Information Quality in Fusion-Driven Human-Machine Environments

Designing decision support systems in complex human-machine integrated environments requires contextual understanding and interpretation of the events and behaviors of interest. The process of building such systems involves gathering and processing of a large amount of multimedia and multispectral information coming from multiple, often geographically distributed sources to gain knowledge of the entire domain of interest. Information to be processed, fused, and made sense of includes but is not limited to data obtained from sensors, surveillance reports, casual observers, and information obtained from open sources (internet, radio, TV, etc.). Successful collection and processing of this information may also demand information sharing and dissemination, and action cooperation of multiple stakeholders. Such complex environments call for an integrated fusion-base human-machine system, in which some processes are best executed automatically while for others the judgment and guidance of human experts and end-users are critical.

The problem of building such integrated systems is complicated by the fact that data and information obtained from observations and reports as well as produced by both human and automatic processes are of variable quality and may be uncertain, unreliable, of low fidelity, insufficient resolution, contradictory, and/or redundant. The success of decision-making in such complex human-machine environments depends on the success of being aware of, and compensating for, insufficient information quality at each time when raw data (sensor reading, open source, database search results, and intelligence reports) enter the system as well as when information is transferred between automatic processes, between humans, and between automatic processes and humans.

The presentation will discuss major challenges and some possible approaches addressing the problem of representing and incorporating information quality into fusion processes. In particular, it will present an ontology of information quality characteristics and identify potential methods of representing and assessing the values of these characteristics and their combination. It will also examine the relation between information quality and context and suggest possible approaches to quality control compensating for insufficient information and model quality.

Dr. Rogova is an independent consultant (DBA as Encompass Consulting) as well as a long-time member of the UB Collaborative Institute for Multisource Information Fusion. She is an internationally recognized expert in the areas of information fusion, information quality, and reasoning and decision-making under uncertainty. Her other expertise includes machine learning, ontology, and computer-aided medical diagnosis. She has worked on a wide range of defense and non-defense problems such as decision-making involving low probability high consequence events, situation and threat assessment, information medical diagnosis, and understanding of volcanic eruption patterns, among others. Her research has been funded by multiple government agencies as well as commercial companies. She has published numerous papers and co-edited 6 books on these topics. Dr. Rogova has been a lecturer and a member of organizing committees of multiple international conferences, NATO Advance Study Institutes, and NATO Advanced Research Workshops on information fusion and decision support.