Multisignal Modulation Classification Using Sliding Window Detection and Complex Convolutional Network in Frequency Domain

Hou, Changbo; Liu, Guowei; Tian, Qiao; Zhou, Zhichao; Hua, Lijie; Lin, Yun

doi:10.1109/jiot.2022.3167107

Cited by 94 publications

(25 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These existing feature-based methods are easy to implement in practice, however, hand-crafted features and hard-coding criteria for AMC make scaling to new modulation types challenging. Recently, due to the superior performance of deep learning, many researchers have resorted to various deep neural network (DNN) architectures for AMC [12][13][14][15][16][17][18][19]. For example, a convolutional neural network (CNN) was used for AMC in [12].…”

Section: Introductionmentioning

confidence: 99%

“…Later convolutional long short-term deep neural networks (CLDNN), long short-term memory neural networks (LSTM), and deep residual networks (ResNet) were proposed to improve the classification performance [16]. A complex CNN was proposed in [17] for the identification of signal spectrum information. A spatio-temporal hybrid deep neural network was proposed in [18] for AMC which is based on multi-channels and multifunction blocks.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Attention-Based Adversarial Robust Distillation in Radio Signal Classifications for Low-Power IoT Devices

Zhang

Lambotharan

Zheng

et al. 2023

IEEE Internet Things J.

View full text Add to dashboard Cite

Due to great success of transformers in many applications such as natural language processing and computer vision, transformers have been successfully applied in automatic modulation classification. We have shown that transformer-based radio signal classification is vulnerable to imperceptible and carefully crafted attacks called adversarial examples. Therefore, we propose a defense system against adversarial examples in transformer-based modulation classifications. Considering the need for computationally efficient architecture particularly for Internet of Things (IoT)-based applications or operation of devices in environment where power supply is limited, we propose a compact transformer for modulation classification. The advantages of robust training such as adversarial training in transformers may not be attainable in compact transformers. By demonstrating this, we propose a novel compact transformer that can enhance robustness in the presence of adversarial attacks. The new method is aimed at transferring the adversarial attention map from the robustly trained large transformer to a compact transformer. The proposed method outperforms the state-of-the-art techniques for the considered white-box scenarios including fast gradient method and projected gradient descent attacks. We have provided reasoning of the underlying working mechanisms and investigated the transferability of the adversarial examples between different architectures. The proposed method has the potential to protect the transformer from the transferability of adversarial examples.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Attention-Based Adversarial Robust Distillation in Radio Signal Classifications for Low-Power IoT Devices

Zhang

Lambotharan

Zheng

et al. 2023

IEEE Internet Things J.

View full text Add to dashboard Cite

show abstract

“…In [7], a zero-shot learning for signal recognition is proposed. In [8], a modulated signal classification method based on sliding window detection and complex convolutional networks is proposed. In [9], the evaluation analysis yields the advantages of plural networks in the signal classification task for radiation sources, such as higher recognition accuracy and faster learning rate.…”

Section: Introductionmentioning

confidence: 99%

Performance Evaluation System Based on Multi-Indicators for Signal Recognition

Li¹,

Yang

Chen

2023

IEEE Access

View full text Add to dashboard Cite

Nowadays, the electromagnetic environment is becoming more and more complex, and it is increasingly difficult to accurately identify electromagnetic signals. At the same time, the quality of models and algorithms largely determines the final result of electromagnetic signal recognition, and a comprehensive and holistic evaluation system is needed to assess the quality of model or algorithm performance in the field of electromagnetic signal recognition. To address this phenomenon, this paper uses different machine learning models and AdaBoost algorithms to identify 100 classes of WiFi radiation source electromagnetic signals. In this paper, the classification performance, complexity and robustness of the models are evaluated comprehensively in three aspects respectively, and a multi-dimensional evaluation system for signal recognition is constructed, and the differences between different model algorithms in signal recognition effects are compared and analyzed, and the correlations between each evaluation index in different dimensions are explored. The experimental results show that different machine learning models and algorithms have different recognition effects on electromagnetic signals, among which the recognition accuracy of ResNet can reach more than 90%, but its computational complexity is high and easily affected by noise. the DNN recognition effect is poor, with the highest computational complexity, but not easily affected by noise. the AdaBoost algorithm does not necessarily improve the recognition classification accuracy of the underlying classifier. The evaluation system established in this paper is meaningful for assessing the performance of models and algorithms.

show abstract

“…With the development of information technology, SEI based on RFF has gradually become an important research topic in the field of signal communication. This technology is of great significance in many fields, such as physical layer security authentication [1], band protection [2], malicious device authentication [3], prevention of cloning attacks, and location identification.…”

Section: Introductionmentioning

confidence: 99%

Specific Emitter Identification of Frequency Hopping Signals Based on Feature Extraction and Deep Residual Network

Xie

Yang

et al. 2022

IEEE Access

View full text Add to dashboard Cite

In the modern war with complex and changeable electromagnetic environment, Specific Emitter Identification (SEI) is an important and difficult problem, which is of great significance in obtaining intelligence information, identifying ourselves or foe, and specifying combat plans. In order to solve the problems of low accuracy, poor robustness and difficulty in extracting effective individual features of frequency hopping (FH) radio set, this paper studies the generation of PSK signal constellation to proposes a radio frequency fingerprint(RFF) based on constellation. We also improved the existing RFF extraction method, combined with the deep learning recognition method based on the Deep Residual Network (ResNet), to achieve effective feature fusion. By comparing different input methods, we found that the recognition accuracy is improved, and reaches 96.16% in the outfield experiments of 15 FH radio sets. In addition, we also designed a ResNet structure to compare the recognition accuracy under different signal-to-noise ratio(SNR), different network structure, different number of individuals, different modulation methods and different recognition algorithms, which proved the superiority of our method.

show abstract

Multisignal Modulation Classification Using Sliding Window Detection and Complex Convolutional Network in Frequency Domain

Cited by 94 publications

References 33 publications

Attention-Based Adversarial Robust Distillation in Radio Signal Classifications for Low-Power IoT Devices

Attention-Based Adversarial Robust Distillation in Radio Signal Classifications for Low-Power IoT Devices

Performance Evaluation System Based on Multi-Indicators for Signal Recognition

Specific Emitter Identification of Frequency Hopping Signals Based on Feature Extraction and Deep Residual Network

Contact Info

Product

Resources

About