Search Results (38)

Specific emitter identification (SEI), which classifies radio transmitters by extracting hardware-intrinsic radio frequency fingerprints (RFFs), faces critical challenges in noise robustness, generalization under limited training data and class imbalance. To address these limitations, we propose adaptive deep ensemble learning (ADEL)—a framework that integrates heterogeneous neural networks including convolutional neural networks (CNN), multilayer perception (MLP) and transformer for hierarchical feature extraction. Crucially, ADEL also adopts adaptive weighted predictions of the three base classifiers based on reconstruction errors and hybrid losses for robust classification. The methodology employs (1) three heterogeneous neural networks for robust feature extraction; (2) the hybrid losses refine feature space structure and preserve feature integrity for better feature generalization; and (3) collaborative decision-making via adaptive weighted reconstruction errors of the base learners for precise inference. Extensive experiments are performed to validate the effectiveness of ADEL. The results indicate that the proposed method significantly outperforms other competing methods. ADEL establishes a new SEI paradigm through robust feature extraction and adaptive decision integrity, enabling potential deployment in space target identification and situational awareness under limited training samples and imbalanced classes conditions. Full article

Traditional specific emitter identification (SEI) systems often suffer significant performance degradation when confronted with previously unseen signal sources, underscoring the critical need for accurate detection and rejection of novel-class instances. To address this limitation, we propose an Integrated Deep Feature Representation and Isolation Forest (IDFIF) method for identifying novel-class radiation emitters. IDFIF begins by employing a convolutional neural network (CNN) to extract embedding features from raw In-phase/Quadrature (IQ) signals, enhancing inter-class separability while suppressing intra-class variability. These deep features are then used to construct an unsupervised iForest that learns the statistical distribution of known classes, enabling the effective detection of anomalies via a threshold-based scoring mechanism. Experiments conducted on a real-world ADS-B dataset demonstrate that the proposed method achieves a novel-class detection accuracy of over 94%, significantly outperforming comparative methods. Furthermore, the method exhibits low sensitivity to known-class samples, thereby ensuring robustness and generalization under open-set conditions. The proposed IDFIF method is promising for deployment in challenging electromagnetic environments. Full article

Specific Emitter Identification (SEI) is a specialized technique for identifying different emitters by analyzing the unique characteristics embedded in received signals, known as Radio Frequency Fingerprints (RFFs), and SEI plays a crucial role in civilian applications. Recently, various SEI methods based on deep learning have been proposed. However, in real-world scenarios, the scarcity of accurately labeled data poses a significant challenge to these methods, which typically rely on large-scale supervised training. To address this issue, we propose a novel SEI framework based on self-supervised contrastive learning. Our approach comprises two stages: an unsupervised pretraining phase that uses contrastive loss to learn discriminative RFF representations from unlabeled data, and a supervised fine-tuning stage regularized through virtual adversarial training (VAT) to improve generalization under limited labels. This framework enables effective feature learning while mitigating overfitting. To validate the effectiveness of the proposed method, we collected real-world satellite navigation signals using a 40-meter antenna and conducted extensive experiments. The results demonstrate that our approach achieves outstanding SEI performance, significantly outperforming several mainstream SEI methods, thereby highlighting the practical potential of contrastive self-supervised learning in satellite transmitter identification. Full article

Specific emitter identification (SEI) is a core technology for wireless device security that plays a crucial role in protecting wireless communication systems from various security threats. However, current deep learning-based SEI methods heavily rely on large amounts of labeled data for supervised training, facing challenges in non-cooperative communication scenarios. To address these issues, this paper proposes a novel contrastive asymmetric masked learning-based SEI (CAML-SEI) method, effectively solving the problem of SEI under scarce labeled samples. The proposed method constructs an asymmetric auto-encoder architecture, comprising an encoder network based on channel squeeze-and-excitation residual blocks to capture radio frequency fingerprint (RFF) features embedded in signals, while employing a lightweight single-layer convolutional decoder for masked signal reconstruction. This design promotes the learning of fine-grained local feature representations. To further enhance feature discriminability, a learnable non-linear mapping is introduced to compress high-dimensional encoded features into a compact low-dimensional space, accompanied by a contrastive loss function that simultaneously achieves feature aggregation of positive samples and feature separation of negative samples. Finally, the network is jointly optimized by combining signal reconstruction and feature contrast tasks. Experiments conducted on real-world ADS-B and Wi-Fi datasets demonstrate that the proposed method effectively learns generalized RFF features, and the results show superior performance compared with other SEI methods. Full article

