Yuqing Xu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Yuqing Xu has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Zeliang An
School of Computer and Information, Anhui Polytechnic University, Wuhu, China
8 shared publications - Ming Shen
Aalborg University
5 shared publications - Abdullah Tahir
Department of Electronic Systems, Aalborg University, Aalborg, Denmark
4 shared publications - Gert Frolund Pedersen
Aalborg University
4 shared publications - Guangxia Xu
Guangzhou University
4 shared publications - Baoze Ma
School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China
2 shared publications
Latest Publications
- 21 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 5224-5243
A Spatio-Temporal Liquid Learning Network for Robust Electromagnetic Signal Identification in 6G RIS-Aided UAV Cognitive Communications With Composite Channel Impairments
In sixth-generation (6G) cognitive communications, deep learning (DL)-driven electromagnetic signal identification (ESI) emerges as a pivotal sensing paradigm to fortify physical layer security in reconfigurable intelligent surface (RIS)-aided uncrewed aerial vehicle (UAV) networks through intelligent waveform learning while preserving spectral efficiency. This paper proposes a robust RIS-aided UAV ESI framework under multiple channel impairments, addressing key challenges in practical deployment scenarios. Specifically, the methodology integrates a real-world RIS signal acquisition system comprising a Rohde & Schwarz vector signal generator (R&S-SMBV100B) emulating UAV transmissions, an FPGA-controled $16\times 16$ programmable RIS metasurface for signal reflection, and an R&S-FSW 67 GHz spectrum analyzer for receiving data capture, augmented by UAV 3D modeling and emulation to construct composite channel fading impairments. The proposed Spatio-Temporal Liquid Learning ESI Network (STL-ESINet) innovatively integrates spatial convolutional operations with temporal liquid learning mechanisms to extract discriminative high-dimensional spatio-temporal features from electromagnetic signals. A hierarchical classification module then synthesizes these spatio-temporal features for precise decision-making, while inter-class and intra-class feature statistics techniques rigorously validate the model interpretability. Experimental validation demonstrates that STL-RSINet outperforms existing DL-based approaches by achieving 97.38% and 100% recognition accuracy at SNR= 2dB and 12dB, respectively, while exhibiting robustness against composite channel impairments including path loss, multipath fading, and Doppler shifts. These results establish a new paradigm for secure RIS-UAV communications, offering both theoretical insights into waveform-learning security mechanisms and practical guidelines for hardware implementation in 6G cognitive communications.
- 21 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 5224-5243
A Spatio-Temporal Liquid Learning Network for Robust Electromagnetic Signal Identification in 6G RIS-Aided UAV Cognitive Communications With Composite Channel Impairments
In sixth-generation (6G) cognitive communications, deep learning (DL)-driven electromagnetic signal identification (ESI) emerges as a pivotal sensing paradigm to fortify physical layer security in reconfigurable intelligent surface (RIS)-aided uncrewed aerial vehicle (UAV) networks through intelligent waveform learning while preserving spectral efficiency. This paper proposes a robust RIS-aided UAV ESI framework under multiple channel impairments, addressing key challenges in practical deployment scenarios. Specifically, the methodology integrates a real-world RIS signal acquisition system comprising a Rohde & Schwarz vector signal generator (R&S-SMBV100B) emulating UAV transmissions, an FPGA-controled $16\times 16$ programmable RIS metasurface for signal reflection, and an R&S-FSW 67 GHz spectrum analyzer for receiving data capture, augmented by UAV 3D modeling and emulation to construct composite channel fading impairments. The proposed Spatio-Temporal Liquid Learning ESI Network (STL-ESINet) innovatively integrates spatial convolutional operations with temporal liquid learning mechanisms to extract discriminative high-dimensional spatio-temporal features from electromagnetic signals. A hierarchical classification module then synthesizes these spatio-temporal features for precise decision-making, while inter-class and intra-class feature statistics techniques rigorously validate the model interpretability. Experimental validation demonstrates that STL-RSINet outperforms existing DL-based approaches by achieving 97.38% and 100% recognition accuracy at SNR= 2dB and 12dB, respectively, while exhibiting robustness against composite channel impairments including path loss, multipath fading, and Doppler shifts. These results establish a new paradigm for secure RIS-UAV communications, offering both theoretical insights into waveform-learning security mechanisms and practical guidelines for hardware implementation in 6G cognitive communications.
