ZXZhuye Xu

Zhuye Xu

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

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


Zhuye Xu has a total of 22 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Study on Urban Traffic Speed Prediction Using Spatiotemporal Attention-Based Convolutional Neural Networks

    by Zhuye Xu, Shaoyang Wang, Hongqiang Xin, Zhongdong Hua

    Urban traffic speed prediction requires effective modeling of road-network spatial dependencies and temporal dynamics. This study develops an attention-based spatiotemporal graph convolutional framework (AT-GCN-GRU) for multi-horizon traffic speed prediction. The model combines graph convolution for spatial feature extraction, GRU for temporal modeling, and a temporal attention mechanism for adaptively weighting historical hidden states. Experiments were conducted on the SZ-taxi dataset and further evaluated on METR-LA. On SZ-taxi, AT-GCN-GRU was compared with conventional and modern baselines, including T-GCN, ASTGCN, and AGCRN, over 15, 30, 45, and 60 min forecasting horizons. The proposed model remained competitive with the modern baselines and obtained lower mean RMSE than T-GCN across the four evaluated horizons, with relative reductions of approximately 1.4–2.9%. Additional ablation, missing-data robustness, attention-weight visualization, and computational-cost analyses were conducted. The results suggest that temporal attention can provide incremental improvements to the GCN-GRU framework with relatively limited additional computational overhead.

  • Open Access

    Research on Medical Image Super-Resolution Reconstruction Algorithm Based on Dilated Convolution and Multi-Module Fusion

    by Zhuye Xu, Yucong Guo

    Medical image resolution plays a crucial role in early disease detection and fine-structure observation. Super-resolution reconstruction technology can restore low-resolution images to high-resolution versions, thereby assisting physicians in making accurate diagnoses. To address challenges in medical image super-resolution reconstruction, including insufficient global information acquisition, excessive network complexity, and suboptimal loss function adaptation for medical imaging data, this paper proposes an image super-resolution reconstruction algorithm named IDCASR-MMF based on improved dilated convolution and multi-module fusion. First, multi-dilation-rate dilated convolution is introduced to expand the receptive field and integrated with a spatial attention mechanism to dynamically calibrate high-frequency features after feature extraction. Subsequently, the Squeeze-and-Excitation module is fused with dilated convolution as a channel attention mechanism to streamline the network architecture. Finally, a weighted fusion strategy combining adversarial loss and MSE loss is adopted, where the dynamic adjustment of weighting coefficients balances pixel-level structural accuracy and high-frequency detail authenticity, achieving synergistic optimization of objective precision and subjective quality for medical images. To validate the effectiveness of the proposed algorithm, IDCASR-MMF is compared with 11 state-of-the-art methods across five datasets (Set5, Set14, BSD100, Urban100, and Bone FD). Experimental results demonstrate that the proposed algorithm achieves superior PSNR and SSIM values on multiple datasets, confirming that IDCASR-MMF can effectively reconstruct high-resolution medical images from low-resolution inputs.

  • Open Access

    A Multimodal Dense Parallel Global Attention Mechanism for Brain Tumor Image Segmentation

    by Zhuye Xu, Ru Qiao

    Brain tumor segmentation from 3D MRI presents significant challenges due to small lesion sizes, ambiguous boundaries, arbitrary spatial distributions, and heterogeneous morphological properties. To tackle these issues, this paper presents a fully automatic 3D brain tumor segmentation network that integrates morphological and anatomical information under a multi-task learning framework for whole tumor, tumor core, and enhanced tumor segmentation. We propose a multimodal feature fusion module to adaptively weight features from four MRI modalities (T1, T1ce, T2, FLAIR), enabling discriminative information integration and helping reduce modality intensity discrepancy and data imbalance. Furthermore, a ConvReXt downsampling module is introduced to preserve fine-grained semantic details by reducing information loss caused by conventional pooling. A dense parallel global attention module is also developed to capture both local details and long-range dependencies, addressing the limited receptive field of standard convolutions. Extensive experiments on the BraTS2020 dataset show that the proposed model obtains average Dice coefficients of 92.54%, 89.21%, and 86.54% for whole tumors, tumor cores, and enhanced tumors. The proposed model achieves competitive performance compared with state-of-the-art methods including nnFormer, validating that it can effectively fuse multimodal and multi-scale features and improve brain tumor segmentation accuracy.

  • Open Access

    Multi-Object Tracking Algorithm for Unmanned Vehicle Autonomous Driving Scene Based on Online Spatiotemporal Feature Correlation

