Wenjian Ma
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Wenjian Ma has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Hanmin Sheng
School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, China
5 shared publications - Kai Chen
University of Electronic Science and Technology of China
4 shared publications Jie Gu
School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, China
2 shared publications- Yuhua Cheng
University of Electronic Science and Technology of China
2 shared publications - Bo Xu
School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, China
1 shared publication Chunxiao Wang
University of Electronic Science and Technology of China
1 shared publication
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 22 (11) , 10222-10233
Dynamic Weighted Adversarial Transferring Network-Guided Remaining Useful Life Prediction Under Cross-Domain Conditions
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 22 (11) , 10222-10233
Dynamic Weighted Adversarial Transferring Network-Guided Remaining Useful Life Prediction Under Cross-Domain Conditions
- 20 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 6886-6897
Robust Blind Modulation Recognition via Entropy-Based CFO-Adaptive Network
Automatic modulation recognition (AMR) plays a vital role in non-cooperative communication systems, yet carrier frequency offset (CFO) degrades its performance due to oscillator mismatches or Doppler shifts. While learning-based AMR methods have shown promising results under controlled conditions, they often overlook the effects of CFO. In realistic non-cooperative environments, the absence of pilot signals inevitably introduces CFO. Although blind synchronization techniques offer a potential solution, they typically introduce significant residual errors, reducing their practical effectiveness. To address this problem, we propose a novel blind compensation framework that jointly estimates and mitigates CFO while enabling end-to-end modulation recognition. The proposed method employs phase entropy minimization as an unsupervised objective to guide CFO correction and integrates an adaptive mechanism that selectively leverages uncertainty samples for online model refinement. This approach operates without prior knowledge of the signal structure, labeling, or protocol-specific parameters.
- 20 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 6886-6897
Robust Blind Modulation Recognition via Entropy-Based CFO-Adaptive Network
Automatic modulation recognition (AMR) plays a vital role in non-cooperative communication systems, yet carrier frequency offset (CFO) degrades its performance due to oscillator mismatches or Doppler shifts. While learning-based AMR methods have shown promising results under controlled conditions, they often overlook the effects of CFO. In realistic non-cooperative environments, the absence of pilot signals inevitably introduces CFO. Although blind synchronization techniques offer a potential solution, they typically introduce significant residual errors, reducing their practical effectiveness. To address this problem, we propose a novel blind compensation framework that jointly estimates and mitigates CFO while enabling end-to-end modulation recognition. The proposed method employs phase entropy minimization as an unsupervised objective to guide CFO correction and integrates an adaptive mechanism that selectively leverages uncertainty samples for online model refinement. This approach operates without prior knowledge of the signal structure, labeling, or protocol-specific parameters.
- 20 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 4198-4211
Domain Adaptive Hybrid Network for Automatic Modulation Recognition
Automatic modulation recognition (AMR) is an essential technology for spectrum sensing and management. Machine learning-based AMR techniques have garnered significant research interest. However, in practical applications, the effectiveness of AMR is hindered by variations in data distribution due to changes in carrier frequency, sample rate, and channel model. Existing deep learning methods struggle to adapt to these diverse distributions, and training separate datasets for each scenario is often impractical. To address these challenges, we propose a domain adaptive hybrid network (DAHNet) that integrates convolutional neural networks (CNNs) and long short-term memory (LSTM) networks. This architecture leverages the phase and amplitude of constellation points, as well as time-series data from I/Q sequences. Additionally, by explicitly minimizing the maximum mean discrepancy (MMD) between features from the source and target domains across multiple neural layers, we tackle the model generalization difficulties posed by varying propagation conditions and noise in complex electromagnetic environments. We validate our method using deep transfer learning on real-world data, with training results derived from the publicly available RadioML2016.10a and RadioML2018.01a datasets. Experimental results demonstrate the proposed method’s superior generalization ability across different spectrum scenarios.
