Novel Modulation Recognition for WFRFT-Based System Using 4th-Order Cumulants

Abstract

We present a novel modulation recognition for weighted-type fractional Fourier transform (WFRFT)-based systems using the fourth-order cumulants. First, the constellation characteristics of the basic digital modulations ASK, PSK, and QAM are analyzed, and the corresponding relationships between the neighboring constellation points' distance and the constellation size are deduced. Second, the closed-form expressions of the fourth-order cumulants (C 42) for the WFRFT-based systems with ASK, PSK, and QAM are derived. Finally, through the first-and second-order derivatives of the C 42 , we prove that the optimal WFRFT order α r can be obtained through the minimization of the C 42. The simulation results show that the novel recognition for the WFRFT-based system is feasible and can reach an accuracy of almost 90% when energy per bit-to-noise power spectrum density ratio (E b /N 0) is greater than 6. INDEX TERMS Weighted-type fractional Fourier transform (WFRFT), modulation recognition, order optimization using 4th-order cumulants.

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

“…Reference [24] uses the fourth-order cumulants for modulation classification. In this work, ASK, PSK and QAM signals are analysed and classified.…”

“…For that, a classifier should be designed to classify a vast number of modulations. In earlier works, the following four steps are frequently used for multi-carrier signal modulation classification: [20] Achieves target optimal performance High complexity due to presence of noise Less classification accuracy due to lack of pre-processing PCA [21] Better performance during feature selection Less accuracy due to lack of significant features and pre-processing KNN [22] Low SNR rate for all modulations Less accuracy due to consider only instantaneous features M-QAM model [23] Reliable recognition rate even at low SNR rate (SNR<0) Only suitable for remove AWGN noise not suitable for other noise WF-RFT [24] Realistic recognition and high accuracy Only limited to PSK, ASK and QAM method when lower order cumulant is not suitable DAM [25] Rapid performance during modulation recognition for varying noise levels and modulations Not suitable for handling real time noisy data due to static threshold during classification Cepstrum model [26] Less computational complexity Inefficient feature extraction DSSS [27] Rapid performance during Tag recognition High information loss due to not select the number of PCA AMC with using deep learning CNN [28] Improved performance at low SNR rate (-4dB) Low performance in feature extraction CNN [29] High performance for modulation recognition with medium for high SNR rate Less accuracy due to lack of pre-processing CNN [30] High accuracy for digital signal modulation at low SNR (4dB) Not suitable for large datasets because SVM takes high amount of time for selecting modulation type CNN [31] Effective feature extraction Less accuracy at low SNR rate CNN [32] Reduce model size and accelerate computation Not suitable for all types modulation such as FSK, ASK, DPSK and etc.…”

Automatic Wireless Signal Classification: A Neural-Induced Support Vector Machine-Based Approach

“…In their study, the GA was used to select the best features from a statistical and spectral Information 2019, 10, 338 3 of 16 feature set. In Reference [25], cumulants are used for classification features with Convolutional Neural Networks (CNN). Oshea [21] used CNN directly for modulation classification and achieved a promising performance compared to previous feature-based neural network approaches.…”

Identification of WFRFT signals' parameter based on multi‐domain statistical features

“…Some studies in recent years have made a big step forward. In [9] and [10], the parameter of WFRFT is estimated in a brute force way(traversal algorithm) with regards to finding an extreme value of the 4th-order cumulant C 42 , after which a typical modulation recognition method is conducted effectively.…”

“…Besides, the periodic property of WFRFT would lead to more than one extreme point in the process of approximating the actual transform order. As a result, the parameter range of WFRFT in [9] and [10] is set within a monotonic interval of a function of C 42 , and the searching step length is minimal.…”