Abstract
In this paper, we propose an innovative approach using Anderson-Darling (A-D) test for signal modulation classification with less signal samples in AWGN channels. The A-D test is a non-parametric approach to measure the goodness of fit test. It is based on Cramer-Von Mises (CVM) test, using the mean square integral of the difference between the empirical cumulative distribution functions (ECDFs) from received signals and cumulative distribution functions (CDFs) of the signal under different candidate modulation format. In order to avoid the default of CVM, such as it is less sensitive at heads and tails of the distributions, more weights are given to heads and tails in A-D test. Massive simulation results show that compared with the Kolmogorov-Smirnov (K-S) classifiers and the traditional high-order cumulant-based classifiers, the A-D classifiers show better classification performance at different SNRs with less signal samples for M-QAM and M-PSK modulations in AWGN channels.
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call