- 2 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 1756-1774
Physics-Embedded Multicarrier Signal Recognition for Ka-Band Land Mobile Satellite Communications Systems Under Rain Attenuation and Shadowed-Rice Fading
In Ka-band land mobile satellite (LMS) communication systems, accurate multicarrier signal recognition (MSR) is crucial for detecting malicious radio signal interference. However, prior research has predominantly focused on terrestrial wireless multicarrier systems, often neglecting the substantial impact of weather-related factors such as rain attenuation on MSR algorithms. To bridge this gap, this paper proposes a Multi-Focus Denoised Cyclic Autocorrelation-Liquid Time Constant Network (MFDCA-LTCNet) algorithm for MSR, specifically designed to mitigate the effects of rain attenuation and Ricean shadowing fading. We first develop a cyclic autocorrelation (CA) denoising algorithm to effectively reduce noise interference in multicarrier signal features. Additionally, a DCT-based multi-focus denoised CA feature fusion algorithm is proposed, integrating Principal Component Analysis (PCA), wavelet transform, and contourlet transform to counteract residual channel fading effects from multiple perspectives. Next, our MFDCA-LTCNet incorporates a physics-embedded liquid dynamic learning mechanism, leveraging first-order ordinary differential equations to achieve a lightweight and robust MSR classifier. Monte Carlo simulations demonstrate the effectiveness and superiority of the proposed MFDCA-LTCNet over existing MSR methods in mitigating adverse Shadowed-Rice (SR) channel effects and rainfall attenuation for Ka-band LMS systems.
- 2 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 1756-1774
Physics-Embedded Multicarrier Signal Recognition for Ka-Band Land Mobile Satellite Communications Systems Under Rain Attenuation and Shadowed-Rice Fading
In Ka-band land mobile satellite (LMS) communication systems, accurate multicarrier signal recognition (MSR) is crucial for detecting malicious radio signal interference. However, prior research has predominantly focused on terrestrial wireless multicarrier systems, often neglecting the substantial impact of weather-related factors such as rain attenuation on MSR algorithms. To bridge this gap, this paper proposes a Multi-Focus Denoised Cyclic Autocorrelation-Liquid Time Constant Network (MFDCA-LTCNet) algorithm for MSR, specifically designed to mitigate the effects of rain attenuation and Ricean shadowing fading. We first develop a cyclic autocorrelation (CA) denoising algorithm to effectively reduce noise interference in multicarrier signal features. Additionally, a DCT-based multi-focus denoised CA feature fusion algorithm is proposed, integrating Principal Component Analysis (PCA), wavelet transform, and contourlet transform to counteract residual channel fading effects from multiple perspectives. Next, our MFDCA-LTCNet incorporates a physics-embedded liquid dynamic learning mechanism, leveraging first-order ordinary differential equations to achieve a lightweight and robust MSR classifier. Monte Carlo simulations demonstrate the effectiveness and superiority of the proposed MFDCA-LTCNet over existing MSR methods in mitigating adverse Shadowed-Rice (SR) channel effects and rainfall attenuation for Ka-band LMS systems.
- 19 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 61 (2) , 5253-5271
Modulation Identification for 6G Multibeam Satellite Systems Using Symbol-level Reconstruction and Physics-informed Scattering Transformation With Partial Channel Knowledge
Blind modulation identification (BMI) of 6G aeronautical multi-beam satellite (MBS) systems is prominently challenging due to the intricacy of Shadowed-Rician (SR) fading, limited channel state information (CSI), and inter-beam interference (IBI). These factors degrade the statistical properties of modulation signals, rendering conventional terrestrial BMI techniques inapplicable to MBS systems. To remedy the above flaws, this paper proposes a physics-informed scattering transformation network (RCR-SCTNet) using symbol-level rotation correlation reconstruction for BMI of MBS signals. Initially, the rotation correlation reconstruction (RCR) strategy with partial CSI is designed to transform destructive interference into constructive interference, alleviating IBI, SR and limited CSI problems. Then, the constellation intensity matrix is constructed as the training data for RCR-SCTNet with the help of domain knowledge. Finally, the scattering transformation module is employed to capture salient features with the lowest trainable parameters, and the gradient centralization (GC) strategy is further integrated into RCR-SCTNet to achieve stable and efficient training. Experimental results demonstrate that our RCR-SCTNet performs best among previous BMI methods in the severe MBS channels. Further, it remains a great generalization, is robust and has low computation complexity.
