Shanping Yu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Shanping Yu has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Kenan Lai
School of Computer Science and Technology, Beijing Institute of Technology Beijing China
2 shared publications - Yan Zhang
Beijing Institute of Technology
2 shared publications Zixin Ye
Beijing Institute of Technology
2 shared publications- Bob Zhang
University of Macau, Macau SAR, China
1 shared publication - Byonghyo Shim
Department of Electrical and Computer Engineering and the Institute of New Media and Communications, Seoul National University, Seoul, Republic of Korea
1 shared publication - Chang Sun
School of Computer Science Beijing University of Posts and Telecommunications Beijing 100876
1 shared publication
Latest Publications
- 19 October 2026
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 36 (6) , e70447
DFTA : Dual‐Flow Trajectory Alignment for Medical Pathology Image Synthesis
Generating medical images with complex anatomical structures frequently faces challenges of morphological distortion and limited diversity. We investigate these issues within an established latent generative pipeline by introducing Dual‐Flow Trajectory Alignment (DFTA), a Flow‐Matching formulation with parallel mask‐flow and image‐flow conditioning. Rather than replacing standard latent encoders, UNet backbones, or ControlNet‐style conditioning, DFTA focuses on how the paired conditional trajectories are regularized and sampled. During training, trajectory consistency guidance uses image flow as a geometric reference for the mask flow; an Online Straight Euler Augmentation (OSEA) mechanism generates intermediate pseudo‐samples. At inference, conditional stochastic flow sampling introduces controlled variation into otherwise deterministic integration. Images generated by our model improve downstream task performance, achieving the best generation metrics and competitive results across downstream classification models. In particular, for medical image segmentation tasks, our method improves the mean Dice coefficient (mDice) and mean Intersection over Union (mIoU) of SegFormer by 1.79% and 1.92%, respectively, and increases the mDice and mIoU of UNet by 2.06% and 2.20%, respectively. The code is available at: https://github.com/yanguanyue/DFTA‐ .
- 19 October 2026
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 36 (6) , e70447
DFTA : Dual‐Flow Trajectory Alignment for Medical Pathology Image Synthesis
Generating medical images with complex anatomical structures frequently faces challenges of morphological distortion and limited diversity. We investigate these issues within an established latent generative pipeline by introducing Dual‐Flow Trajectory Alignment (DFTA), a Flow‐Matching formulation with parallel mask‐flow and image‐flow conditioning. Rather than replacing standard latent encoders, UNet backbones, or ControlNet‐style conditioning, DFTA focuses on how the paired conditional trajectories are regularized and sampled. During training, trajectory consistency guidance uses image flow as a geometric reference for the mask flow; an Online Straight Euler Augmentation (OSEA) mechanism generates intermediate pseudo‐samples. At inference, conditional stochastic flow sampling introduces controlled variation into otherwise deterministic integration. Images generated by our model improve downstream task performance, achieving the best generation metrics and competitive results across downstream classification models. In particular, for medical image segmentation tasks, our method improves the mean Dice coefficient (mDice) and mean Intersection over Union (mIoU) of SegFormer by 1.79% and 1.92%, respectively, and increases the mDice and mIoU of UNet by 2.06% and 2.20%, respectively. The code is available at: https://github.com/yanguanyue/DFTA‐ .
- 20 September 2026
- Published by Wiley in Transactions on Emerging Telecommunications Technologies
- Vol. 37 (10) , e70495
LigPPFNet: A Lightweight Multimodal Fusion Method for Palmprint and Palm Vein Recognition
Due to their high stability, accuracy, and security, palmprint and palm vein recognition offer significant advantages in biometric applications. However, traditional deep neural network models typically suffer from high computational complexity and large parameters, which limit their application in practical embedded devices and mobile terminals. To address this limitation, we propose a novel lightweight palmprint and palm vein fusion network (LigPPFNet) for multimodal recognition. To address this limitation, we propose LigPPFNet, a lightweight multimodal fusion network for palmprint and palm vein recognition. We first construct PPFNet as the base multimodal fusion architecture, which employs a cross‐modal high‐order fusion mechanism to promote feature interaction and complementarity between palmprint and palm vein features. Building upon PPFNet, we further develop LigPPFNet as the final lightweight model through a series of targeted structural simplifications. Specifically, we simplify the feature fusion module, reduce the channel scale of the competitive blocks, remove the computationally expensive attention structure, and redesign the classification head. Extensive experiments on three public datasets show that, under the adopted experimental protocol, LigPPFNet achieved 100% recognition accuracy. Compared with its base architecture, LigPPFNet reduced the number of parameters by 97.8% (from 818.08 M to 17.86 M) and FLOPs by 93.9% (from 952.97 M to 58.48 M), indicating its potential for resource‐constrained biometric applications.
