Combining Self-Organizing Map and Lipschitz Condition for Estimation in Direction of Arrival

There are many DOA estimation methods based on different signal features, and these often evaluated by experimental results, but lack the necessary theoretical basis. Therefore, a direction of arrival (DOA) system self-organizing map (SOM) designed for arbitrarily distributed sensor array is proposed. The essential principle this method that from distance difference (DDOA) to Lipschitz continuity, it indicates similar topology between them, thus Kohonen SOM suitable network classify through DDOA. simulation results show errors less than 1° most signals 0° 180°. Compared MUSIC, Root-MUSIC, ESPRIT, RBF, under signal-to-noise ratios (SNR) declines 20 dB 2 robust, better RBF almost close MUSIC. Further, can be trained in advance, which makes possible implemented real-time.