Advanced algorithm for automatic modulation recognition for analogue digital signals

摘要

In this paper we propose a new algorithm for recognition of analogue and digital communication signals utilizing decision tree classifier. Eight features extracted from instantaneous information (amplitude and phase) and signal spectra are used to discriminate between eighteen signals (AM, FM, DSB, LSB, USB, VSB, combined (AM-FM), CW, Noise, MASK (2, 4 and 8), MPSK (2, 4 and 8) and MFSK (2, 4 and 8)) at low SNR. The simulation results show that the overall recognition rate can reach 99% when SNR=7dB. This algorithm has small computation loads comparing with most of the existing algorithms.