- 20 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 4198-4211
Domain Adaptive Hybrid Network for Automatic Modulation Recognition
Automatic modulation recognition (AMR) is an essential technology for spectrum sensing and management. Machine learning-based AMR techniques have garnered significant research interest. However, in practical applications, the effectiveness of AMR is hindered by variations in data distribution due to changes in carrier frequency, sample rate, and channel model. Existing deep learning methods struggle to adapt to these diverse distributions, and training separate datasets for each scenario is often impractical. To address these challenges, we propose a domain adaptive hybrid network (DAHNet) that integrates convolutional neural networks (CNNs) and long short-term memory (LSTM) networks. This architecture leverages the phase and amplitude of constellation points, as well as time-series data from I/Q sequences. Additionally, by explicitly minimizing the maximum mean discrepancy (MMD) between features from the source and target domains across multiple neural layers, we tackle the model generalization difficulties posed by varying propagation conditions and noise in complex electromagnetic environments. We validate our method using deep transfer learning on real-world data, with training results derived from the publicly available RadioML2016.10a and RadioML2018.01a datasets. Experimental results demonstrate the proposed method’s superior generalization ability across different spectrum scenarios.
- 10 June 2025
- Published by Elsevier in Measurement
- Vol. 256
A high-precision and soft-hardware coordinated clock synchronization architecture for distributed acquisition systems
- 10 June 2025
- Published by Elsevier in Measurement
- Vol. 256
A high-precision and soft-hardware coordinated clock synchronization architecture for distributed acquisition systems
- 28 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 24 (5) , 4073-4085
Carrier Frequency Offset Robust Self-Compensating Neural Network
Automatic modulation recognition plays a critical role in modern communication systems as it provides valuable information for tasks such as signal recognition, interference jamming, and interception. Despite the significant potential of machine learning in this field, its practical effectiveness often falls short of expectations. In non-cooperative communication systems, irregular phase shifts and carrier frequency offsets (CFO) in the signal can negatively impact recognition accuracy. Conventional algorithms for compensating CFO, including those reliant on phase-locked loops, as well as various existing blind modulation techniques, encounter constraints in non-cooperative environments. This paper presents a novel CFO self-compensating neural network. A CFO compensation module is designed and integrated into the neural network. Additionally, a regularization term is proposed to evaluate the effectiveness of CFO compensation, which is incorporated into the loss function. The effectiveness of the proposed approach is demonstrated through experiments conducted on both publicly accessible datasets and experimentally measured data generated using software-defined radio. Experimental results demonstrate that the proposed new architecture maintains reliable recognition capabilities even in the presence of CFO. Additionally, it can be applied to all modulation schemes that are demodulable using constellation diagrams in non-cooperative conditions.
- 28 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 24 (5) , 4073-4085
Carrier Frequency Offset Robust Self-Compensating Neural Network
Automatic modulation recognition plays a critical role in modern communication systems as it provides valuable information for tasks such as signal recognition, interference jamming, and interception. Despite the significant potential of machine learning in this field, its practical effectiveness often falls short of expectations. In non-cooperative communication systems, irregular phase shifts and carrier frequency offsets (CFO) in the signal can negatively impact recognition accuracy. Conventional algorithms for compensating CFO, including those reliant on phase-locked loops, as well as various existing blind modulation techniques, encounter constraints in non-cooperative environments. This paper presents a novel CFO self-compensating neural network. A CFO compensation module is designed and integrated into the neural network. Additionally, a regularization term is proposed to evaluate the effectiveness of CFO compensation, which is incorporated into the loss function. The effectiveness of the proposed approach is demonstrated through experiments conducted on both publicly accessible datasets and experimentally measured data generated using software-defined radio. Experimental results demonstrate that the proposed new architecture maintains reliable recognition capabilities even in the presence of CFO. Additionally, it can be applied to all modulation schemes that are demodulable using constellation diagrams in non-cooperative conditions.