- 20 September 2026
- Published by Wiley in Transactions on Emerging Telecommunications Technologies
- Vol. 37 (10) , e70495
LigPPFNet: A Lightweight Multimodal Fusion Method for Palmprint and Palm Vein Recognition
Due to their high stability, accuracy, and security, palmprint and palm vein recognition offer significant advantages in biometric applications. However, traditional deep neural network models typically suffer from high computational complexity and large parameters, which limit their application in practical embedded devices and mobile terminals. To address this limitation, we propose a novel lightweight palmprint and palm vein fusion network (LigPPFNet) for multimodal recognition. To address this limitation, we propose LigPPFNet, a lightweight multimodal fusion network for palmprint and palm vein recognition. We first construct PPFNet as the base multimodal fusion architecture, which employs a cross‐modal high‐order fusion mechanism to promote feature interaction and complementarity between palmprint and palm vein features. Building upon PPFNet, we further develop LigPPFNet as the final lightweight model through a series of targeted structural simplifications. Specifically, we simplify the feature fusion module, reduce the channel scale of the competitive blocks, remove the computationally expensive attention structure, and redesign the classification head. Extensive experiments on three public datasets show that, under the adopted experimental protocol, LigPPFNet achieved 100% recognition accuracy. Compared with its base architecture, LigPPFNet reduced the number of parameters by 97.8% (from 818.08 M to 17.86 M) and FLOPs by 93.9% (from 952.97 M to 58.48 M), indicating its potential for resource‐constrained biometric applications.
- 1 April 2026
- Published by Springer Nature
- p. 354-362
Entanglement-Preserving Control of Three-Qubit Systems Under Local Markovian Dephasing
- 1 April 2026
- Published by Springer Nature
- p. 354-362
Entanglement-Preserving Control of Three-Qubit Systems Under Local Markovian Dephasing
- Open Access
DualStream Contextual Fusion Network: Efficient Target Speaker Extraction by Leveraging Mixture and Enrollment Interactions
Target speaker extraction focuses on extracting a target speech signal from an environment with multiple speakers by leveraging an enrollment. Existing methods predominantly rely on speaker embeddings obtained from the enrollment, potentially disregarding the contextual information and the internal interactions between the mixture and enrollment. In this paper, we propose a novel DualStream Contextual Fusion Network (DCF-Net) in the time-frequency (T-F) domain. Specifically, DualStream Fusion Block (DSFB) is introduced to obtain contextual information and capture the interactions between contextualized enrollment and mixture representation across both spatial and channel dimensions, and then rich and consistent representations are utilized to guide the extraction network for better extraction. Experimental results demonstrate that DCF-Net outperforms state-of-the-art (SOTA) methods, achieving a scale-invariant signal-to-distortion ratio improvement (SI-SDRi) of 21.6 dB on the benchmark dataset, and exhibits its robustness and effectiveness in both noise and reverberation scenarios. In addition, the wrong extraction results of our model, called target confusion problem, reduce to 0.4%, which highlights the potential of DCF-Net for practical applications.
Open AccessDualStream Contextual Fusion Network: Efficient Target Speaker Extraction by Leveraging Mixture and Enrollment Interactions
Target speaker extraction focuses on extracting a target speech signal from an environment with multiple speakers by leveraging an enrollment. Existing methods predominantly rely on speaker embeddings obtained from the enrollment, potentially disregarding the contextual information and the internal interactions between the mixture and enrollment. In this paper, we propose a novel DualStream Contextual Fusion Network (DCF-Net) in the time-frequency (T-F) domain. Specifically, DualStream Fusion Block (DSFB) is introduced to obtain contextual information and capture the interactions between contextualized enrollment and mixture representation across both spatial and channel dimensions, and then rich and consistent representations are utilized to guide the extraction network for better extraction. Experimental results demonstrate that DCF-Net outperforms state-of-the-art (SOTA) methods, achieving a scale-invariant signal-to-distortion ratio improvement (SI-SDRi) of 21.6 dB on the benchmark dataset, and exhibits its robustness and effectiveness in both noise and reverberation scenarios. In addition, the wrong extraction results of our model, called target confusion problem, reduce to 0.4%, which highlights the potential of DCF-Net for practical applications.
