检索结果-内蒙古大学图书馆

UniQGAN: Towards Improved modulation classification With Adversarial Robustness Using Scalable Generator Design

IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING 2024年第2期21卷 732-745页

作者： Lee, Insup Lee, Wonjun Korea Univ Sch Cybersecur Network & Secur Res Lab Seoul 02841 South Korea

automatic modulation classification (AMC) has been envisioned as a significant element for security issues at the physical layer due to its indispensable role in accurate communications. Recent attention to deep learning has impacted the AMC, which exhibits exceptional performance without manual feature engineering. To guarantee the accuracy and robustness of deep learning-based AMC, data augmentation is a critical issue. While existing studies have used several deep generative models to handle the data insufficiency, these studies face three challenges including low scalability, lengthy training time, and limited accuracy improvement. To this end, this paper presents UniQGAN, a novel unified generative architecture that models I/Q constellation diagrams from various signal-to-noise ratios (SNRs) using a single model. The proposed method enables the generation of high-quality data with a scalable generator, while requiring reduced training time. At the core of UniQGAN are multi-conditions embedding and multi-domains classification techniques that leverage both SNR and modulation type during the optimization process to enable unified modeling. Using abundant high-quality training data, UniQGAN accelerates the enhanced AMC with high performance and adversarial robustness. Experimental results demonstrate that the data generation by UniQGAN achieves superiority in terms of scalability, training time, and accuracy.

关键词： Adversarial robustness automatic modulation classification data augmentation deep learning GAN

来源：评论

学校读者我要写书评

暂无评论

Multi-terminal modulation classification network with rain attenuation interference for UAV MIMO-OFDM communications using blind signal reconstruction and gradient integration optimization

引用

DIGITAL SIGNAL PROCESSING 2025年 161卷

作者： Zhang, Gongjing Yan, Nan Dai, Jiashu An, Zeliang Li, Yifa Anhui Polytech Univ Sch Comp & Informat Wuhu 241060 Peoples R China Aalborg Univ Fac Engn & Sci Dept Elect Syst Antenna Propagat & Millimeter Wave Syst APMS Sect DK-9220 Aalborg Denmark

The field of automatic modulation classification (AMC) has emerged as a critical component in the advancement of next-generation intelligent Unmanned Aerial Vehicles (UAVs), 6G cognitive space communications, and spectrum regulation initiatives. Our research introduces an innovative AMC algorithm tailored for UAV MIMOOFDM communication systems. This algorithm leverages blind signal reconstruction, constellation density matrix analysis, multi-terminal decision fusion, and model optimization training to enhance performance. The algorithm begins with the application of blind source separation to reconstruct signals and bolster their representation capabilities. Subsequently, we introduce a novel feature, the Enhanced Constellation Density Matrix (CDM), crafted to withstand the challenges posed by UAV channel interferences while providing a robust representation of the constellation diagram. Building upon this foundation, we propose the UAV-Decision Fusion Network (UAV-DFNet), an advanced network that utilizes CDM features as inputs to deeply mine signal characteristics and achieve superior signal recognition accuracy. To further refine the classification precision, we implement dual strategies: multi-terminal decision fusion and gradient integration, into the UAV-DFNet. Comprehensive experimental results substantiate the effectiveness and superiority of our UAV-DFNet classifier over existing deep learning (DL)-based classifiers, demonstrating its potential to significantly advance the state of the art in UAV cognitive communications and beyond.

关键词： automatic modulation classification Unmanned aerial vehicle(UAV) Deep learning Gradient integration Multi-terminal decision fusion

来源：评论

学校读者我要写书评

暂无评论

Radio modulation classification Optimization Using Combinatorial Deep Learning Technique

引用

IEEE ACCESS 2024年 12卷 17552-17570页

作者： Elkhatib, Ziad Kamalov, Firuz Moussa, Sherif Ben Mnaouer, Adel Yagoub, Mustapha C. E. Yanikomeroglu, Halim Canadian Univ Dubai Dept Elect & Comp Engn Dubai U Arab Emirates Prince Sultan Univ Dept Comp Sci Engn Riyadh 66833 Saudi Arabia Univ Ottawa Dept Elect & Comp Engn Ottawa ON K1N 6N5 Canada Carleton Univ Dept Elect & Comp Engn Ottawa ON K1S 5B6 Canada