- Open Access
- 5 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 138850-138855
A Low-Loss and Full-360° Reflection-Type Phase Shifter for WLAN Wireless Backhaul Applications
This paper presents a reflective-type phase shifter (RTPS) capable of full 360° phase shift range with low-loss and compact for 5.47-5.85 GHz WLAN wireless backhaul. Intuitive and concise analyses of common reflective loads, including single-element single-tunable (SEST), dual-element single-tunable (DEST) and there-element single-tunable (TEST), are analyzed, elaborating their limitations. The four-elements dual-tunable (FEDT) load technique is proposed to increase the phase shift range. In addition, the influence factors of phase shift step and insertion loss (IL) are comprehensively discussed. Measurement results show that the proposed RTPS provides a phase shift range greater than 360°, a phase shift step less than 15°, an IL less than 2.3 dB in the entire frequency band. Meanwhile, the size of this RTPS is just only 9.5×8.2 mm 2 . Compared to other RTPS, this design has the advantages of low IL, compact size, wide-band, high precision, and easy to control.
- 5 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 138850-138855
Open AccessA Low-Loss and Full-360° Reflection-Type Phase Shifter for WLAN Wireless Backhaul Applications
This paper presents a reflective-type phase shifter (RTPS) capable of full 360° phase shift range with low-loss and compact for 5.47-5.85 GHz WLAN wireless backhaul. Intuitive and concise analyses of common reflective loads, including single-element single-tunable (SEST), dual-element single-tunable (DEST) and there-element single-tunable (TEST), are analyzed, elaborating their limitations. The four-elements dual-tunable (FEDT) load technique is proposed to increase the phase shift range. In addition, the influence factors of phase shift step and insertion loss (IL) are comprehensively discussed. Measurement results show that the proposed RTPS provides a phase shift range greater than 360°, a phase shift step less than 15°, an IL less than 2.3 dB in the entire frequency band. Meanwhile, the size of this RTPS is just only 9.5×8.2 mm 2 . Compared to other RTPS, this design has the advantages of low IL, compact size, wide-band, high precision, and easy to control.
- 5 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 23 (2) , 1447-1458
Transfer Reinforcement Learning for Dynamic Spectrum Environment
Reinforcement learning (RL) has proven to be an effective approach for achieving intelligence in Cognitive Radio (CR). Through interactions with the environment, RL enables a CR to optimize in an efficient and flexible manner. The vast majority of studies, however, are carried out in a spectrum environment with prefixed user access rules, typically with a constant transition probability and reward distribution. In fact, in a real-world spectrum environment, changes in access rules are common, which has a significant impact on the effectiveness of RL, while few studies have been conducted on this topic. This paper demonstrates how changes in primary user’s (PU) access rules affect RL strategies. To improve the secondary user’s (SU) performance for the dynamic spectrum environment, a transfer Deep Q-Network (DQN) is proposed, this method screens out knowledge from historical experience while avoiding interference from irrelevant information with an experience playback mechanism. Experiments show that this method outperforms traditional RL methods in terms of conflict rate, spectrum utilization rate, and convergence rate in the dynamic spectrum. Given the scarcity of studies on this topic, this study is expected to serve as a benchmark for the future research.
- 5 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 23 (2) , 1447-1458
Transfer Reinforcement Learning for Dynamic Spectrum Environment
Reinforcement learning (RL) has proven to be an effective approach for achieving intelligence in Cognitive Radio (CR). Through interactions with the environment, RL enables a CR to optimize in an efficient and flexible manner. The vast majority of studies, however, are carried out in a spectrum environment with prefixed user access rules, typically with a constant transition probability and reward distribution. In fact, in a real-world spectrum environment, changes in access rules are common, which has a significant impact on the effectiveness of RL, while few studies have been conducted on this topic. This paper demonstrates how changes in primary user’s (PU) access rules affect RL strategies. To improve the secondary user’s (SU) performance for the dynamic spectrum environment, a transfer Deep Q-Network (DQN) is proposed, this method screens out knowledge from historical experience while avoiding interference from irrelevant information with an experience playback mechanism. Experiments show that this method outperforms traditional RL methods in terms of conflict rate, spectrum utilization rate, and convergence rate in the dynamic spectrum. Given the scarcity of studies on this topic, this study is expected to serve as a benchmark for the future research.