Radio Frequency Machine Learning (RFML) has in recent years become a popular method for performing a variety of classification tasks on received signals. Among these tasks is Specific Emitter Identification (SEI), which seeks to associate a received signal with the physical emitter that transmitted it. Many different model architectures, including individual classifiers and ensemble methods, have proven their capabilities for producing high accuracy classification results when performing SEI. Though the works studying different model architectures report on successes, there is a notable absence regarding the examination of systemic failures and negative traits associated with learned behaviors. This work studies those failure patterns for a 64-radio SEI classification problem by isolating common patterns in incorrect classification results across multiple model architectures and two distinct control variables: Signal-to-Noise Ratio (SNR) and the quantity of training data utilized. This work finds that many of the RFML-based models devolve to selecting from amongst a small subset of classes (≈10% of classes) as SNRs decrease and that observed errors are reasonably consistent across different SEI models and architectures. Moreover, our results validate the expectation that ensemble models are generally less brittle, particularly at a low SNR, yet they appear not to be the highest-performing option at a high SNR. Full article

Specific emitter identification (SEI), as an emerging physical-layer security authentication method, is crucial for maintaining information security in the Internet of Things. However, existing deep learning-based SEI methods require extensive labeled data for training, which are often unavailable in untrusted scenarios. Furthermore, due to the subtle nature of radio-frequency fingerprints, unsupervised SEI struggles to achieve high accuracy in identification without the guidance of labels. In this paper, we propose an unsupervised SEI method based on group label-driven contrastive learning (GLD-CL). We propose a novel method for constructing the dataset: all input samples derived from the same received signal segment are grouped together and assigned a unique identifier, termed the group label. Based on this, we improve the loss function of self-supervised contrastive learning. With the assistance of group labels, the feature vectors of the same class in the feature space become more closely clustered, enhancing the accuracy of unsupervised SEI. Extensive experimental results based on real-world datasets demonstrate that the normalized mutual information of GLD-CL achieves 96.4% accuracy, representing an improvement of 5.68% or more compared to the baseline algorithms. Furthermore, GLD-CL exhibits robust performance, achieving good identification accuracy across various signal-to-noise ratio scenarios. Full article

Specific emitter identification (SEI) methods based on deep learning (DL) have effectively addressed complex, multi-dimensional signal recognition tasks by leveraging deep neural networks. However, this advancement introduces challenges such as model parameter redundancy and high feature dimensionality, which pose limitations for resource-constrained (RC) edge devices, especially in Internet of Things (IoT) applications. To tackle these problems, we propose an RC-SEI method based on efficient design and model compression. Specifically, for efficient design, we have developed a lightweight convolution network (LCNet) that aims to balance performance and complexity. Regarding model compression, we introduce sparse regularization techniques in the fully connected (FC) layer, achieving over 99% feature dimensionality reduction. Furthermore, we have comprehensively evaluated the proposed method on public automatic-dependent surveillance-broadcast (ADS-B) and Wi-Fi datasets. Simulation results demonstrate that our proposed method exhibits superior performance in terms of both recognition accuracy and model complexity. Specifically, LCNet achieved accuracies of 99.40% and 99.90% on the ADS-B and Wi-Fi datasets, respectively, with only 33,510 and 33,544 parameters. These results highlight the feasibility and potential of our proposed RC-SEI method for RC scenarios. Full article

With the help of specific emitter identification (SEI), the control efficiency of the satellite communication systems can be effectively improved by discriminating the individual satellite. In recent years, deep learning has been introduced into SEI to enhance identification performance because of its powerful classification capability. However, classical real-valued neural networks exhibit some limitations in extracting the radio frequency fingerprint (RFF) features from complex signals, limiting the improvement of identification accuracy. Thus, we proposed a complex-valued conditional adversarial generative network (CC-GAN) which can directly deal with complex signals. Through adversarial learning between the generator and the discriminator, the generator implements direct mapping from the dynamic noisy signals to the noise-free signals. In addition, an auxiliary classifier is introduced into the discriminator to make the discriminator able to label the sample, which effectively compress the proposed model. The experimental results for a signal dataset collected in a real environment demonstrated that the proposed model is superior to the traditional denoising methods in denoising performance, which effectively improves the identification accuracy under dynamic noises. Furthermore, the proposed model outperforms other deep learning models in terms of identification performance under various SNRs, which can effectively improve the robustness and adaptability of the SEI system for communication satellites in dynamic noisy environments. Full article