We present an automatic signal modulation classification model using combinatorial deep learning technique. Our proposed deep learning model increase accuracy for low Signal-to-Noise Ratio (SNR) and maintain a high classification accuracy for high SNR signals. Using a hybrid deep learning model combining both ConvLSTM with Transformer-block neural networks, the proposed modulation classifier architecture can learn the signal for both low and high SNR and get better accuracy for signals with high noise. The proposed deep learning modulation classification technique achieves improved classification accuracy of 66% for low SNR signals and 93.5% at high SNR showing that our model is robust under noisy signal modulation. Thus, getting better accuracy in lower SNR signals without sacrifice accuracy for higher SNR signals. An adaptive weighted focal loss function is proposed as an optimized loss function for efficient classification which can be used to control the outliers within a class imbalance and avoid underflow issues. Our deep learning radio modulation classification model works using raw signal without the need of denoising the noisy signal.

关键词： Signal to noise ratio modulation Feature extraction Deep learning Transformers Computational modeling Noise measurement automatic modulation classification dynamic spectrum allocation deep learning techniques transformer-block ConvLSTM feature-based extraction AI-based wireless communications

来源：评论

学校读者我要写书评

暂无评论

Refined Semi-Supervised modulation classification: Integrating Consistency Regularization and Pseudo-Labeling Techniques

引用

FUTURE INTERNET 2024年第2期16卷 38-38页

作者： Ma, Min Liu, Shanrong Wang, Shufei Shi, Shengnan Nanjing Vocat Coll Informat Technol Sch Network & Commun Nanjing 210023 Peoples R China Beijing Xiaomi Mobile Software Co Ltd Nanjing Branch Nanjing 210026 Peoples R China Nanjing Univ Posts & Telecommun Coll Telecommun & Informat Engn Nanjing 210003 Peoples R China

automatic modulation classification (AMC) plays a crucial role in wireless communication by identifying the modulation scheme of received signals, bridging signal reception and demodulation. Its main challenge lies in performing accurate signal processing without prior information. While deep learning has been applied to AMC, its effectiveness largely depends on the availability of labeled samples. To address the scarcity of labeled data, we introduce a novel semi-supervised AMC approach combining consistency regularization and pseudo-labeling. This method capitalizes on the inherent data distribution of unlabeled data to supplement the limited labeled data. Our approach involves a dual-component objective function for model training: one part focuses on the loss from labeled data, while the other addresses the regularized loss for unlabeled data, enhanced through two distinct levels of data augmentation. These combined losses concurrently refine the model parameters. Our method demonstrates superior performance over established benchmark algorithms, such as decision trees (DTs), support vector machines (SVMs), pi-models, and virtual adversarial training (VAT). It exhibits a marked improvement in the recognition accuracy, particularly when the proportion of labeled samples is as low as 1-4%.

关键词： automatic modulation classification semi-supervised learning consistency regularization data augmentation

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Learning and Nearest Neighbors for Out-of-Distribution modulation classification

引用

IEEE WIRELESS COMMUNICATIONS LETTERS 2025年第5期14卷 1466-1470页

作者： Tai, Yuchen Zeng, Yuan Gong, Yi Southern Univ Sci & Technol Dept Elect & Elect Engn Shenzhen 518055 Peoples R China Shenzhen Technol Univ Coll Dig Data & Internet Shenzhen 518118 Peoples R China

In non-cooperative communications, most modulation recognition tasks assume that the transmitted (training) signals and the received (test) signals are independent and identically distributed. However, the received signals may suffer from unknown impairments in practical communication systems, resulting in different data distributions between the test and training signals. Such test signals are regarded as out-of-distribution (OOD) signals. In this letter, we consider OOD scenarios with varying carrier frequency offset and varying sampling frequency and propose a new self-supervised method to improve the robustness of modulation recognition. The key idea is to use contrastive learning with information maximization to pre-train a feature extractor from unlabeled signals and leverage the feature space of the fine-tuned feature extractor with deep k-nearest neighbors to recognize modulation modes of the test signals. Experimental results show that our method has better representation and recognition accuracy than the baseline methods.

关键词： Feature extraction Nearest neighbor methods Training Contrastive learning Frequency modulation Streams Robustness Data mining Accuracy Receivers automatic modulation classification self-supervised learning out-of-distribution k-nearest neighbors

来源：评论

学校读者我要写书评

暂无评论

automatic modulation classification of Common Communication and Pulse Compression Radar Waveforms using Cyclic Features

Automatic Modulation Classification of Common Communication ...

