Article
Computer Science, Information Systems
Chao Wang, Xianglin Wei, Jianhua Fan, Yongyang Hu, Long Yu, Qing Tian
Summary: This article proposes a novel universal adversarial perturbation attack under frequency and data constraints (UAP-FD) to solve the challenges faced when applying UAP directly to RF signals. UAP-FD counteracts perturbation neutralization, promotes imperceptibility, and adapts to data-free black-box settings. Experimental results demonstrate that UAP-FD achieves a higher fooling rate, maintains good imperceptibility and shift-invariance, and reduces the accuracy of the ADNN model.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Yilin Sun, Edward A. Ball
Summary: AMC is a rapidly evolving technology suitable for 5G and 6G technology, where machine learning can provide efficient modulation classification. This article introduces two dynamic systems for modulation classification that do not rely on received signal phase and frequency locks, with the GRF technique performing well in low SNR environments.
IET COMMUNICATIONS
(2022)
Article
Chemistry, Analytical
Ke Zang, Wenqi Wu, Wei Luo
Summary: This paper introduces a neural network parameter optimization method based on sparse learning, which can reduce parameters without compromising network performance. Experimental results demonstrate that the proposed method effectively reduces model parameters and improves network generalization ability.
Article
Telecommunications
Jiawei Zhang, Tiantian Wang, Zhixi Feng, Shuyuan Yang
Summary: With the advancement of modern communications technology, automatic modulation classification (AMC) has become increasingly important in complex wireless communication environments. Existing deep learning-based AMC schemes have limitations in utilizing feature maps, whereas the proposed adaptive wavelet network (AWN) overcomes this limitation by introducing adaptive wavelet decomposition and channel attention mechanism. AWN explicitly extracts features from multiple frequency bands and selects optimal frequencies, efficiently integrating signal properties in the frequency domain. Simulation results demonstrate the superiority of the proposed AMC scheme over benchmark schemes in terms of performance and computational complexity.
IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING
(2023)
Article
Engineering, Electrical & Electronic
Kuiyu Chen, Jingyi Zhang, Si Chen, Shuning Zhang, Huichang Zhao
Summary: This article proposes an X-net recognition network for detecting radiation signals under intense noise background using only simulation samples for training. The method improves recognition performance under low signal-to-noise ratios through pre-training and a supplementary classification network, and demonstrates outstanding performance in comparative experiments.
DIGITAL SIGNAL PROCESSING
(2022)
Article
Chemistry, Analytical
Zhan Ge, Hongyu Jiang, Youwei Guo, Jie Zhou
Summary: A deep learning model was designed to automatically identify modulation schemes, showing that different features performed differently under various channel conditions.
Article
Engineering, Electrical & Electronic
Fuxin Zhang, Chunbo Luo, Jialang Xu, Yang Luo
Summary: This article proposes an autoencoder-based method to enhance the information interaction between in-phase/quadrature (I/Q) channels of the input data for automatic modulation recognition (AMR). The method utilizes an autoencoder to correlate the features of I/Q data and obtain the interaction feature, which is concatenated with the original I/Q data as model inputs. The proposed method improves recognition accuracy and has a smaller time overhead compared to complex-valued neural networks.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2023)
Article
Computer Science, Information Systems
Hao Zhang, Lu Yuan, Guangyu Wu, Fuhui Zhou, Qihui Wu
Summary: This paper proposes a novel involution-enabled AMC scheme utilizing the bottleneck structure of residual networks, enhancing the discrimination capability and expressiveness of the model through a self-attention mechanism. Simulation results demonstrate that the proposed scheme outperforms other benchmark schemes in terms of classification performance and convergence speed.
IEEE WIRELESS COMMUNICATIONS LETTERS
(2021)
Article
Computer Science, Information Systems
To Truong An, Byung Moo Lee
Summary: In a non-cooperative communication environment, automatic modulation classification (AMC) is crucial for analyzing signals and classifying different types of signal modulation. Deep learning (DL)-based AMC has been proposed as an efficient method to achieve high classification performance. However, current DL-AMC methods have limited generalization capabilities under varying noise conditions, especially at low signal-to-noise ratios (SNRs). This paper introduces a threshold autoencoder denoiser convolutional neural network (TADCNN) that improves classification accuracy by 70% at low SNR and achieves higher accuracy compared to the current AMC model on the RML2016.10A dataset.
Article
Computer Science, Information Systems
Hany S. Hussein, Mohamed Hassan Essai Ali, Mohammed Ismeil, Mohamed N. Shaaban, Mona Lotfy Mohamed, Hany A. Atallah
Summary: This study proposes robust CNN-based AMC techniques, which eliminate the need for feature extraction and can achieve high classification accuracy. The developed techniques utilize different classification layers and can automatically learn the features from the transmitted signals during training.
Article
Computer Science, Information Systems
Thien Huynh-The, Quoc-Viet Pham, Toan-Van Nguyen, Thanh Thi Nguyen, Rukhsana Ruby, Ming Zeng, Dong-Seong Kim
Summary: Automatic modulation classification (AMC) is a fundamental signal processing technique in wireless communication systems. Deep learning (DL) has been increasingly used to improve modulation classification performance by leveraging the underlying characteristics of radio signals. Various deep architectures, such as neural networks, recurrent neural networks, and convolutional neural networks, have been studied for AMC in wireless communications.
Article
Computer Science, Information Systems
Clayton A. Harper, Mitchell A. Thornton, Eric C. Larson
Summary: This research investigates various architectures for automatic modulation classification and analyzes the impacts of hyperparameters and design elements on classification accuracy. The study shows that using specific design elements can achieve higher accuracy in classifying different modulation types for intercepted signal bursts.
Article
Chemistry, Analytical
Mengtao Wang, Youchen Fan, Shengliang Fang, Tianshu Cui, Donghang Cheng
Summary: This paper proposes a joint automatic modulation discrimination (AMC) model that combines deep learning (DL) and expert features to address the challenges in distinguishing 16QAM and 64QAM. Experimental results show that the proposed model outperforms benchmark networks and improves signal classification accuracy and QAM signal discrimination.
Article
Engineering, Electrical & Electronic
Jibin Che, Li Wang, Xueru Bai, Chunheng Liu, Feng Zhou
Summary: This paper proposes a novel few-shot learning framework, STHFEN, for automatic modulation classification in wireless spectrum monitoring. STHFEN utilizes two feature extraction networks to map wireless communication signals into spatial and temporal feature spaces, and a hybrid inference classifier is designed to combine the classification results in these spaces. Experimental results demonstrate the effectiveness and robustness of STHFEN in few-shot AMC tasks.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2022)
Article
Telecommunications
Hao Zhang, Fuhui Zhou, Qihui Wu, Wei Wu, Rose Qingyang Hu
Summary: A novel automatic modulation classification scheme inspired by face recognition and utilizing a multi-scale network was proposed, with a new loss function combining center loss and cross entropy loss to learn discriminative and separable features for improved classification performance. Extensive simulation results showed that the proposed scheme outperformed benchmark schemes in terms of classification accuracy.
IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING
(2022)
