检索结果-内蒙古大学图书馆

RanNet: Learning Residual-Attention Structure in CNNs for automatic modulation classification

IEEE WIRELESS COMMUNICATIONS LETTERS 2022年第6期11卷 1243-1247页

作者： Huynh-The, Thien Pham, Quoc-Viet Nguyen, Toan-Van Nguyen, Thanh Thi da Costa, Daniel Benevides Kim, Dong-Seong Kumoh Natl Inst Technol ICT Convergence Res Ctr Gumi 39177 South Korea Kumoh Natl Inst Technol Dept IT Convergence Gumi 39177 South Korea Pusan Natl Univ Korean Southeast Ctr Ind Revolut Leader Educ 4 Busan South Korea Utah State Univ Dept Elect & Comp Engn Logan UT 84322 USA Deakin Univ Sch Informat Technol Waurn Ponds Vic 3216 Australia Technol Innovat Inst AI & Telecom Res Ctr Abu Dhabi U Arab Emirates Natl Yunlin Univ Sci & Technol Future Technol Res Ctr Touliu 64002 Yunlin Taiwan

With the rapid emergence of advanced technologies for wireless communications, automatic modulation classification (AMC) has been deployed in the physical layer to blindly identify the modulation fashion of an incoming signal at the receiver and consequently improve the efficiency of spectrum utilization and management. Although recent works on AMC have adopted deep learning with convolutional neural networks (CNNs) to deal with large-confusing signal data, they have shown to be vulnerable to channel deterioration by primitive architectures. In this letter, we design a high-performance CNN architecture, namely Residual-attention Convolutional Network (RanNet), that mainly involves multiple advanced processing blocks to learn intrinsic features of combined waveform data (including in-phase, quadrature, amplitude, and phase components). Each block incorporates attention connection and skip connection in a sophisticated-designed structure to strengthen relevant features and weaken irrelevant features while preventing the network from vanishing gradient. Simulation results on the RadioML 2018.01A dataset show that RanNet is robust to different channel impairments and outperforms state-of-the-art deep networks in terms of accuracy while having a reasonable complexity.

关键词： modulation Feature extraction Convolution Wireless communication Receivers Computer architecture Simulation automatic modulation classification convolutional neural network residual-attention connection structure

来源：评论

学校读者我要写书评

暂无评论

Channel-Robust automatic modulation classification Using Companding Spectral Quotient Cumulants

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2024年第11期73卷 17749-17753页

作者： Huang, Sai Chen, Yuting He, Jiashuo Chang, Shuo Feng, Zhiyong Beijing Univ Posts & T elecommun Key Lab Universal Wireless Commun Minist Educ Beijing 100876 Peoples R China

automatic modulation classification (AMC) is to identify the modulation format of the received signal corrupted by the channel effects and noise. Most existing works focus on the impact of noise while relatively little attention has been paid to the impact of channel effects. However, the instability posed by multipath fading channels leads to significant performance degradation. To mitigate the adverse effects of the multipath channel, we propose a channel-robust modulation classification framework named companding spectral quotient cumulant classification (CSQCC) for orthogonal frequency division multiplexing (OFDM) systems. Specifically, we first transform the received signal to the companding spectral quotient (CSQ) sequence by spectral circular shift division operations and modified- sigmoid function mapping. Secondly, we extract the companding spectral quotient cumulants (CSQCs) from the CSQ sequence. At last, the CSQCs serve as the inputs to train the artificial neural network (ANN) classifier and use the trained ANN to make the final decisions. Notably, the classifier is only trained using the data under the Additive White Gaussian Noise (AWGN) channel condition but tested under Rician multipath fading channel. Simulation results show that the proposed CSQCC method performs robust and superior classification performance when subjected to unknown Rician multipath fading channels, in comparison to other methods. Specifically, the proposed CSQCC method achieves nearly 100% classification accuracy at the signal-to-noise ratio (SNR) of 4 dB when testing under multiple channels but only training under AWGN channel.

