This thesis describes the implementation of an ELINT algorithm for the detection and classification of Low Probability of Intercept (LPI) signals. The algorithm was coded in the C programming language and executed on a Field Programmable Gate Array based reconfigurable computer; the SRC-6 manufactured by SRC Computers, Inc. Specifically, this thesis focuses on the preprocessing stage of an LPI signal processing algorithm. This stage receives a detected signal that has been run through a Quadrature Mirror Filter Bank and outputs the preprocessed signal for classification by a neural network. A major value of this study comes from comparing the performance of the reconfigurable computer to that of supercomputers and embedded systems that are currently used to solve the signal processing needs of the United States Navy. / US Navy (USN) author.

An increasing number of LPI radars are integrated into integrated air defense systems (IADS) and modern platforms and weapons, such as anti-ship missiles, and littoral weapon systems. These LPI radars create a requirement for modern armed forces to develop new techniques, strategies, and equipment. The primary objective of this thesis is to investigate methods and means to counter LPI radar threats integrated into a modern platforms and weapons and focus on the related techniques, strategies, and technology. To accomplish this objective both platform centric and network centric approaches will be examined thoroughly.

Thesis (M.S. in Systems Engineering and M.S. in Engineering Science (Electrical Engineering))--Naval Postgraduate School, September 2003. / Thesis advisor(s): Phillip E. Pace, D. Curtis Schleher. Includes bibliographical references (p. 125-126). Also available online.

Today, there is a demand for reliable ways to perform automatic modulation recognition of Low Probability of Intercept (LPI) radar signals, not least in the defense industry. This study explores the possibility of performing automatic modulation recognition on these signals through clustering and more specifically how to learn representations of input signals for this task. A semi-supervised approach using a bootstrapped convolutional neural network classifier for representation learning is proposed. A comparison is made between training the representation learner on raw time-series and on spectral representations of the input signals. It is concluded that, overall, the system trained on spectral representations performs better, though both approaches show promise and should be explored further. The proposed system is tested both on known modulation types and on previously unseen modulation types in the task of novelty detection. The results show that the system can successfully identify known modulation types with adjusted mutual information of 0.86 for signal-to-noise ratios ranging from -10 dB to 10 dB. When introducing previously unseen modulations, up to six modulations can be identified with adjusted mutual information above 0.85. Furthermore, it is shown that the system can learn to separate LPI radar signals from telecom signals which are present in most signal environments. / Idag finns ett behov av pålitlig automatiserad modulationsigenkänning (AMR) av Low Probability of Inercept (LPI)-radarsignaler, inte minst hos försvarsindustrin. Denna studie utforskar möjligheten att utföra AMR av dessa signaler genom klustring och mer specifikt hur man bör lära in representationer av signalerna i detta syfte. En halvövervakad inlärningsmetod som använder en klassificerare baserad på faltningsnätverk föreslås. En jämförelse görs mellan ett system som tränar för representationsinlärning på råa tidsserier och ett system som tränar på spektrala representationer av signalerna. Resultaten visar att systemet tränat på spektrala representationer på det stora hela presterar bättre, men båda metoderna visar lovande resultat och bör utforskas vidare. Systemet testas på signaler från både kända och för systemet tidigare okända modulationer i syfte att pröva förmågan att upptäcka nya typer av modulationer. Systemet identifierar kända modulationer med adjusted mutual information på 0.86 i brusnivåer från -10 dB till 10 dB. När tidigare okända modulationer introduceras till systemet ligger adjusted mutual information över 0.85 för upp till sex modulationer. Studien visar dessutom att systemet kan lära sig skilja LPI-radarsignaler från telekommunikationssignaler som är vanliga i de flesta signalmiljöer.

Thesis (M.App.Sc.) - Carleton University, 2007. / Includes bibliographical references (p. 83-86). Also available in electronic format on the Internet.