Exploratory Research on RADAR: A User-Adaptive Bayesian Framework for Data-Based Decision Support Exploratory Research on RADAR: A User-Adaptive Bayesian Framework for Data-Based Decision Support As the Navys vision network centric warfare is realized, the analysts and warfighters alike will have access to a multitude of structured, semi-structured and unstructured information sources. The decision makers will increasingly rely on these sources to make data-supported decision making. To ensure that this wealth of information does not turn into an information overload, human decision analysts will require a decision support system that (i) recognizes the plans and goals of the decision makers and (ii) proactively supports their information needs through retrieval, rectification, alignment and aggregation of the information. The recognition is needed so as to proactively provide the analysts with valuable information, where the value of a piece of information for a decision maker depends critically on how it supports in the generation/execution of their plans. Rectification is needed to improve the quality of uncurated data (with missing information of multiple modalities). The alignment is needed to support seamless querying and browsing of structured and unstructured data (e.g., align captioned/annotated images, micro-blogs and stored records with the appropriate segments of a text document such as military doctrine). The technical objective of this work is to develop, implement and evaluate RADAR, that can track the goals and intents of the human decision maker to prefetch high-value information from a multitude of incomplete, inconsistent, imprecise and unreliable sources. RADAR will have the ability to (i) recognize the higher level plans of the human decision makers to predict their information needs, and to suggest context-specific decision alternatives (ii) proactively query and fetch high value information for supporting decision making. Additionally, its information gathering process would have the ability to (iii) select trustworthy and relevant sources (iv) process queries over the structured data that explicitly takes into account data incompleteness, inconsistency and query imprecision and (v) align the structured and unstructured data to support a seamless querying and browsing experience. The primary deliverable of this exploratory project is a briefing to be provided at the CDM PDS Strategy Workshop to be held in July. The aim of this briefing would be to explain how the vision of RADAR framework will mesh with the overall programmatic goals of Proactive Decision Support program, and to explore potential collaborations with the other program participants. After the workshop, we will provide a technical report on our briefing. The proposed work demands expertise in two normally disjoint areas of researchautomated planning/plan recognition, and information extraction/integration/alignment. The principal investigator for the proposed work is Subbarao Kambhampati who does have significant expertise in both Information Integration and Automated Planning. He has had several successful previous grants from the ONR. The proposed work is a natural and highly promising cross-fertilization of two separate efforts funded by ONR through grants N000140910032, which supported work on user- and source-adaptive information integration, and N00014-09-1-0017, which supported work on the foundations of model-lite planning.
|Effective start/end date||5/1/14 → 12/31/14|
- DOD-NAVY: Office of Naval Research (ONR): $20,000.00
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.