ISBN: 978-981-09-5471-0 DOI: 10.18178/wcse.2015.04.097
A Novel Algorithm for Open-set Modulation Recognition of Communication Signals
Abstract— In this paper, a novel algorithm is proposed for open-set modulation recognition of
communication signals by extracting the characteristics of received signals in the presence of additive
white Gaussian noise. Some instant characteristics are defined, including continuous coefficient of
unification instant phase, concentration ratio of instant amplitude unification and so on, meanwhile a
two-stage classifier is also designed to improve recognition accuracy and avoid adding much
computing time. The proposed recognition algorithm can identify nine different modulation modes
from other unknown one, and noted that it is rarely sensitive to residual frequency offsets and
available for MF signals. Simulation results demonstrate that the recognition accuracy of the
proposed algorithm is better than 93% at 8 dB SNR value and robustness is also achieved for varied
cosine roll-off signals.
Index Terms— open-set modulation recognition, instant characteristic, high-order cumulants, classifier
Wang Bo, Huang Zhen
Space Center, Tsinghua University, CHINA
Cite: Wang Bo, Huang Zhen, "A Novel Algorithm for Open-set Modulation Recognition of Communication Signals," 2015 The 5th International Workshop on Computer Science and Engineering-Information Processing and Control Engineering (WCSE 2015-IPCE), pp. 587-594, Moscow, Russia, April 15-17, 2015.