You are here

Exploiting Latent Semantics for Embedded Intelligence Monitoring and Trainer Development.

Award Information
Agency: Department of Defense
Branch: Air Force
Contract: F33615-02-M-6058
Agency Tracking Number: 021HE-0174
Amount: $100,000.00
Phase: Phase I
Program: SBIR
Solicitation Topic Code: N/A
Solicitation Number: N/A
Timeline
Solicitation Year: N/A
Award Year: 2002
Award Start Date (Proposal Award Date): N/A
Award End Date (Contract End Date): N/A
Small Business Information
1660 So. Amphlett Blvd., Suite 350
San Mateo, CA 94402
United States
DUNS: 608176715
HUBZone Owned: No
Woman Owned: No
Socially and Economically Disadvantaged: No
Principal Investigator
 Terrance Goan
 Principal Investigator
 (206) 545-1478
 goan@shai-seattle.com
Business Contact
 Melissa Thiemmedh
Title: Lead Accountant
Phone: (650) 655-7242
Email: thiemmedh@shai.com
Research Institution
N/A
Abstract

"We propose an innovative approach to achieving Cognitive Readiness with respect to Information Warfare through a combination of automated monitoring, adaptive information display, real-time coaching, and the capture of scenarios suitable for training andrehearsal. In particular we will investigate the exploitation of Latent Semantic Analysis, which is a means for making accurate comparisons of the semantic similarity between pieces of textual information, and has been applied with success to a number ofproblems closely related to the task at hand. But real-time monitoring of intelligence information poses some unique challenges including the need to maintain the currency of LSA's matrices, and feeding its voracious appetite for training data. Toovercome these obstacles we propose a unique combination of new and proven techniques. Our approach will exploit our recent advances in fully automated search to capture the required training data, as well as recent techniques for detecting content driftso as to minimize the update requirements of the LSA matrices. Our Phase I work-centered research and design, and the development and operational testing of a limited prototype, will lay the groundwork for the Phase II complete implementation andvalidation of our technology, called Aware. The technology proposed herein offers the potential to fulfill the market demand for tools to increase productivity in the processing of electronic docum

* Information listed above is at the time of submission. *

US Flag An Official Website of the United States Government