ZZZhengyu Zhang

Zhengyu Zhang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Zhengyu Zhang has a total of 45 co-authors. Here are the top co-authors by number of shared publications:

  • Ruisi He

    Beijing Jiaotong University

    16 shared publications
  • Bo Ai

    Beijing Jiaotong University

    15 shared publications
  • Mi Yang

    Beijing Jiaotong University

    15 shared publications
  • Xuejian Zhang

    State Key Laboratory of Advanced Rail Autonomous Operation, the School of Electronics and Information Engineering, and the Frontiers Science Center for Smart High-speed Railway System, Beijing Jiaotong University, Beijing, China

    11 shared publications
  • Ziyi Qi

    State Key Laboratory of Advanced Rail Autonomous Operation, the School of Electronics and Information Engineering, and the Frontiers Science Center for Smart High-speed Railway System, Beijing Jiaotong University, Beijing, China

    9 shared publications
  • Zhangdui Zhong

    State Key Laboratory of Advanced Rail Autonomous Operation, the School of Electronics and Information Engineering, and the Frontiers Science Center for Smart High-speed Railway System, Beijing Jiaotong University, Beijing, China

    7 shared publications

Latest Publications

  • Delay-Doppler Domain Channel Measurements and Modeling in High-Speed Railways

    by Hao Zhou, Yiyan Ma, Dan Fei, Weirong Liu, Zhengyu Zhang, Mi Yang, Guoyu Ma, Yunlong Lu, Ruisi He, Guoyu Wang, et al.

    As next-generation wireless communication systems need to be able to operate in high-frequency bands and high-mobility scenarios, delay-Doppler (DD) domain multicarrier (DDMC) modulation schemes, such as orthogonal time frequency space (OTFS), demonstrate superior reliability over orthogonal frequency division multiplexing (OFDM). Accurate DD domain channel modeling is essential for DDMC system design. However, since traditional channel modeling approaches are mainly confined to time, frequency, and space domains, the principles of DD domain channel modeling remain poorly studied. To address this issue, we propose a systematic DD domain channel measurement and modeling methodology in high-speed railway (HSR) scenarios. First, we design a DD domain channel measurement method based on the long-term evolution for railway (LTE-R) system. Second, for DD domain channel modeling, we investigate quasi-stationary interval, statistical power modeling of multipath components, and particularly, the quasi-invariant intervals of DD domain channel fading coefficients. Third, via LTE-R measurements at 371 km/h, taking the quasi-stationary interval as the decision criterion, we establish DD domain channel models under different channel time-varying conditions in HSR scenarios. Fourth, the accuracy of proposed DD domain channel models is validated via bit error rate comparison of OTFS transmission. In addition, simulation verifies that in HSR scenario, the quasi-invariant interval of DD domain channel fading coefficient is on millisecond (ms) order of magnitude, which is much smaller than the quasi-stationary interval length on 100 ms order of magnitude. This study could provide theoretical guidance for DD domain modeling in high-mobility environments, supporting future DDMC and integrated sensing and communication designs for 6G and beyond.


  • Deep Learning-Based Dynamic Environment Reconstruction for Vehicular ISAC Scenarios

    by Junzhe Song, Ruisi He, Mi Yang, Zhengyu Zhang, Bingcheng Liu, Jiahui Han, Haoxiang Zhang, Bo Ai

    Integrated Sensing and Communication (ISAC) technology plays a critical role in future intelligent transportation systems, by enabling vehicles to perceive and reconstruct the surrounding environment through reuse of wireless signals, thereby reducing or even eliminating the need for additional sensors such as LiDAR or radar. However, existing ISAC-based reconstruction methods often lack the ability to track dynamic scenes with sufficient accuracy and temporal consistency, limiting the real-world applicability. To address this limitation, we propose a deep learning based framework for vehicular environment reconstruction by using ISAC channels. We first establish a joint channel–environment dataset based on multi-modal measurements from real-world urban street scenarios. Then, a multi-stage deep learning network is developed to reconstruct the environment. Specifically, a scene decoder identifies the environmental semantic context such as buildings, trees, and so on; a semantic center decoder predicts coarse spatial layouts by localizing dominant object centers; a point cloud decoder recovers fine-grained geometry and structure of surrounding environments. Experimental results demonstrate that the proposed method achieves high-quality global reconstruction of dynamic environments, with a Chamfer Distance of 0.29 and F-score@0.5m of 0.87. In addition, complexity analysis demonstrates the efficiency and practical applicability of the method in real-time scenarios. This work provides a pathway toward low-cost environment reconstruction based on ISAC for future intelligent transportation.


