In this paper, we propose two low-complexity automatic modulation classification (AMC) classifiers based on order-statistics: the linear support vector machine (LSVM) and the approximate maximum likelihood (AML). Specifically, LSVM applies the linear combination of the entire order-statistics of the received signals for the classification, while AML resorts to the asymptotic distribution of the reduced order- statistics to decrease the computational complexity. The Simulations show that the performance of our proposed classifiers is close to that of the maximum likelihood (ML) classifier and outperforms the Kolmogorov-Smirnov (KS) and cumulant-based classifiers. While the complexity of our proposed classifiers is much lower than that of the ML classifier.
Low Complexity Automatic Modulation Classification Based on Order Statistics
01.09.2016
249813 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Depth Analysis in Deep Learning-Based Automatic Modulation Classification
DOAJ | 2024
|