Narrowband Emitter Identification by Exploiting Gaussian Mixture Model
Narrowband emitter identification is used to correctly identify unknown narrowband emitters from the results of direction finding (DF). In this paper, we modeled the set of azimuth angles by a mixture of Gaussian densities, and divided narrowband emitter identification into two different stages. In the first stage, a competitive stop expectation-maximization (CSEM) algorithm was developed, which was based on Shapiro-Wilk test and minimum description length variant (MDL2) criterion. The CSEM only employed the estimated azimuth angles at all the signal-occupied frequency bins as feature parameters, while the frequency information implied in each cluster was not exploited sufficiently. So based on the implied frequency information, a postprocessing algorithm was introduced in the second stage. The experimental results show that the CSEM algorithm is more robust, and it has an increased capability to find the underlying model while maintaining a low execution time. By adopting CSEM and postprocessing algorithm in narrowband emitter identification, we are able to identify narrowband emitters with high correctness.