- 19 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 61 (2) , 5253-5271
Modulation Identification for 6G Multibeam Satellite Systems Using Symbol-level Reconstruction and Physics-informed Scattering Transformation With Partial Channel Knowledge
Blind modulation identification (BMI) of 6G aeronautical multi-beam satellite (MBS) systems is prominently challenging due to the intricacy of Shadowed-Rician (SR) fading, limited channel state information (CSI), and inter-beam interference (IBI). These factors degrade the statistical properties of modulation signals, rendering conventional terrestrial BMI techniques inapplicable to MBS systems. To remedy the above flaws, this paper proposes a physics-informed scattering transformation network (RCR-SCTNet) using symbol-level rotation correlation reconstruction for BMI of MBS signals. Initially, the rotation correlation reconstruction (RCR) strategy with partial CSI is designed to transform destructive interference into constructive interference, alleviating IBI, SR and limited CSI problems. Then, the constellation intensity matrix is constructed as the training data for RCR-SCTNet with the help of domain knowledge. Finally, the scattering transformation module is employed to capture salient features with the lowest trainable parameters, and the gradient centralization (GC) strategy is further integrated into RCR-SCTNet to achieve stable and efficient training. Experimental results demonstrate that our RCR-SCTNet performs best among previous BMI methods in the severe MBS channels. Further, it remains a great generalization, is robust and has low computation complexity.
- 18 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (1) , 425-434
Physics-Informed Scattering Transform Network for Modulation Recognition in 5G Industrial Cognitive Communications Considering Nonlinear Impairments in Active Phased Arrays
Modulation recognition (MR) plays a pivotal role due to its application in the spectrum sensing of 5G industrial cognitive communications and radio interference detection at the physical layer of the Internet of Things (IoT). Previous works have mainly focused on simulated fourth-generation (4G) multicarrier systems and ideal radio frequency (RF) scenarios. To bridge the gap between practice and theory, we propose a viable MR algorithm on all-physical testbeds, with nonlinear impairments of 28 GHz active phased arrays (APA). Specifically, our testbed is built on the Rohde&Schwarz (R&S) vector signal generation R&S-SMBV100B and spectrum analyzer R&S-FSW 67 GHz. To extract salient modulation patterns, we develop a physical-informed scattering transform (SCT) MR network (SCTMR-Net). With SCT modules, SCTMR-Net produces the translation-invariant and deformation-stable representations of 5-G signals by wavelet convolution, nonlinear modulus and low-pass filters. Extensive experiments on real-world measurement verify the viability of SCTMR-Net for high robustness to APA impairments.
- 18 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (1) , 425-434
Physics-Informed Scattering Transform Network for Modulation Recognition in 5G Industrial Cognitive Communications Considering Nonlinear Impairments in Active Phased Arrays
Modulation recognition (MR) plays a pivotal role due to its application in the spectrum sensing of 5G industrial cognitive communications and radio interference detection at the physical layer of the Internet of Things (IoT). Previous works have mainly focused on simulated fourth-generation (4G) multicarrier systems and ideal radio frequency (RF) scenarios. To bridge the gap between practice and theory, we propose a viable MR algorithm on all-physical testbeds, with nonlinear impairments of 28 GHz active phased arrays (APA). Specifically, our testbed is built on the Rohde&Schwarz (R&S) vector signal generation R&S-SMBV100B and spectrum analyzer R&S-FSW 67 GHz. To extract salient modulation patterns, we develop a physical-informed scattering transform (SCT) MR network (SCTMR-Net). With SCT modules, SCTMR-Net produces the translation-invariant and deformation-stable representations of 5-G signals by wavelet convolution, nonlinear modulus and low-pass filters. Extensive experiments on real-world measurement verify the viability of SCTMR-Net for high robustness to APA impairments.