Specific emitter identification (SEI) is a technique that identifies the emitter through physical layer features contained in radio signals, and it is widely used in tasks such as identifying illegal transmitters and authentication. Thanks to the development of deep learning, SEI tasks based on deep learning have achieved significant improvements in recognition performance. However, illegal transmitters often broadcast for short durations and at low frequencies, resulting in very limited available training samples. In such cases, directly training deep learning models may lead to underfitting issues, thereby reducing recognition accuracy. In this paper, to address the issue of traditional methods struggling to classify transmitters when there is a scarcity of emitter samples and limited training data, we propose a method based on TFC-CNN. We propose a TFC-CNN method. Specifically, we first use continuous wavelet transform (CWT) as a data augmentation method to construct time–wavelet spectrum sample pairs. Then, we use complex-valued neural networks (CVNNs) and deep convolutional neural networks (DCNNs) to extract the hidden emitter identity features from the time and wavelet spectrum samples. We train the model using the normalized temperature-scaled cross-entropy (NT-Xent) loss and cross-entropy (CE) loss, ensuring the consistency of feature vector distributions across the two modalities with cosine loss. Finally, we fine-tune the model to achieve SEI tasks with few samples. Experimental results on open-source WiFi datasets and automatic dependent surveillance–broadcast (ADS-B) datasets show that our proposed method outperforms existing state-of-the-art methods. With only 5% of the training samples, the recognition accuracy for the ADS-B test dataset is 84.10%, and for the WiFi test dataset, it is 96.99%. Full article

Specific emitter identification (SEI) is a highly active research area in physical layer security. In this paper, we propose a SEI scheme based on time-frequency domain channel, spatial, and self-attention mechanisms (TF-CSS) for deep networks with few-shot learning. The scheme first uses an asymmetric masked auto-encoder (AMAE) with attention mechanisms for unsupervised learning, then removes the decoder and adds a linear layer as a classifier, and finally fine-tunes the whole network to achieve effective recognition. The scheme improves the feature representation and identification performance of complex-value neural network (CVNN)-based AMAE by adding channel, spatial, and self-attention mechanisms in the time-frequency domain, respectively. Experimental results show that this scheme outperforms the recognition accuracy of contrastive learning and other MAE/AMAE-based methods in 30 classes of LoRa baseband signal transmitter recognition with different few-shot scenarios and observation lengths. Full article

Specific emitter identification (SEI) is a promising physical-layer authentication technique that serves as a crucial complement to upper-layer authentication mechanisms. SEI capitalizes on the inherent radio frequency fingerprints stemming from circuit discrepancies, which are intrinsic hardware properties and challenging to counterfeit. Recently, various deep learning (DL)-based SEI methods have been proposed, achieving outstanding performance. However, collecting and annotating substantial data for novel or unknown radiation sources is not only time-consuming but also cost-intensive. To address this issue, this paper proposes a few-shot (FS) metric learning-based time-frequency fusion network. To enhance the discriminative capability for radiation source signals, the model employs a convolutional block attention module (CBAM) and feature transformation to effectively fuse the raw signal’s time domain and time-frequency domain representations. Furthermore, to improve the extraction of discriminative features under FS scenarios, the proxy-anchor loss and center loss are introduced to reinforce intra-class compactness and inter-class separability. Experiments on the ADS-B and Wi-Fi datasets demonstrate that the proposed TFAF-Net consistently outperforms existing models in FS-SEI tasks. On the ADS-B dataset, TFAF-Net achieves a 9.59% higher accuracy in 30-way 1-shot classification compared to the second-best model, and reaches an accuracy of 85.02% in 10-way classification. On the Wi-Fi dataset, TFAF-Net attains 90.39% accuracy in 5-way 1-shot classification, outperforming the next best model by 6.28%, and shows a 13.18% improvement in 6-way classification. Full article