关键词： modulation OFDM Fading channels Rician channels Feature extraction AWGN channels Symbols automatic modulation classification Rician multipath fading channel companding spectral quotient cumulant

来源：评论

学校读者我要写书评

暂无评论

MAMCOptimal on Accuracy and Efficiency for automatic modulation classification With Extended Signal Length

引用

IEEE COMMUNICATIONS LETTERS 2024年第12期28卷 2864-2868页

作者： Zhang, Yezhuo Zhou, Zinan Cao, Yichao Li, Guangyu Li, Xuanpeng Southeast Univ Sch Instrument Sci & Engn Nanjing 210096 Jiangsu Peoples R China Univ Sci & Technol Sch Comp Sci & Engn Nanjing 210094 Jiangsu Peoples R China

In automatic modulation classification (AMC), extended signal lengths offer a bounty of information, yet impede the model's adaptability, introduce more noise interference, extend the training and inference time, and increase memory usage. To bridge the gap between these requirements, we propose a novel AMC framework, designated as the Mamba-based automatic modulation classification (MAMC), which addresses the accuracy and efficiency requirements for long-sequence AMC. Specifically, we introduce the Selective State Space Model (Mamba), which enhances the model's capabilities in long-term memory and information selection, and reduces computational complexity and spatial overhead. We further design a denoising unit to filter out effective semantic information to improve accuracy. Rigorous experimental evaluations on the publicly available dataset RML2016.10 and TorchSig affirm that MAMC delivers superior recognition accuracy while necessitating minimal computational time and memory occupancy. Codes are available on https://***/ZhangYezhuo/MAMC.

关键词： Computational modeling Accuracy Mathematical models Adaptation models modulation Training Noise reduction Memory management Feature extraction Convolution automatic modulation classification mamba state space model cognitive radio long sequence

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Feature Fusion and Distribution Similarity Network for Few-Shot automatic modulation classification

引用

IEEE SIGNAL PROCESSING LETTERS 2024年 31卷 2890-2894页

作者： Tan, Haoyue Zhang, Zhenxi Li, Yu Shi, Xiaoran Zhou, Feng Xidian Univ Xian 710126 Peoples R China

automatic modulation classification (AMC), as a key technology of cognitive radio, has become a focal point of research. However, most deep learning-based AMC methods require an extensive number of labeled signals to acquire a comprehensive understanding of modulation types, placing substantial pressure on signal acquisition and labeling. To solve this issue, we propose a few-shot AMC (FSAMC) method to facilitate rapid generalization and recognition with limited data, namely multi-scale feature fusion and distribution similarity network (MS2F-DS). Firstly, we design a multi-scale feature fusion (MS2F) model, which aims to extract features with varying fields of view and boost feature fusion, enabling the derivation of contextual information from the signal. Furthermore, we introduce a distribution similarity (DS) classifier to address the insufficient measurement of current similarity measurement functions by considering both micro and macro perspectives of vectors, further increasing intra-class compactness and inter-class separability. Finally, extensive experiments were conducted on 3-way 1, 3, and 5-shot FSAMC tasks using public datasets RML2016.10a and RML2016.10b, and the results demonstrated the effectiveness of our method.

关键词： Feature extraction Convolution modulation Kernel Vectors Accuracy Data mining Convolutional neural networks Signal to noise ratio Current measurement automatic modulation classification distribution similarity few-shot learning multi-scale feature fusion

来源：评论

学校读者我要写书评

暂无评论

A Fast Multi-Loss Learning Deep Neural Network for automatic modulation classification

引用

IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING 2023年第6期9卷 1503-1518页

作者： Chang, Shuo Yang, Zheng He, Jiashuo Li, Rong Huang, Sai Feng, Zhiyong Beijing Univ Posts & Telecommun Sch Cyberspace Secur Beijing 100876 Peoples R China Beijing Univ Posts & Telecommun Key Lab Universal Wireless Commun Minist Educ Beijing 100876 Peoples R China State Radio Monitoring Ctr Beijing Radio Monitoring Stn Beijing 100876 Peoples R China