    by Haijun Li, Zhuye Xu, Changxi Ma, Xiao Tang

    Aiming at the problem that the multi-object tracking algorithm is difficult to accurately design the object feature model and data association algorithm in the process of unmanned vehicle autonomous driving, a multi-object tracking algorithm based on online spatiotemporal feature correlation for unmanned vehicle autonomous driving scene (MOTA-BOSFCFUVADS) is proposed. Firstly, the algorithm performs object detection on the training samples, calibrates the coordinates of the detection results in the time dimension and the coordinates of the space dimension, eliminates the detection results whose confidence is less than the set value, and eliminates the overlapping boundaries in the detection through non-maximum suppression. Secondly, we use Kalman filter to predict the position of the tracking object in the current frame, then build the feature model of the object in the time dimension and the space dimension respectively, and fuse the temporal feature model of the tracking object with the spatial feature model, thereby, the spatiotemporal feature model of the tracking object is obtained. Finally, the spatiotemporal feature response of the object in the current frame is detected online, and the spatiotemporal feature response is correlated with the spatiotemporal object feature model of the tracking object, and then the similarity metric matching matrix obtained by fusion is calculated, and the tracking is solved by using the Hungarian algorithm. The optimal correlation pair between the object historical trajectory and the detection response, and update the parameters of the object spatiotemporal feature model. In addition, we use the MOT2015 database to test the effectiveness of the algorithm. The results show that the proposed algorithm has better tracking performance than the other two algorithms, and can effectively track multiple object continuously in time and space.


  • Open Access

    Cooperative Lane-Change Control Method for Freeways Considering Dynamic Intelligent Connected Dedicated Lanes

    by Jian Xiang, Zhengwu Wang, Qi Mi, Qiang Wen, Zhuye Xu

    Connected Autonomous Vehicle (CAV) dedicated lanes can spatially eliminate the disturbance from Human-Driven Vehicles (HDVs) and increase the probability of vehicle cooperative platooning, thereby enhancing road capacity. However, when the penetration rate of CAVs is low, CAV dedicated lanes may lead to a waste of road resources. This paper proposes a cooperative lane-changing control method for multiple vehicles considering Dynamic Intelligent Connected (DIC) dedicated lanes. Initially, inspired by the study of dedicated bus lanes, the paper elucidates the traffic regulations for DIC dedicated lanes, and two decision-making approaches are presented based on the type of lane-change vehicle and the target lane: CAV autonomous cooperative lane change and HDV mandatory cooperative lane change. Subsequently, considering constraints such as acceleration, speed, and safe headway, cooperative lane-change control models are proposed with the goal of minimizing the weighted sum of vehicle acceleration and lane-change duration. The proposed model is solved by the TOPSIS multi-objective optimization algorithm. Finally, the effectiveness and advancement of the proposed cooperative lane-changing method are validated through simulation using the SUMO software (Version 1.19.0). Simulation results demonstrate that compared to traditional lane-changing models, the autonomous cooperative lane-changing model for CAVs significantly improves the success rate of lane changing, reduces lane-changing time, and causes less speed disturbance to surrounding vehicles. The mandatory cooperative lane-changing model for HDVs results in shorter travel times and higher lane-changing success rates, especially under high traffic demand. The methods presented in this paper can notably enhance the lane-changing success rate and traffic efficiency while ensuring lane-changing safety.


  • Open Access

    Research on Parking Space Detection and Prediction Model Based on CNN-LSTM

    by Zhuye Xu, Xiao Tang, Changxi Ma, Renshuai Zhang

    With the continuous acceleration of urbanization, the parking problem is becoming increasingly serious. How to better manage parking resources has become an urgent problem to be solved in urban development. In this context, according to the historical data and real-time video data collected by the parking camera, this paper proposes an algorithm for parking space detection and state recognition. Through image preprocessing, region of interest selection, Hough line detection, and parking information recognition of the input test image, an intelligent parking space detection model is constructed, which improves the utilization rate of parking space and reduces the management cost. On this basis, according to the free parking space data obtained by the detection algorithm, a short-term demand prediction algorithm for on-road parking based on Convolutional Neural Network (CNN) and Long Short-Term Memory Neural Network (LSTM) was proposed. Through the preprocessing of input parking space data, time vector transformation, data separation, model training, and prediction, the parking demand data is predicted and analyzed. By comparing the prediction results of multiple models, it was found that the CNN-LSTM prediction model had the best model stability and goodness of fit, the lowest Mean Error (MAE) and Root Mean Square Error (RMSE), the errors of working days were 13.301 and 21.156, and the errors of rest days were 12.573 and 20.739, respectively. It shows that CNN-LSTM can effectively capture the time and spatial feature information of parking lot free parking space data, and the prediction accuracy is good, which can be used to predict the number of free parking spaces in parking lots.


  • Open Access

    A Statistical Shape-Based Patient-Specific Anatomical Structure Model

    by Zhuye Xu, Xiaoqiang Zhao

    A patient-specific anatomical structure model has been widely used in many medical applications. However, in practical applications, to effectively construct a patient-specific anatomical structure model is a challenge, the reasons are: (1) the manual marking process for landmark points is time-consuming and is prone to have false points; (2) the correspondence establishment is difficult; (3) the performance of the model is limited. Therefore, the purpose of this study is to automatically construct a patient-specific anatomical structure model to solve these difficulties. Firstly, the input data are preprocessed to enhance the region of interest in CT scan images. Then, the region of interest is regarded as a training specimen, and the triangle is used to mesh the training specimen. Meanwhile, vertices contraction strategy is introduced to iteratively contract triangle meshes, and the correspondences are established through improved B-spline free-form deformation. Finally, principal component analysis is used to generate the final patient-specific anatomical structure model. Experimental results on 30 pelvic CT scan images verify that the proposed method outperforms the compared methods.