Specific emitter identification is a challenge in the field of radar signal processing. Its aims to extract individual fingerprint features of the signal. However, early works are all designed using either signal or time–frequency image and heavily rely on the calculation of hand-crafted features or complex interactions in high-dimensional feature space. This paper introduces the time–frequency multimodal feature fusion network, a novel architecture based on multimodal feature interaction. Specifically, we designed a time–frequency signal feature encoding module, a wvd image feature encoding module, and a multimodal feature fusion module. Additionally, we propose a feature point filtering mechanism named FMM for signal embedding. Our algorithm demonstrates high performance in comparison with the state-of-the-art mainstream identification methods. The results indicate that our algorithm outperforms others, achieving the highest accuracy, precision, recall, and F1-score, surpassing the second-best by 9.3%, 8.2%, 9.2%, and 9%. Notably, the visual results show that the proposed method aligns with the signal generation mechanism, effectively capturing the distinctive fingerprint features of radar data. This paper establishes a foundational architecture for the subsequent multimodal research in SEI tasks. Full article

Deep learning has brought great development to radar emitter identification technology. In addition, specific emitter identification (SEI), as a branch of radar emitter identification, has also benefited from it. However, the complexity of most deep learning algorithms makes it difficult to adapt to the requirements of the low power consumption and high-performance processing of SEI on embedded devices, so this article proposes solutions from the aspects of software and hardware. From the software side, we design a Transformer variant network, lightweight convolutional Transformer (LW-CT) that supports parameter sharing. Then, we cascade convolutional neural networks (CNNs) and the LW-CT to construct a one-dimensional-CNN-Transformer(1D-CNN-Transformer) lightweight neural network model that can capture the long-range dependencies of radar emitter signals and extract signal spatial domain features meanwhile. In terms of hardware, we design a low-power neural network accelerator based on an FPGA to complete the real-time recognition of radar emitter signals. The accelerator not only designs high-efficiency computing engines for the network, but also devises a reconfigurable buffer called “Ping-pong CBUF” and two-level pipeline architecture for the convolution layer for alleviating the bottleneck caused by the off-chip storage access bandwidth. Experimental results show that the algorithm can achieve a high recognition performance of SEI with a low calculation overhead. In addition, the hardware acceleration platform not only perfectly meets the requirements of the radar emitter recognition system for low power consumption and high-performance processing, but also outperforms the accelerators in other papers in terms of the energy efficiency ratio of Transformer layer processing. Full article

In future aviation surveillance, the demand for higher real-time updates for global flights can be met by deploying automatic dependent surveillance–broadcast (ADS-B) receivers on low Earth orbit satellites, capitalizing on their global coverage and terrain-independent capabilities for seamless monitoring. Specific emitter identification (SEI) leverages the distinctive features of ADS-B data. High data collection and annotation costs, along with limited dataset size, can lead to overfitting during training and low model recognition accuracy. Transfer learning, which does not require source and target domain data to share the same distribution, significantly reduces the sensitivity of traditional models to data volume and distribution. It can also address issues related to the incompleteness and inadequacy of communication emitter datasets. This paper proposes a distributed sensor system based on transfer learning to address the specific emitter identification. Firstly, signal fingerprint features are extracted using a bispectrum transform (BST) to train a convolutional neural network (CNN) preliminarily. Decision fusion is employed to tackle the challenges of the distributed system. Subsequently, a transfer learning strategy is employed, incorporating frozen model parameters, maximum mean discrepancy (MMD), and classification error measures to reduce the disparity between the target and source domains. A hyperbolic space module is introduced before the output layer to enhance the expressive capacity and data information extraction. After iterative training, the transfer learning model is obtained. Simulation results confirm that this method enhances model generalization, addresses the issue of slow convergence, and leads to improved training accuracy. Full article

Transfer learning (TL) techniques, which leverage prior knowledge gained from data with different distributions to achieve higher performance and reduced training time, are often used in computer vision (CV) and natural language processing (NLP), but have yet to be fully utilized in the field of radio frequency machine learning (RFML). This work systematically evaluates how the training domain and task, characterized by the transmitter (Tx)/receiver (Rx) hardware and channel environment, impact radio frequency (RF) TL performance for example automatic modulation classification (AMC) and specific emitter identification (SEI) use-cases. Through exhaustive experimentation using carefully curated synthetic and captured datasets with varying signal types, channel types, signal to noise ratios (SNRs), carrier/center frequencys (CFs), frequency offsets (FOs), and Tx and Rx devices, actionable and generalized conclusions are drawn regarding how best to use RF TL techniques for domain adaptation and sequential learning. Consistent with trends identified in other modalities, our results show that RF TL performance is highly dependent on the similarity between the source and target domains/tasks, but also on the relative difficulty of the source and target domains/tasks. Results also discuss the impacts of channel environment and hardware variations on RF TL performance and compare RF TL performance using head re-training and model fine-tuning methods. Full article