automatic modulation classification (AMC) enables significant applications in both the military and civilian domains. Inspired by the great success of deep learning (DL), a dual-stream neural network using in-phase/quadrature (I/Q) and amplitude/phase (A/P) data has made a superior performance. However, this dual-stream model is oversized (large number of parameters) and time-consuming (high inference time). To deal with that, a novel lightweight single stream neural network made up of group convolutional layer and transformer encoder layer is proposed. Specifically, the group convolutional layer divides the input tensor into different groups for convolution, which needs fewer parameters and has lower computational complexity than commonly used convolutional layers. For the transformer encoder layer, it can generate all time steps' outputs in parallel by using multi-head attention scheme, which is impossible for the commonly used recurrent-like layers (i.e., the recurrent-like layers output all time steps one by one.). Furthermore, a novel class center distance expansion loss incorporating the cross entropy loss is proposed for model training, which can enlarge the distance of different class centers Finally, the overlapping risk of different class features is reduced. As a result, the inference time of the proposed FastMLDNN is 13x faster than MLDNN, and the model size is near 1/6 as MLDNN, which only sacrifices 0.12% in accuracy. The source code has been released in the github: https://***/Singingkettle/ChangShuoRadioRecognition/tree/main/configs/fastmldnn.

关键词： modulation Hidden Markov models Task analysis Feature extraction Entropy Convolution Transformers automatic modulation classification deep neural network group convolutional layer transformer layer multi-loss functions

来源：评论

学校读者我要写书评

暂无评论

On classifiers for blind feature-based automatic modulation classification over multiple-input-multiple-output channels

引用

IET COMMUNICATIONS 2016年第7期10卷 790-795页

作者： Kharbech, Sofiane Dayoub, Iyad Zwingelstein-Colin, Marie Simon, Eric Pierre Higher Inst Technol Studies Gabes Dept Commun & Informat Technol STIC Gabes 6011 Tunisia Univ Valenciennes & Hainaut Cambresis IEMN DOAE Lab UMR CNRS 8520 F-59313 Valenciennes France Univ Lille 1 TELICE Lab IEMN UMR CNRS 8520 F-59100 Lille France

modulation recognition is crucial for a good environmental awareness required by cognitive radio systems. In this study, the authors design and compare models of four among the most commonly used classifiers for feature-based automatic modulation classification (FB-AMC) algorithms. Classifiers whose models will be designed are classification tree, K-nearest neighbours, artificial neural networks (ANNs), and support vector machines. In this study, they apply some statistical pattern recognition techniques in the context of blind FB-AMC over multiple-input-multiple-output channels. Comparison criteria are classification accuracy and computational complexity. To improve the impartiality of this comparison, each classifier is optimally deployed by selecting its optimal model with respect to their context. Model selection for the classifiers is done using the k-fold cross-validation' model validation technique. The comparison study, within the considered context, shows that ANN classifiers have the best performance/complexity tradeoff.

关键词： cognitive radio wireless channels MIMO communication statistical analysis blind feature classifiers automatic modulation classification multiple-input-multiple-output channels modulation recognition environmental awareness cognitive radio systems feature based automatic modulation classification algorithms FB-AMC algorithms artificial neural networks K-nearest neighbours support vector machines statistical pattern recognition techniques computational complexity optimal model

来源：评论

学校读者我要写书评

暂无评论

Dyadic Aggregated Autoregressive Model (DASAR) for automatic modulation classification

引用

IEEE ACCESS 2020年 8卷 156096-156103页

作者： Pinto-Orellana, Marco Antonio Hammer, Hugo Lewi Oslo Metropolitan Univ Fac Technol Art & Design Dept Mech Elect & Chem Engn N-0103 Oslo Norway Oslo Metropolitan Univ Fac Technol Art & Design Dept Informat Technol N-0103 Oslo Norway Oslo Metropolitan Univ Simula Metropolitan Ctr N-0103 Oslo Norway

In this article, 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 single-frequency 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.

关键词： Frequency shift keying Mathematical model Stochastic processes Resonant frequency Estimation automatic modulation classification signal processing spectrum modeling autoregressive model machine learning

来源：评论

学校读者我要写书评

暂无评论

High-Order Convolutional Attention Networks for automatic modulation classification in Communication

