Designing an automatic modulation classifier (AMC) for high frequency (HF) band is a research challenge. This is due to the recent observation that noise distribution in HF band is changing over time. Existing AMCs are often designed for one type of noise distribution, e.g., additive white Gaussian noise. This means their performance is severely compromised in the presence of HF noise. Therefore, an AMC capable of mitigating the time-varying nature of HF noise is required. This article presents a robust AMC method for the classification of FSK, PSK, OQPSK, QAM, and amplitude-phase shift keying modulations in presence of HF noise using feature-based methods. Here, extracted features are insensitive to symbol synchronization and carrier frequency and phase offsets. The proposed AMC method is simple to implement as it uses decision-tree approach with pre-computed thresholds for signal classification. In addition, it is capable to classify type and order of modulation in both Gaussian and non-Gaussian environments.
High frequency (HF) band has both military and civilian uses. It can be used either as a primary or backup communication link. Automatic modulation classification (AMC) is of an utmost importance in this band for the purpose of communications monitoring; e.g., signal intelligence and spectrum management. A widely used method for AMC is based on pattern recognition (PR). Such a method has two main steps: feature extraction and classification. The first step is generally performed in the presence of channel noise. Recent studies show that HF noise could be modeled by Gaussian or bi-kappa distributions, depending on day-time. Therefore, it is anticipated that change in noise model will have impact on features extraction stage. In this article, we investigate the robustness of well known digitally modulated signal features against variation in HF noise. Specifically, we consider temporal time domain (TTD) features, higher order cumulants (HOC), and wavelet based features. In addition, we propose new features extracted from the constellation diagram and evaluate their robustness against the change in noise model. This study is targeting 2PSK, 4PSK, 8PSK, 16QAM, 32QAM, and 64QAM modulations, as they are commonly used in HF communications.
Abstrac t-In this paper, we propose a novel algorithm for automatic modulation classification of single carrier digital modulations widely used in High Frequency (HF) band that serves both military and civilian applications. Specifically, the proposed algorithm addresses the classification of 2FSK, 4FSK, 8FSK, 2PSK, 4PSK, 8PSK, 16QAM. 32QAM. 64QAM, and OQPSK using two features: Dissimilarity in constellation diagram for classification of PSKlQAM signals and spectral peaks for classification of FSK signals with the use of both Decision Tree (D1) and Support Vector Machine (SVM) classifiers. The robustness of proposed algorithm is tested against noise power and changes in noise model. Additive White Gaussian Noise (A WGN) and Bi-kappa noise models are considered in this work, as both exist in HF band
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.