- 25 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 17 (5) , 2012-2026
An Efficient RLWE-Based Privacy-Preserving Authentication Scheme Based on Edge Computing in Industrial Internet of Things
An industrial network connects devices, sensors, and other physical devices through wireless networks to collect, share, and analyze data to increase productivity, reduce costs, and improve product quality. Due to the accessibility of wireless channels to everyone, the number of malicious exploits of these services is increasing. Thus, confirming the validity of smart devices and servers and guaranteeing communication security are essential. Mutual authentication has become an essential security concern in wireless communication to meet this tendency. However, available techniques rely on prime factorization and discrete logarithm problems that cannot effectively resist quantum attacks. This study presents an anonymous authentication system based on edge computing for the Industrial Internet of Things (IIoT). Specifically, we devised an RLWE-based authentication method to withstand diverse attacks while improving operating efficiency. The proposed scheme achieves mutual authentication in a single-message exchange round, while ensuring user anonymity and perfect forward security. Security analysis and verification with ProVerif demonstrate that our scheme enhances privacy and reliability. Furthermore, experimental results show that our scheme outperforming existing schemes in terms of communication and computing costs
- 25 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 17 (5) , 2012-2026
An Efficient RLWE-Based Privacy-Preserving Authentication Scheme Based on Edge Computing in Industrial Internet of Things
An industrial network connects devices, sensors, and other physical devices through wireless networks to collect, share, and analyze data to increase productivity, reduce costs, and improve product quality. Due to the accessibility of wireless channels to everyone, the number of malicious exploits of these services is increasing. Thus, confirming the validity of smart devices and servers and guaranteeing communication security are essential. Mutual authentication has become an essential security concern in wireless communication to meet this tendency. However, available techniques rely on prime factorization and discrete logarithm problems that cannot effectively resist quantum attacks. This study presents an anonymous authentication system based on edge computing for the Industrial Internet of Things (IIoT). Specifically, we devised an RLWE-based authentication method to withstand diverse attacks while improving operating efficiency. The proposed scheme achieves mutual authentication in a single-message exchange round, while ensuring user anonymity and perfect forward security. Security analysis and verification with ProVerif demonstrate that our scheme enhances privacy and reliability. Furthermore, experimental results show that our scheme outperforming existing schemes in terms of communication and computing costs
- 12 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 60 (4) , 5226-5246
Collaborative Learning-Based Modulation Recognition for 6G Multibeam Satellite Communication Systems via Blind and Semiblind Channel Equalization
Blind modulation recognition (BMR) involves identifying the modulation scheme of intercepted signals, an essential component of terrestrial radio management. While deep learning (DL) has advanced BMR research in terrestrial contexts, 6 G multi-beam mobile satellite (MMS) systems present many challenges. One pivotal hurdle is the reliance on perfect channel-state information (CSI) for signal equalization in terrestrial MIMO BMR literature. In MMS systems, the vast satellite-ground distance can lead to outdated CSI, making traditional equalization techniques less effective. Addressing this, we introduce a viable BMR algorithm that leverages blind and semi- blind channel equalization to overcome challenges like inter-beam interference (IBI), limited CSI, and Shadowed-Rician (SR) fading. By transforming the MMS system into an equivalent MIMO satellite system, we enable enhanced MIMO channel equalization to counteract IBI and SR attenuations. Our proposed locality-globality convolutional-transformer deep neural network (LG-CTDNet) merges the strengths of CNNs in local feature extraction with Transformers in global feature discernment. A decision fusion strategy is then incorporated to utilize cooperative diversity across multiple eavesdroppers. Numerical tests validate the effectiveness of our blind and semi- blind equalization techniques, emphasizing their superiority over existing DL-based methods in satellite modulation signal identification even in conditions with limited or absent CSI.
- 12 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 60 (4) , 5226-5246
Collaborative Learning-Based Modulation Recognition for 6G Multibeam Satellite Communication Systems via Blind and Semiblind Channel Equalization
Blind modulation recognition (BMR) involves identifying the modulation scheme of intercepted signals, an essential component of terrestrial radio management. While deep learning (DL) has advanced BMR research in terrestrial contexts, 6 G multi-beam mobile satellite (MMS) systems present many challenges. One pivotal hurdle is the reliance on perfect channel-state information (CSI) for signal equalization in terrestrial MIMO BMR literature. In MMS systems, the vast satellite-ground distance can lead to outdated CSI, making traditional equalization techniques less effective. Addressing this, we introduce a viable BMR algorithm that leverages blind and semi- blind channel equalization to overcome challenges like inter-beam interference (IBI), limited CSI, and Shadowed-Rician (SR) fading. By transforming the MMS system into an equivalent MIMO satellite system, we enable enhanced MIMO channel equalization to counteract IBI and SR attenuations. Our proposed locality-globality convolutional-transformer deep neural network (LG-CTDNet) merges the strengths of CNNs in local feature extraction with Transformers in global feature discernment. A decision fusion strategy is then incorporated to utilize cooperative diversity across multiple eavesdroppers. Numerical tests validate the effectiveness of our blind and semi- blind equalization techniques, emphasizing their superiority over existing DL-based methods in satellite modulation signal identification even in conditions with limited or absent CSI.