引用

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS 2023年第7期22卷 4600-4610页

作者： Zhang, Duona Lu, Yuanyao Li, Yundong Ding, Wenrui Zhang, Baochang North China Univ Technol Sch Informat Sci & Technol Beijing 100144 Peoples R China Beihang Univ Inst Unmanned Syst Beijing Peoples R China Beihang Univ Inst Artificial Intelligence Beijing Peoples R China Zhongguancun Lab Beijing 102206 Peoples R China

automatic modulation classification is a challenging and critical task in the field of communication. Deep convolutional networks (ConvNets) have been recently applied in cognitive radio and achieved remarkable performance. However, existing ConvNet-based methods mainly focus on the first-order architecture design, while fail to explore feature correlations of radio signal, which are particularly significant for useful information extraction in low signal-to-noise ratios (SNRs). In this paper, we propose high-order convolutional attention networks (HoCANs) for radio signal expression and feature correlation learning, based on a novel high-order attention mechanism to rescale the convolutional features along channel and sequence dimensions. High-order convolutional layer and covariance matrix after nonlinear transformation are led for tenser filtering with more discriminative representations of radio signals. Experiments have been conducted to validate the superiority of HoCANs which achieve state-of-the-art accuracy for automatic modulation classification on RADIOML 2018.01A dataset.

关键词： Convolution modulation Covariance matrices Deep learning Convolutional neural networks Correlation Computational modeling High-order convolution covariance matrix Index Terms attention mechanism automatic modulation classification intelligent communication

来源：评论

学校读者我要写书评

暂无评论

A Deep Ensemble-Based Wireless Receiver Architecture for Mitigating Adversarial Attacks in automatic modulation classification

引用

IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING 2022年第1期8卷 71-85页

作者： Sahay, Rajeev Brinton, Christopher G. Love, David J. Purdue Univ Elmore Family Sch Elect & Comp Engn W Lafayette IN 47907 USA

Deep learning-based automatic modulation classification (AMC) models are susceptible to adversarial attacks. Such attacks inject specifically crafted wireless interference into transmitted signals to induce erroneous classification predictions. Furthermore, adversarial interference is transferable in black box environments, allowing an adversary to attack multiple deep learning models with a single perturbation crafted for a particular classification model. In this work, we propose a novel wireless receiver architecture to mitigate the effects of adversarial interference in various black box attack environments. We begin by evaluating the architecture uncertainty environment, where we show that adversarial attacks crafted to fool specific AMC DL architectures are not directly transferable to different DL architectures. Next, we consider the domain uncertainty environment, where we show that adversarial attacks crafted on time domain and frequency domain features to not directly transfer to the altering domain. Using these insights, we develop our Assorted Deep Ensemble (ADE) defense, which is an ensemble of deep learning architectures trained on time and frequency domain representations of received signals. Through evaluation on two wireless signal datasets under different sources of uncertainty, we demonstrate that our ADE obtains substantial improvements in AMC classification performance compared with baseline defenses across different adversarial attacks and potencies.

关键词： Adversarial attacks automatic modulation classification machine learning in communications wireless security

来源：评论

学校读者我要写书评

暂无评论

Sequential Convolutional Recurrent Neural Networks for Fast automatic modulation classification

引用

IEEE ACCESS 2021年 9卷 27182-27188页

作者： Liao, Kaisheng Zhao, Yaodong Gu, Jie Zhang, Yaping Zhong, Yi Sci & Technol Elect Informat Control Lab Chengdu 610000 Peoples R China

A novel and efficient end-to-end learning model for automatic modulation classification is proposed for wireless spectrum monitoring applications, which automatically learns from the time domain in-phase and quadrature data without requiring the design of hand-crafted expert features. With the intuition of convolutional layers with pooling serving as the role of front-end feature distillation and dimensionality reduction, sequential convolutional recurrent neural networks are developed to take complementary advantage of parallel computing capability of convolutional neural networks and temporal sensitivity of recurrent neural networks. Experimental results demonstrate that the proposed architecture delivers overall superior performance in signal to noise ratio range above -10 dB, and achieves significantly improved classification accuracy from 80% to 92.1% at high signal to noise ratio range, while drastically reduces the average training and prediction time by approximately 74% and 67%, respectively. Response patterns learned by the proposed architecture are visualized to better understand the physics of the model. Furthermore, a comparative study is performed to investigate the impacts of various sequential convolutional recurrent neural network structure settings on classification performance. A representative sequential convolutional recurrent neural network architecture with the two-layer convolutional neural network and subsequent two-layer long short-term memory neural network is developed to suggest the option for fast automatic modulation classification.

关键词： Wireless communication Wireless sensor networks Recurrent neural networks Convolution modulation Computer architecture Monitoring automatic modulation classification convolutional neural networks cognitive radio deep learning recurrent neural networks spectrum monitoring

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：