Modulation Order Reduction Method for Improving the Performance of AMC Algorithm Based on Sixth–Order Cumulants

Marko S Pajic,Mladen Veinovic,Vladimir D Orlic,Miroslav Peric

doi:10.1109/access.2020.3000358

Marko S Pajic, Mladen Veinovic + Show 2 more

Open Access

https://doi.org/10.1109/access.2020.3000358

Copy DOI

Abstract

For the last two decades a large number of different automatic modulation classification (AMC) algorithms were developed, and many improvements in classification performance are reported. This was commonly achieved by engaging complex structures of neural networks, or other adaptable mechanisms for achieving better precision, when it comes to decision-making. Still, from practical implementation point of view, low algorithm complexity, economical usage of resources and fast execution remain to represent very desirable properties of an AMC algorithm. These properties are recognized in AMC algorithms based on higher - order cumulants as classification features, so their further improvement is of interest. Previous performance analysis of an algorithm based on sixth - order cumulants, in scenarios with complex valued signals' classification, showed that improvements are possible in the context of resources engaged and speed of execution. In this paper a novel approach is presented, for improving the correctness of classification process with sixth-order cumulants and simple two-step feature extraction structure, by engaging a new method for reduction of observed signal's modulation order which directly improves the classification performance. While tested with sixth-order cumulants, proposed method preserves good statistical properties of signal's higher - order cumulants in general, so it can be adopted in other AMC algorithms as well. Proposed modulation order reduction method is described in details, tested through computer simulations within the sixth-order cumulant AMC algorithm, and achieved improvements in performance are presented and explained.

Highlights

Automatic modulation classification (AMC) represents an important integral component of modern wireless systems, crucial for both military and civilian applications
FB algorithms based on various instantaneous features, wavelet transforms, higher order statistics–moments and cumulants, or cyclic statistics, are in recent researches commonly supported with complex classifiers which may result in excellent performance, such as Artificial Neural Networks (ANN), Support Vector Machines (SVM), K-Nearest Neighbor (KNN), Deep Neural Networks (DNN) or other Deep-Learning (DL) methods
In this paper a novel approach for improving the correctness of classification process in AMC algorithm based on sixth–order cumulants and simple two–step feature extraction structure is presented, by engaging a new method for reduction of observed signal’s modulation order

Summary

INTRODUCTION

Automatic modulation classification (AMC) represents an important integral component of modern wireless systems, crucial for both military and civilian applications. At all SNR values higher than 5dB, even with relatively small number of samples N used This fact opened good space for additional effectiveness in AMC algorithm based on sixth-order cumulants, through simple two-step classification defined in following manner:. Step 2: If estimated Cˆ 63,x value corresponds with QAM signals’ values, repeat the procedure from equation (8) with (bigger) number of samples N in order to provide necessary precision in classification of QAM signals, and compare it with ‘‘middle of the interval’’ threshold between 64-QAM and 16-QAM signal’s cumulants This concept is justified when condition SNR > 5dB is fulfilled, which can be confirmed through estimation of SNR just before the feature extraction starts [19].

SIMULATIONS AND PERFORMANCE ANALYSIS

CONCLUSION