  • Top Cited Papers

    Channel Semantic Characterization for Integrated Sensing and Communication Scenarios: From Measurements to Modeling

    by Zhengyu Zhang, Ruisi He, Bo Ai, Mi Yang, Xuejian Zhang, Ziyi Qi, Zhangdui Zhong

    As a novel technology in the sixth-generation (6G) wireless communication systems, integrated sensing and communication (ISAC) enables intelligent agents to perceive, predict, and interact with the environment. It is crucial for ISAC to acquire environmental information based on electromagnetic propagation, referred to as channel semantics, to facilitate tasks such as decision-making and beamforming. However, channel models that focus on physical characteristics face challenges in representing the semantics embedded in the channel, thereby limiting the performance evaluation of ISAC systems. To tackle this, we present a novel unified framework for channel modeling from the conceptual event perspective. By leveraging a multi-level semantic structure and characterized knowledge libraries, the framework decomposes complex channel characteristics into composable and extensible high-level semantic characterization, thereby better capturing the relationship between the environment and channel, and enabling more flexible adjustments of channel models for different events without requiring a complete reset. Specifically, we define channel semantics from three levels: status semantics, behavior semantics, and event semantics, corresponding to channel transient multipaths, channel time-varying trajectories, and channel topology, respectively. Taking a realistic vehicular ISAC scenario as an example, we perform semantic clustering through depth estimation and semantic segmentation of environmental images, and further characterize the channel status semantics by fitting multipath statistical distributions; behavior semantics are modeled using Markov chains to capture time-varying characteristics; event semantics are characterized by employing a co-occurrence matrix. The results indicate that the proposed model can generate accurate channels whereas representing rich semantic information. Additionally, generalization of the model for customized semantics is demonstrated.


  • Cluster-Based Time-Variant Channel Characterization and Modeling for 5G-Railways

    by Xuejian Zhang, Ruisi He, Bo Ai, Mi Yang, Jianwen Ding, Shuaiqi Gao, Ziyi Qi, Zhengyu Zhang, Zhangdui Zhong

    With the rapid development of high-speed railways, 5G for Railways (5G-R) is gradually replacing the legacy Global System for the Mobile Communications for Railway (GSM-R) system to meet growing communication demands. However, the large bandwidth, use of array antennas, and pronounced non-stationarity caused by high mobility make 5G-R channel modeling significantly more complex. Accurate and realistic channel models are therefore essential to support reliable system design. Despite this need, there is a scarcity of time-variant channel models specifically tailored to 5G-R frequency bands and scenarios, particularly those that adopt a cluster-based framework. This paper proposes a cluster-based time-variant channel model for 5G-R, extending the 3GPP framework by incorporating temporal evolution and dynamic multipath behavior. The model is constructed from comprehensive real-world measurements on a 5G-R private network. Key propagation features including path loss, Rice K-factor, delay and angular spreads are statistically characterized, with the Kolmogorov–Smirnov test validating their goodness of fit. Clustering analysis shows 1 to 6 multipath clusters per stationarity region, and their birth-death dynamics are effectively modeled using a first-order four-state Markov chain. Compared to the standard 3GPP CDL model, the proposed 5G-R CDL model exhibits longer delays, more balanced cluster power distribution, and wider angular spreads, better reflecting the unique features of the railway propagation environment. Moreover, validation with cluster dynamic parameters confirms that the birth–death model accurately captures cluster evolution, supporting the Markov process assumption. Link-level simulations further demonstrate that the proposed model more accurately captures real-world variations in bit error rate and signal quality than existing 3GPP models. The proposed model enhances realism and adaptability for link-level simulations, network planning, and physical layer algorithm design in high-speed railway scenarios, providing a solid foundation for future 5G-R channel standardization.


  • Integrated Sensing, Communication, Computing, and Control Meets UAV Swarms in 6G

    by Yiyan Ma, Bo Ai, Jingli Li, Weijie Yuan, Boxiang He, Weiyang Feng, Zhengyu Zhang, Qingqing Cheng, Zhangdui Zhong

  • A Novel Structure-Aware Multipath Clustering and Tracking Algorithm for Dynamic Communication Channels

    by Shuaiqi Gao, Mi Yang, Bo Ai, Jingjing Yu, Yi Gong, Ruisi He, Zhengyu Zhang, Junzhe Song

