Dyadic Aggregated Autoregressive Model (DASAR) for Automatic Modulation Classification

Abstract

In this paper, we presented a novel spectral estimation method, the dyadic aggregated autoregressive model (DASAR), that characterizes the spectrum dynamics of a modulated signal. DASAR enhances automatic modulation classification (AMC) on environments where new or unknown modulation techniques are introduced, and only size-restricted data is accessible to train classification algorithms. A key component for obtaining efficient machine learning-based classification is the development of valuable knowledge-descriptive features. DASAR constructs a multi-level spectral representation by subdividing a signal into successive dyadic segments where each partition is modeled as an aggregation of singlefrequency autoregressive processes. Thus, the model ensures a robust representation at the segment level, while the multi-level decomposition can capture time-varying spectra. As a feature extraction model, DASAR can provide useful learning features related to signals with complex spectra. The effectiveness of our model was tested on a dataset comprised of 11 different modulation techniques and realistic transmission medium characteristics. Using only 200 128-point samples per modulation scheme (1% of the available signal samples) and a proper selection of a classification algorithm, DASAR reaches accuracy up to 70.96% compared with a maximum accuracy of 43.62% using the state-of-art methods tested under the same conditions. INDEX TERMS Automatic modulation classification, signal processing, spectrum modeling, autoregressive model, machine learning. I. INTRODUCTION A reliable communication system enforces that a transmitted message will only be understood if the transmitter and receiver have complete information about the communication parameters, including the type and characteristics of the desired modulation (i.e., the techniques to adapt the message to the transmission medium conditions). However, it is feasible to infer some properties about the communication channel's configuration if we intercept the modulated message passing through the channel. This inference is the central goal in automatic modulation classification (AMC) [1]. AMC was developed for military applications such as electronic warfare, surveillance, and threat analysis [2]. Nevertheless, its relevance made it fundamental for other widespread civilian purposes, including software-defined radio (SDR) and spectrum management. SDR is the base of selforganized communication infrastructures that rely on AMC to recognize the modulation in real-time and to adapt or optimize resources during the ongoing transmission process. The rapid progress and spread of high-speed wireless communication networks (especially 5G and WiFi 802.11ax), and the consequent spectrum saturation, impulse the role of AMC in spectrum management allowing the regulatory entities to detect misused spectrum ranges by non-authorized communication channels. AMC algorithms can be classified into likelihood-based (LB-AMC) and feature-based (FB-AMC) methods [1], [2],

Dyadic aggregated autoregressive (DASAR) model for time-frequency representation of biomedical signals

“…In both cases, previous knowledge of the signal to be analyzed was required in order to define a fixed resonating frequency ω * k . In [32], Pinto et al introduced an iterative heuristic approach to estimate a general ASAR (K) which is only restricted by the maximum number of components or the desired approximation error.…”

“…As an alternative time-frequency representation, the dyadic aggregated autoregressive (DASAR) model, a novel time-frequency approach, was initially proposed in [32] as a tool to extract evolving frequency properties from modulated signals as features for automatic classification of modulation. DASAR proposes an approximation of an evolving spectrum through dyadically splitting a signal and provides an approximation of the spectrum of each segment using an aggregated second-order autoregressive model (SAR).…”

Dual-Determination of Modulation Types and Signal-to-Noise Ratios Using 2D-ASIQH Features for Next Generation of Wireless Communication Systems

“…A larger modulation pool was examined in [38] for modulation type recognition using four types of classifiers (i.e., CNN, random forest, extreme gradient boosting trees, and decision tree). They proposed a feature-based model, that is sensitive to the spectrum dynamics of the detected signal, called dyadic aggregated autoregressive model (DASAR) to extract the detected signal features using 200 samples of the signal (i.e., smaller size of dataset).…”

“…In contrast to [38], a better performance of modulation recognition has been achieved in [39] via convolutional neural network (CNN) tool but considering 1024 samples per transmitted signal (i.e., larger size of dataset compared to [38]). Their model processed analog and digital modulation types under Rayleigh fading channel and obtained an average recognition accuracy of 91.48% at SNR value of 10 dB.…”

AMC2-Pyramid: Intelligent Pyramidal Feature Engineering and Multi-Distance Decision Making for Automatic Multi-Carrier Modulation Classification

“…AMC is vital in recognising the modulation algorithm used by the transmitter to the receiver. AMC has wide applications in the military and civilian fields [4]. Typically, AMC is performed for singleand multi-carrier modulation techniques with no spectrum efficiency.…”