Robustness of digitally modulated signal features against variation in HF noise model

Hazza, Alharbi; Shoaib, Mobien; Alshebeili, Saleh; Fahd, Alturki

doi:10.1186/1687-1499-2011-24

Cited by 12 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…k is the set of kernels, and b ∈ R N s is the bias for each output. The output of the k-th k = 1, 2, ..., N l k kernel is denoted by (8), and x l × W l k is the convolution between x l and W l k . Assume that the length of the output is L l o .…”

Section: Convolutional Layermentioning

confidence: 99%

See 1 more Smart Citation

A robust modulation classification method using convolutional neural networks

Zhou

Yin

et al. 2019

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

Automatic modulation classification (AMC) is a core technique in noncooperative communication systems. In particular, feature-based (FB) AMC algorithms have been widely studied. Current FB AMC methods are commonly designed for a limited set of modulation and lack of generalization ability; to tackle this challenge, a robust AMC method using convolutional neural networks (CNN) is proposed in this paper. In total, 15 different modulation types are considered. The proposed method can classify the received signal directly without feature extracion, and it can automatically learn features from the received signals. The features learned by the CNN are presented and analyzed. The robust features of the received signals in a specific SNR range are studied. The accuracy of classification using CNN is shown to be remarkable, particularly for low SNRs. The generalization ability of robust features is also proven to be excellent using the support vector machine (SVM). Finally, to help us better understand the process of feature learning, some outputs of intermediate layers of the CNN are visualized.

show abstract

Section: Convolutional Layermentioning

confidence: 99%

“…Transformation-based features were calculated from Fourier and wavelet transforms [5,6]. The high-order cumulant (HOC) features [7,8] are statistical features obtained from different orders of cumulants from the received signals. Additive white Gaussian noise (AWGN) can be completely mathematically eliminated in HOC features.…”

Section: Introductionmentioning

confidence: 99%

A robust modulation classification method using convolutional neural networks

Zhou

Yin

et al. 2019

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

show abstract

“…Fourier and wavelet transforms were used to calculate features based on transformations [4]. Statistically significant are high-order cumulant (HOC) [5] properties characteristics that are derived from various orders of cumulants [6] from the received signals. The mathematical elimination of additive white Gaussian noise (AWGN) in HOC features is possible.…”

Section: Introductionmentioning

confidence: 99%

Automatic Modulation Classification: Convolutional Deep Learning Neural Networks Approaches

lotfy¹,

Essai

Atallah

2023

SVU-International Journal of Engineering Sciences and Applicati

View full text Add to dashboard Cite

In this study, automatic modulation classification (AMC), a key part of both civilian and military applications, is looked at using a deep learning method .A lot of research has been done on feature-based (FB) AM algorithms in particular. In this paper, a robust AMC strategy based on convolutional neural networks (CNN) is proposed to solve the issue that current FB AMC methods frequently target a small set of modulations and lack generalisation capability. In total, 11 different modulation types are taken into consideration. Conventional AMCs can be categorised into maximum likelihood (ML)-based (ML-AMC) and feature-based AMCs. This paper proposes a robust convolutional neural network (CNN)-based automatic modulation classification (AMC) technique. The recommended method may automatically identify the characteristics of the incoming signals and classify them without the need for feature extraction. A comparison study was done for the proposed CNN-based AMCs with two different optimizers at two different signal-to-noise ratios to select the best one of them based on performance.

show abstract

“…The above-mentioned aspects motivated the work presented in this paper, which proposes a new DL-based approach to the classification of digitally modulated signals with improved generalization abilities that employs CAPs in conjunction with the CC features of the signals. The synergistic use of CAPs and CC features is supported by the CAPs’ ability to distinguish digital modulations [ 29 , 30 ] and to outperform CNNs and RESNETs in the I/Q-based classification of digitally modulated signals [ 23 ], as well as by the proven robustness of the CC features obtained by CSP to co-channel signals [ 9 , 10 ] and to variations in noise models [ 31 ]. To the best of our knowledge, using CC features with DL-based signal classifiers has not been studied before.…”

Section: Introductionmentioning

confidence: 99%

Deep-Learning-Based Classification of Digitally Modulated Signals Using Capsule Networks and Cyclic Cumulants

Snoap

Popescu

Latshaw

et al. 2023

Sensors

View full text Add to dashboard Cite

This paper presents a novel deep-learning (DL)-based approach for classifying digitally modulated signals, which involves the use of capsule networks (CAPs) together with the cyclic cumulant (CC) features of the signals. These were blindly estimated using cyclostationary signal processing (CSP) and were then input into the CAP for training and classification. The classification performance and the generalization abilities of the proposed approach were tested using two distinct datasets that contained the same types of digitally modulated signals, but had distinct generation parameters. The results showed that the classification of digitally modulated signals using CAPs and CCs proposed in the paper outperformed alternative approaches for classifying digitally modulated signals that included conventional classifiers that employed CSP-based techniques, as well as alternative DL-based classifiers that used convolutional neural networks (CNNs) or residual networks (RESNETs) with the in-phase/quadrature (I/Q) data used for training and classification.

show abstract

Robustness of digitally modulated signal features against variation in HF noise model

Cited by 12 publications

References 15 publications

A robust modulation classification method using convolutional neural networks

A robust modulation classification method using convolutional neural networks

Automatic Modulation Classification: Convolutional Deep Learning Neural Networks Approaches

Deep-Learning-Based Classification of Digitally Modulated Signals Using Capsule Networks and Cyclic Cumulants

Contact Info

Product

Resources

About