- 15 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 23 (6) , 6347-6361
Beamforming Design With Partial Channel Estimation and Feedback for FDD RIS-Assisted Systems
Beamforming design with partial channel estimation and feedback for frequency-division duplexing (FDD) reconfigurable intelligent surface (RIS) assisted systems is considered in this paper. We leverage the observation that path angle information (PAI) varies more slowly than path gain information (PGI). Then, several dominant paths are selected among all the cascaded paths according to the known PAI for maximizing the spectral efficiency of downlink data transmission. To acquire the dominating path gain information (DPGI, also regarded as the path gains of selected dominant paths) at the base station (BS), we propose a DPGI estimation and feedback scheme by jointly beamforming design at BS and RIS. Both the required number of downlink pilot signals and the length of uplink feedback vector are reduced to the number of dominant paths, and thus we achieve a great reduction of the pilot overhead and feedback overhead. Furthermore, we optimize the active BS beamformer and passive RIS beamformer by exploiting the feedback DPGI to further improve the spectral efficiency. From numerical results, we demonstrate the superiority of our proposed algorithms over the conventional schemes.
- 15 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 23 (6) , 6347-6361
Beamforming Design With Partial Channel Estimation and Feedback for FDD RIS-Assisted Systems
Beamforming design with partial channel estimation and feedback for frequency-division duplexing (FDD) reconfigurable intelligent surface (RIS) assisted systems is considered in this paper. We leverage the observation that path angle information (PAI) varies more slowly than path gain information (PGI). Then, several dominant paths are selected among all the cascaded paths according to the known PAI for maximizing the spectral efficiency of downlink data transmission. To acquire the dominating path gain information (DPGI, also regarded as the path gains of selected dominant paths) at the base station (BS), we propose a DPGI estimation and feedback scheme by jointly beamforming design at BS and RIS. Both the required number of downlink pilot signals and the length of uplink feedback vector are reduced to the number of dominant paths, and thus we achieve a great reduction of the pilot overhead and feedback overhead. Furthermore, we optimize the active BS beamformer and passive RIS beamformer by exploiting the feedback DPGI to further improve the spectral efficiency. From numerical results, we demonstrate the superiority of our proposed algorithms over the conventional schemes.
- 19 July 2023
- Published by Springer Nature
- p. 174-183
An Intelligent Wireless Signal Detection and Recognition Platform
- 19 July 2023
- Published by Springer Nature
- p. 174-183
An Intelligent Wireless Signal Detection and Recognition Platform
- Open Access
- 19 April 2022
- Published by MDPI AG in Electronics
- Vol. 11 (9) , 1297
Weather-Conscious Adaptive Modulation and Coding Scheme for Satellite-Related Ubiquitous Networking and Computing
As a crucial part of ubiquitous networking and computing (UNC) technologies, low earth orbit (LEO) satellite communications aim at providing internet connectivity services everywhere. To improve the spectrum efficiency of satellite-to-ground communications, adaptive modulation and coding (AMC) are widely used, which can adjust the modulation and coding types according to the varying channel condition. However, satellite-to-ground communication channels have the characterizations such as fast dynamic change, fast switching, and significant fading. These characterizations make it challenging to predict the channel state information accurately and, thus, to perform accurate AMC. For example, rain loss is one of the crucial factors in satellite-to-ground channel fading. In general, it is difficult to build an integrated global model for rain loss because it varies in different regions around the world. Moreover, for the emerging applications of multiple antennas on satellites, the conventional look-up table method cannot cope with the high-dimensional inputs of the multiple antennas. To tackle the above challenges, we propose an AMC method based on deep learning (DL) and deep reinforcement learning (DRL) for ubiquitous satellite-to-ground networks. The proposed method directly processes real-time global weather and location information in the environment and intelligently selects encoding schemes to maximize system throughput. Simulation results show that the proposed method can increase the total throughput. The total number of correctly transmitted bits per unit time is improved, and the efficiency of the satellite-to-ground communication is enhanced.
