Generation of EW Libraries and Automatic Threat Identification (GELATI) Navy SBIR FY2013.1 Sol No.: Navy SBIR FY2013.1 Topic No.: N131-036 Topic Title: Generation of EW Libraries and Automatic Threat Identification (GELATI) Proposal No.: N131-036-0259 Firm: Charles River Analytics Inc. 625 Mount Auburn Street Cambridge, Massachusetts 02138-4555 Contact: Wayne Thornton Phone: (617) 491-3474 Web Site: www.cra.com Abstract: Electronic warfare (EW) systems classify emitters by matching the signals detected against reference signatures in a tactical EW library. Since emitter signals can differ markedly from their library signatures (due to drift, new modes, propagation effects, etc.), ships with AN/SLQ-32(V) or SEWIP Block 1/2 systems use a labor-intensive process to iteratively "tailor" or "color" reference signatures to more closely resemble the signals they expect to detect. To enable ships to automatically build and update their tactical EW libraries-while improving their ability to respond to new threat emitters-we propose to develop a system for Generation of EW Libraries and Automatic Threat Identification (GELATI). GELATI will perform the following: (1) generate data sets containing representative signal parameters by thoroughly exploring the envelope of tactical and EW scenarios; (2) account for signal attenuation and distortion by noise and propagation effects; (3) compute recommended revisions to the reference signatures in the tactical EW library to optimize emitter classification performance; and (4) rapidly classify threat emitters even if their reference signatures are not yet updated. By leveraging existing and developing technologies, we will demonstrate GELATI's conceptual and engineering feasibility in Phase I, while ensuring that GELATI successfully interfaces with current and future transition targets. Benefits: GELATI technologies will be initially targeted at military applications for sensor processing-for electronic warfare (EW) as well as for other types of sensor processing systems. GELATI technologies will also be useful in any domain or application requiring adaptive classification of high-dimensional data. Examples of these applications include sensor processing (e.g., computer vision, image processing, and video surveillance); speech recognition; text recognition (hand-written, on-line, and printed); and even laboratory analysis of DNA microarray data. In addition, we plan to transition specific classification and fusion algorithms and features of the overall system architecture to our VisionKitT software suite to increase its commercial viability. Return