    Extensive channel measurement campaigns have shown that multipath components (MPCs) generally exhibit clustered distributions, making cluster-based models a cornerstone of wireless channel modeling. Developing time-varying cluster-based channel models requires not only clustering MPCs in the delay, angle, and power domains, but also tracking their temporal evolution. However, existing multipath clustering algorithms typically rely on fixed hyperparameters and therefore are often poorly suited to dynamically evolving clusters, while tracking algorithms based solely on distance metrics are prone to ambiguous associations among spatially proximate clusters. Moreover, treating clustering and tracking as separate processes often prevents temporal evolution information from being fully exploited during clustering. This paper proposes a structure-aware unified framework that integrates Adaptive Neighborhood Robust Mean Shift (AN-RMS) clustering with BoxKF-Cluster tracking. Within the proposed framework, AN-RMS, built upon kernel density estimation, adaptively determines the effective number of nearest neighbors K by detecting abrupt changes in the second-order gradient of the neighborhood-distance sequence, thereby identifying structural cluster boundaries and providing locally adaptive guidance for density-mode iteration. BoxKF-Cluster introduces oriented bounding boxes derived from root-mean-square statistics to characterize the evolving morphology of clusters, and combines Kalman filtering with a successive-interference-cancellation (SIC)-like strategy, in which the influence of existing clusters is first removed to facilitate the detection of newly emerging ones. As a result, clustering and tracking are jointly accomplished within a unified framework. The proposed method is validated in complex scattering scenarios using both ray-tracing simulations and real vehicle-to-vehicle millimeter-wave measurement data, demonstrating its effectiveness for time-varying channel modeling.

  • Vision-Aided Channel Prediction Based on Image Segmentation at Street Intersection Scenarios

    by Xuejian Zhang, Ruisi He, Mi Yang, Ziyi Qi, Zhengyu Zhang, Bo Ai, Zhangdui Zhong

    Intelligent vehicular communication with vehicle-road collaboration capability is a key technology enabled by 6G, and the integration of various visual sensors on vehicles and infrastructures plays a crucial role. Moreover, accurate channel prediction is foundational to realizing intelligent vehicular communication. Traditional methods are still limited by the inability to balance accuracy and complexity based on substantial spectrum resource consumption and highly refined description of environment. In this paper, we propose a vision-aided channel prediction model that leverages out-of-band visual information for precise prediction of typical channel characteristics, including path loss, Rice K-factor, and delay spread. We first conduct extensive vehicle-to-infrastructure measurements at urban intersections, collecting synchronized channel and visual data. After post-processing and filtering, segmented images of the target vehicle are generated using YOLOv8 network to construct an image-channel dataset. These segmented images are then used as inputs to a ResNet-34 model for supervised learning. Finally, four experiments are designed to evaluate the model, which are scenario self-validation, cross-validation, generalization to varying vehicle appearances, and performance under different segmentation and prediction networks. Experimental results confirm that our model, trained with instance-segmented images, achieves high prediction accuracy and strong generalization across scenarios and target users. The proposed approach offers a promising and practical solution for intelligent channel prediction in future vehicular communication systems.


  • Vision Aided Channel Prediction for Vehicular Communications: A Case Study of Received Power Prediction Using RGB Images

    by Xuejian Zhang, Ruisi He, Mi Yang, Zhengyu Zhang, Ziyi Qi, Bo Ai

    The communication scenarios and channel characteristics of 6G will be more complex and difficult to characterize. Conventional methods for channel prediction face challenges in achieving an optimal balance between accuracy, practicality, and generalizability. Additionally, they often fail to effectively leverage environmental features. Within the framework of integration communication and artificial intelligence as a pivotal development vision for 6G, it is imperative to achieve intelligent prediction of channel characteristics. Vision-aided methods have been employed in various wireless communication tasks, excluding channel prediction, and have demonstrated enhanced efficiency and performance. In this paper, we propose a visionaided two-stage model for channel prediction in millimeter wave vehicular communication scenarios, specifically realizing accurate received power prediction utilizing solely RGB images. First, we acquire the original image and channel data (mainly received power) of the propagation environment via RGB cameras and channel measurements. In stage 1, redundant data is filtered and synchronized to yield one-to-one channel-image data pairs. The image data is then fed into YOLOv8 network, which extracts key vehicle features—such as size, shape, and location—using three typical computer vision methods (including object detection, instance segmentation and binary mask). These processed images are input into the ResNets for training and testing in stage 2, with the received power serving as the label and expected output. Finally, we conduct five experiments to evaluate the performance of proposed model, demonstrating its feasibility, accuracy and generalization capabilities. The model proposed in this paper offers novel solutions for achieving intelligent channel prediction in vehicular communications.