- 19 April 2022
- Published by MDPI AG in Electronics
- Vol. 11 (9) , 1297
Open AccessWeather-Conscious Adaptive Modulation and Coding Scheme for Satellite-Related Ubiquitous Networking and Computing
As a crucial part of ubiquitous networking and computing (UNC) technologies, low earth orbit (LEO) satellite communications aim at providing internet connectivity services everywhere. To improve the spectrum efficiency of satellite-to-ground communications, adaptive modulation and coding (AMC) are widely used, which can adjust the modulation and coding types according to the varying channel condition. However, satellite-to-ground communication channels have the characterizations such as fast dynamic change, fast switching, and significant fading. These characterizations make it challenging to predict the channel state information accurately and, thus, to perform accurate AMC. For example, rain loss is one of the crucial factors in satellite-to-ground channel fading. In general, it is difficult to build an integrated global model for rain loss because it varies in different regions around the world. Moreover, for the emerging applications of multiple antennas on satellites, the conventional look-up table method cannot cope with the high-dimensional inputs of the multiple antennas. To tackle the above challenges, we propose an AMC method based on deep learning (DL) and deep reinforcement learning (DRL) for ubiquitous satellite-to-ground networks. The proposed method directly processes real-time global weather and location information in the environment and intelligently selects encoding schemes to maximize system throughput. Simulation results show that the proposed method can increase the total throughput. The total number of correctly transmitted bits per unit time is improved, and the efficiency of the satellite-to-ground communication is enhanced.
- 14 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 10 (3) , 994-1003
Agent-Based Model of Mass Campus Shooting: Comparing Hiding and Moving of Civilians
The follow-up impact of the campus shooting incident is enormous. Due to a large number of minors (vulnerable groups) and complex building environments, the school is one of the main targets of terrorists. The Sandy Hook Elementary School shooting in 2012 poses a challenge to social and public security. Considering the dichotomous characteristics of the people shot and the impact of the refuge area on the crowd movement in the shooting incident, we use an agent-based model to restore the real target case. Based on the optimal solution, we explore the effects of the number and location of building exits, the scale of the shooter's attack, and the time to find shelter on the shooting results. For building exits, we found that for the environment in the case, the exit location has little impact on the number of casualties, but the increase in the number of exits provides more evacuation routes for the crowd and reduces the number of casualties. Panic will increase the probability of collision and injury. Hiding in a refuge area away from the shooter is effective to avoid shooting injury. At the same time, we propose the critical point of hiding probability. When it is greater than 40%, the faster the escape speed is, the higher the safety is; escape is more likely to replace avoidance in hiding probability less than 40% of environments. These findings are helpful to guide the building evacuation channel construction and emergency evacuation training.
- 14 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 10 (3) , 994-1003
Agent-Based Model of Mass Campus Shooting: Comparing Hiding and Moving of Civilians
The follow-up impact of the campus shooting incident is enormous. Due to a large number of minors (vulnerable groups) and complex building environments, the school is one of the main targets of terrorists. The Sandy Hook Elementary School shooting in 2012 poses a challenge to social and public security. Considering the dichotomous characteristics of the people shot and the impact of the refuge area on the crowd movement in the shooting incident, we use an agent-based model to restore the real target case. Based on the optimal solution, we explore the effects of the number and location of building exits, the scale of the shooter's attack, and the time to find shelter on the shooting results. For building exits, we found that for the environment in the case, the exit location has little impact on the number of casualties, but the increase in the number of exits provides more evacuation routes for the crowd and reduces the number of casualties. Panic will increase the probability of collision and injury. Hiding in a refuge area away from the shooter is effective to avoid shooting injury. At the same time, we propose the critical point of hiding probability. When it is greater than 40%, the faster the escape speed is, the higher the safety is; escape is more likely to replace avoidance in hiding probability less than 40% of environments. These findings are helpful to guide the building evacuation channel construction and emergency evacuation training.