This applied research project focuses on novel techniques and learning algorithms for (1) classifying chat messages, 2) summarizing chat room situations, and (3) 3D audio and visual cueing techniques for intelligently cueing watchstanders in a Navy Combat Information Center (CIC). The project is developing novel, knowledge-intensive statistical relational algorithms for learning more accurate classifiers on a wide range of tasks. Research results empirically validate audio-visual (e.g., chat) event notification and attention management strategies for CIC operations. The project further develops testbed improvements, extended to support chat task simulations, for use in a synthetic task environment.
The project uses CIC chat room logs and prepares knowledge sources for use by learning algorithms. It develops and validates performance of knowledge-intensive statistical relational learning algorithms (for chat classification and chat room summarization). Group members are designing the auditory, visual, and Notification Manager components for cueing watchstanders on any display. Finally, the various components are being integrated into NRL’s watchstation test bed. The group finally conducts empirical verification studies with human subjects to assess the efficacy of the learned classifiers, chat room summarization displays, and cueing methods.
David W. Aha
Adaptive Systems, Code 5514
Naval Research Laboratory
Washington DC 20375
Washington, DC 20375
Email: w5514 "at" aic.nrl.navy.mil