引用

作者： John A. Hadjis Air Force Institute of Technology

学位级别：硕士

This research develops a feature-based maximum a posteriori (MAP) classification system and applies it to classify several common pulse compression radar and communi- cation modulations. All signal parameters are treated as unknown to the classifier system except SNR and the signal carrier frequency. The features are derived from estimated duty cycle, cyclic spectral correlation, and cyclic cumulants. The modulations considered in this research are BPSK, QPSK, 16-QAM, 64-QAM, 8-PSK, and 16-PSK communication modulations, as well as Barker 5 coded, Barker 11 coded, Barker 5,11 coded, Frank 49 coded, Px 49 coded, and LFM pulse compression modulations. Simulations show that average cor- rect signal modulation type classification %C > 90% is achieved for SNR > 9dB, average signal modulation family classification %C > 90% is achieved for SNR > 1dB, and an av- erage communication versus pulse compression radar modulation classification %C > 90% is achieved for SNR > 4dB. Also, it is shown that the classification performance using selected input features is sensitive to signal bandwidth but not to carrier frequency. Mis- matched bandwidth between training and testing signals caused degraded classification of %C 10% 14% over the simulated SNR range.

关键词： Spectral Correlation automatic modulation classification Cyclic Features Cyclic Cumulants Radar Communication

来源：评论

学校读者我要写书评

暂无评论

Distributed Deep Learning for modulation classification in 6G Cell-Free Wireless Networks

Distributed Deep Learning for Modulation Classification in 6...

引用

IEEE International Symposium on Dynamic Spectrum Access Networks (IEEE DySPAN)

作者： Verbruggen, Dieter Sallouha, Hazem Pollin, Sofie Katholieke Univ Leuven Dept Elect Engn ESAT WaveCoRE B-3000 Leuven Belgium

ISBN: (纸本)9798350317657;9798350317640

In the evolution of 6th Generation (6G) technology, the emergence of cell-free networking presents a paradigm shift, revolutionizing user experiences within densely deployed networks where distributed access points collaborate. However, the integration of intelligent mechanisms is crucial for optimizing the efficiency, scalability, and adaptability of these 6G cell-free networks. One application aiming to optimize spectrum usage is automatic modulation classification (AMC), a vital component for classifying and dynamically adjusting modulation schemes. This paper explores different distributed solutions for AMC in cell-free networks, addressing the training, computational complexity, and accuracy of two practical approaches. The first approach addresses scenarios where signal sharing is not feasible due to privacy concerns or fronthaul limitations. Our findings reveal that maintaining comparable accuracy is remarkably achievable, yet it comes with increased computational demand. The second approach considers a central model and multiple distributed models collaboratively classifying the modulation. This hybrid model leverages diversity gain through signal combining and requires synchronization and signal sharing. The hybrid model demonstrates superior performance, achieving a 2.5% improvement in accuracy with equivalent total computational load. Notably, the hybrid model distributes the computational load across multiple devices, resulting in a lower individual computational load.

关键词： Cell-free automatic modulation classification Distributed Processing Network Architecture Deep-Learning

来源：评论

学校读者我要写书评

暂无评论

Robust modulation classification in the Presence of Realistic Propagation in Rural Environment

Robust Modulation Classification in the Presence of Realisti...

引用

2024 International Telecommunications Conference, ITC-Egypt 2024

作者： Anis, Mark Aziz Elgamel, Sherif A. Elshafey, Mohamed A. Aboelazm, Mohamed Atta Military Technical College Electronic Warfare Department Cairo Egypt Military Technical College Department of Computer Engineering and Artificial Intelligence Cairo Egypt

ISBN: (纸本)9798350351408

automatic modulation classification (AMC) is crucial for optimizing spectrum resources in contemporary communication systems by determining the modulation type of received signals without prior information. Deep learning has demonstrated the potential to improve classification accuracy. However, current synthetic datasets lack the consideration of important large-scale fading channel conditions such as shadowing effects, which restrict the accuracy and robustness of modulation classification models. This study aims to overcome this constraint by proposing a method to integrate shadowing effects into the most common synthetic datasets. ITU 1546 standard is used to create an algorithm that models the shadowing effect and improves the generality conditions of modulation classification synthetic datasets. The performance of the proposed model is evaluated through extensive simulations, and compared to prior studies, using CNN and ResNet models, on RML 2016 and RML 2018 datasets. Our research emphasizes the significance of taking shadowing effects into account in AMC and confirms the efficacy of our method in enhancing classification resilience in realistic communication channels. © 2024 IEEE.

