlefield awareness for all warfighters beyond anything that is implemented today.

This paper describes the technology developed in the Defense Advanced Research Projects Agency's (DARPA) High-Performance Knowledge-Base (HPKB) Program that was transferred to follow-on applications. These applications include the following: 1. a data-mining project using naive Bayesian networks for the U.S. Marine Corps; 2. a Theatre Ballistic Missile Reasoner project, using Bayesian networks for the U.S. Air Force; 3. an application of course-of-action technology for the U.S. Army, and 4. on-going research projects to mine knowledge from the World Wide Web. The HPKB program objectives are presented and each transferred technology is described in relation to its target application. Future trends for knowledge-based and data-mining technology are discussed.

Artificial intelligence, including fuzzy logic, is applied to the diagnosis of glaucoma. Current methods and difficulties are reviewed and a diagnostic and prediction system is proposed. Validation of the developed software will involve data collected from the clinical evaluation of glaucoma patients, glaucoma-suspect patients and normal subjects. The proposed system is expected to lead to a decrease in the difficulty and cost of glaucoma diagnosis as well as a decrease in the associated health risks.

Complementary Processing (CP), is a scheduling methodology to increase software execution speed. Experiments were performed to test CP with command and control software, specifically, to measure the effect of CP on the speed of processing Navy track-message data. A 37.5-fold increase was observed in this preliminary test. Recommendations for future tests are discussed.

This paper explores challenges facing data administrators, database engineers, and knowledge-base developers in the management of information in the United States (U.S.) Department of Defense (DoD), particularly in the information systems utilized to support Command, Control, Communications, Computers, and Intelligence (C/sup 4/I). These information systems include operational tactical systems, decision-support systems, modeling and simulation systems, and non-tactical business systems, all of which can affect the design, operation, interoperation, and application of C/sup 4/I systems. Specific topics include issues in integration and interoperability, joint standards, data access, data aggregation, information-system component reuse and legacy systems. Broad technological trends, as well as the use of specific developing technologies will be discussed in light of how they may enable the U.S. DoD to meet the present and future data-management challenges.