Automatic feature extraction from insufficient JEM signals based on compressed sensing method

This paper presents an automatic feature extraction from insufficient JEM signals based on compressed sensing (CS) method. First, the CS method was employed to extract a refined spectrum from insufficient JEM signals. In the process of applying the CS method to JEM signals, we utilized the modified linear programming (LP) standard form of an optimization method. After converting the spectrum into the time domain signal using the inverse Fourier transform (IFT), the cepstrum function was used for acquiring the spool rate. Then, the blade domain signal can be obtained by rounding off operation after dividing the reconstructed frequencies by the spool rate. Finally, the final blade number was extracted based on the divisor-multiplier (DM) rule and the scoring concept. Its application to insufficient JEM signals demonstrated that the automatic feature extraction method improved the accuracy of JEM analysis and is expected to be effective from the perspective of radar resource management.