关键词： automatic modulation classification Deep Learning ITU 1546 Standard Shadowing Effects

来源：评论

学校读者我要写书评

暂无评论

Signal Processing-Based Deep Learning for Blind Symbol Decoding and modulation classification

引用

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS 2022年第1期40卷 82-96页

作者： Hanna, Samer Dick, Chris Cabric, Danijela Univ Calif Los Angeles Elect & Comp Engn Dept Los Angeles CA 90095 USA Xilinx Inc San Jose CA 95124 USA Nvidia Inc Santa Clara CA 95051 USA

Blindly decoding a signal requires estimating its unknown transmit parameters, compensating for the wireless channel impairments, and identifying the modulation type. While deep learning can solve complex problems, digital signal processing (DSP) is interpretable and can be more computationally efficient. To combine both, we propose the dual path network (DPN). It consists of a signal path of DSP operations that recover the signal, and a feature path of neural networks that estimate the unknown transmit parameters. By interconnecting the paths over several recovery stages, later stages benefit from the recovered signals and reuse all the previously extracted features. The proposed design is demonstrated to provide 5% improvement in modulation classification compared to alternative designs lacking either feature sharing or access to recovered signals. The estimation results of DPN along with its blind decoding performance are shown to outperform a blind signal processing algorithm for BPSK and QPSK on a simulated dataset. An over-the-air software-defined-radio capture was used to verify DPN results at high SNRs. DPN design can process variable length inputs and is shown to outperform relying on fixed length inputs with prediction averaging on longer signals by up to 15% in modulation classification.

关键词： modulation Decoding Neural networks Deep learning Signal processing Receivers Frequency modulation Blind symbol decoding deep learning automatic modulation classification

来源：评论

学校读者我要写书评

暂无评论

MIMO-OFDM modulation classification Using Three-Dimensional Convolutional Network

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2022年第6期71卷 6738-6743页

作者： Thien Huynh-The Toan-Van Nguyen Quoc-Viet Pham da Costa, Daniel Benevides Kim, Dong-Seong Kumoh Natl Inst Technol ICT Convergence Res Ctr Gumi 39177 Gyeongsangbuk D South Korea Kumoh Natl Inst Technol Dept IT Convergence Gumi 39177 Gyeongsangbuk D South Korea Utah State Univ Dept Elect & Comp Engn Logan UT 84321 USA Pusan Natl Univ Korean Southeast Ctr Ind Revolut Leader 4 Yangsan 50612 Gyeongsangnam D South Korea Technol Innovat Inst AI & Telecom Res Ctr Abu Dhabi 9639 U Arab Emirates Natl Yunlin Univ Sci & Technol Future Technol Res Ctr Touliu 64002 Yunlin Taiwan

automatic modulation classification (AMC) plays a vital role in cognitive radio to improve spectrum utilization efficiency, however, most of the existing works have focused on single-carrier communications in single-input single-output systems. In this paper, we propose an efficient AMC method for multiple-input multiple-output orthogonal frequency-division multiplexing (MIMO-OFDM) communication systems with the assumption of unknown frequency-selective fading channels and signal-to-noise ratio. At the receiver, the complex envelope samples of a burst signal acquired by multiple antennas are decomposed into in-phase and quadrature samples, which are then structured into a high-dimensional data array. To learn the modulation patterns from received signals, we develop a deep network, namely three-dimensional MIMO-OFDM convolutional neural network (MONet). With cuboidal convolution filters, the proposed MONet allows the network to capture underlying features as intra- and inter-antenna correlations at multi-scale signal representations. Relying on simulations, MONet achieves the classification accuracy of over 95% at 0 dB SNR under various channel impairments and shows the robustness with different MIMO antenna configurations.

关键词： modulation Receiving antennas OFDM Correlation Convolution Transmitting antennas Three-dimensional displays automatic modulation classification 3D convolutional neural network orthogonal frequency-division multiplexing multiple-input multiple-output

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：