- 25 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 69 (9) , 3959-3963
A Novel Blind High-Order Modulation Classifier Using Accumulated Constellation Temporal Convolution for OSTBC-OFDM Systems
Deep learning (DL)-based blind modulation classification (BMC) has flourished in the single carrier system for low-order modulation signals. However, the research of DL-based BMC has not been well explored in the OSTBC-OFDM system (Orthogonal Space-Time Block Coded-Orthogonal Frequency Division Multiplexing), especially high-order modulation types. This brief proposes a novel BMC algorithm for high-order modulation signals (e.g., 4096QAM), which is based on reconstruction processing and accumulation constellation temporal convolution BMC network (ACTC-BMCNet). First, we employ the blind zero-forcing (ZF) equalization algorithm to reconstruct the damaged signal and enhance the signal representation power. Then, the constellation accumulation strategy is executed on the raw constellation diagram (CD) to generate the accumulated CD (ACD) image for reducing constellation dispersion. After that, instead of traditional 2D convolution, the constellation temporal convolution enabled in ACTC-BMCNet is leveraged to reduce computational overhead and extract the more discriminative feature. Monte-Carlo experiments are performed on fourteen modulation signals, and results indicate that the proposed ACTC-BMCNet possesses a superior classification accuracy and a faster recognition speed than the DL-based benchmark classifiers.
- 25 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 69 (9) , 3959-3963
A Novel Blind High-Order Modulation Classifier Using Accumulated Constellation Temporal Convolution for OSTBC-OFDM Systems
Deep learning (DL)-based blind modulation classification (BMC) has flourished in the single carrier system for low-order modulation signals. However, the research of DL-based BMC has not been well explored in the OSTBC-OFDM system (Orthogonal Space-Time Block Coded-Orthogonal Frequency Division Multiplexing), especially high-order modulation types. This brief proposes a novel BMC algorithm for high-order modulation signals (e.g., 4096QAM), which is based on reconstruction processing and accumulation constellation temporal convolution BMC network (ACTC-BMCNet). First, we employ the blind zero-forcing (ZF) equalization algorithm to reconstruct the damaged signal and enhance the signal representation power. Then, the constellation accumulation strategy is executed on the raw constellation diagram (CD) to generate the accumulated CD (ACD) image for reducing constellation dispersion. After that, instead of traditional 2D convolution, the constellation temporal convolution enabled in ACTC-BMCNet is leveraged to reduce computational overhead and extract the more discriminative feature. Monte-Carlo experiments are performed on fourteen modulation signals, and results indicate that the proposed ACTC-BMCNet possesses a superior classification accuracy and a faster recognition speed than the DL-based benchmark classifiers.
- 18 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 69 (6) , 3002-3006
An Advancing Temporal Convolutional Network for 5G Latency Services via Automatic Modulation Recognition
Automatic modulation recognition (AMR) has received significant attention since its decisive factor for modern non-cooperative communication systems. Meanwhile, the existing works on deep learning technique achieve exceptional accuracy; however, these works dissatisfy real-time requirements for 5G low-latency services. To remedy this flaw, this brief proposes a low-latency AMR method by applying temporal convolutional network (TCN). Furthermore, the principal component analysis (PCA)-based TCN and uniform subsampling-based TCN methods are leveraged to further alleviate the computation complexity and render real-time TCN viable. Experimental results demonstrate that the proposed method can achieve lower complexity and superior recognition accuracy than existing works and pave the way for 5G low-latency services.
- 18 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 69 (6) , 3002-3006
An Advancing Temporal Convolutional Network for 5G Latency Services via Automatic Modulation Recognition
Automatic modulation recognition (AMR) has received significant attention since its decisive factor for modern non-cooperative communication systems. Meanwhile, the existing works on deep learning technique achieve exceptional accuracy; however, these works dissatisfy real-time requirements for 5G low-latency services. To remedy this flaw, this brief proposes a low-latency AMR method by applying temporal convolutional network (TCN). Furthermore, the principal component analysis (PCA)-based TCN and uniform subsampling-based TCN methods are leveraged to further alleviate the computation complexity and render real-time TCN viable. Experimental results demonstrate that the proposed method can achieve lower complexity and superior recognition accuracy than existing works and pave the way for 5G low-latency services.