Adaptive DBSCAN-based algorithm for constellation reconstruction and modulation identification

The identification of PSK/QAM signals contaminated by additive white Gaussian noise (AWGN) is studied. A new adaptive density-based clustering algorithm named ADBSCAN (adaptive density based spatial clustering of applications with noise) is proposed for clustering and reconstruction of signal constellations with arbitrary shape; it has an improved anti-noise performance. The adaptive adjustment of the input parameters optimizes the clustering process, resulting in correct identification of modulation types. Simulation results prove the feasibility and performance improvement of the algorithm.