Xinyi Zhou

Dr. Xinyi Zhou

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 November 2025 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
XZXinyi Zhou
Xinyi Zhou
SSSiyu Sun
Siyu Sun
Nizar BouguilaNizar Bouguila
Nizar Bouguila
ZPZachary Patterson
Zachary Patterson
Short-term passenger flow prediction is critical for intelligent scheduling and efficient operation of public transportation systems. However, existing methods often struggle to maintain robustness and generalizability when facing complex and heterogeneous noise sources, such as passenger flow noise including sensor-induced missing values and abrupt ridership fluctuations caused by unexpected events, and graph structural noise resulting from dynamic changes in the network topology due to route modifications or stop closures. To address these challenges, this paper proposes a novel deep learning framework: Robust Dynamic Graph Neural Networks (RDGNN), that integrates noise cleaning, dynamic graph modeling, and more efficient prediction. The proposed noise cleaning employs K-Nearest Neighbor imputation and Gaussian Mixture Models with a penalty function to mitigate data-level noise, while a graph structure denoising module is introduced to correct topological anomalies in the transit network and enhance the reliability of spatial representation. For feature modeling, the framework constructs a dynamic graph neural network from a subgraph perspective to capture both spatial dependencies and temporal dynamics, particularly suited to modeling interactions among transfer stations. A Liquid Neural Network is adopted as the prediction module, leveraging its strong adaptability and memory capacity to handle irregular and non-stationary time series, while remaining computationally efficient. The RDGNN model was trained and validated on real-world bus passenger flow data from Ames, Iowa, and further evaluated on the large-scale EXO dataset. Compared to state-of-the-art models, RDGNN consistently achieves better prediction accuracy, higher robustness to noise and missing data, and greater computational efficiency. Its strong and stable performance across both datasets, including in scenarios such as route disruptions and seasonal variation, demonstrates excellent generalization capability in diverse urban transit systems. The code is available at: https://github.com/XinyiZhou0318/A-Noise-Robust-Approach-Using-Dynamic-Graph-Neural-Networks-for-Bus-Passenger-Flow-Prediction

25 September 2023 in Sensors
Verified
Journal Article
Open access
PDF file
MLMAN LI
MAN LI
XZXinyi Zhou
Xinyi Zhou
SQSiyao Qin
Siyao Qin
ZBZiyan Bin
Ziyan Bin
YWYanhui Wang
Yanhui Wang
The traction system is very important to ensure the safe operation of high-speed trains, and the failure of the traction transformer is the most likely fault in the traction system. Fault diagnosis in actual work relies largely on manual experience. This paper proposes an improved RAkEL (Random k-Labelsets) algorithm for the fault diagnosis of high-speed train traction transformers. Firstly, this article starts from the large amount of “sleeping” fault maintenance data accumulated by the railway department, takes a single maintenance record as an instance, uses specific monitoring values to construct an instance vector, and uses the fault phenomena corresponding to the monitoring indicators as labels. Then, this paper improves the step of selecting k-labelsets in RAkEL, and extracts associated faults using the Relief algorithm. Finally, this paper excavates and uses the association rules between data and faults to identify traction transformer faults. The results showed that the improved RAkEL diagnostic method had a significant improvement in the evaluation indicators. Compared with other multi-label classification algorithms, including BR (Binary Relevance) and CLR (Calibrated Label Ranking), this method performs well on multiple evaluation indicators. It can further help engineers perform timely maintenance work in the future.

30 March 2026 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
XZXinyi Zhou
Xinyi Zhou
Nizar BouguilaNizar Bouguila
Nizar Bouguila
ZPZachary Patterson
Zachary Patterson
Bus passenger flow prediction is a crucial task in bus transportation management and optimization, characterized by strong spatiotemporal dependencies and influenced by external factors such as weather and holidays. However, existing methods face challenges in responding to sudden events, modeling dynamic changes in bus network topology, and improving model generalization. To address these issues, this paper proposes a graph transfer learning-based approach for bus passenger flow prediction. First, a dynamic graph neural network is used to construct the passenger flow network, and Framelet Transform along with Self-Expressiveness Regularization is applied for denoising, enhancing data quality. Second, an adaptive neighborhood-aware dynamic graph convolutional network is introduced, integrating random mask enhancement, hop count perception fusion, and multi-channel spatiotemporal feature extraction for accurate passenger flow modeling. Furthermore, a combination of source data and source free transfer learning is leveraged to optimize feature distribution alignment through pseudo-label generation, graph diffusion, and consistency loss. Finally, a GRU is used for passenger flow prediction, and extensive experiments on real-world datasets test the proposed method. Results demonstrate superior accuracy and generalization performance compared to existing state of the art (SOTA) models.

22 January 2026 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
ABAsiye Baghbani
Asiye Baghbani
XZXinyi Zhou
Xinyi Zhou
Nizar BouguilaNizar Bouguila
Nizar Bouguila
ZPZachary Patterson
Zachary Patterson
Accurate passenger flow prediction helps public transportation authorities optimize routes, reduce delays, and enhance travel experiences. Recently, Spatial-Temporal Graph Neural Networks (ST-GNNs) have emerged as powerful tools for predicting passenger flows in public transportation. While ST-GNNs can offer valuable insights, they usually assume a static network structure that may not fully consider the real-world dynamics of public transportation systems. With the increasing accessibility of real-time bus schedule data, passengers are adjusting their arrival times at stops according to the latest bus schedules, significantly impacting passenger flow patterns. To address these dynamics, it is critical to incorporate real-time data into ST-GNNs, making these models more dynamic and flexible in terms of both nodes and edges. This adjustment allows the models to better align with actual bus schedules. Current ST-GNN models primarily focus on the temporal evolution of edges, often overlooking the changing status of the nodes. This study introduces a novel dynamic spatial-temporal graph neural network framework, the first to account for the dynamic nature of nodes, providing a more comprehensive approach to predicting passenger flow in bus networks. In this framework, which is entitled Spatial-Temporal Attention Masked Graph Encoder-Decoder, through analysis of active stops - those where buses are scheduled to arrive based on the bus schedule - a more realistic representation of a network’s spatial and temporal dynamics will be captured. The proposed model was evaluated on two real-world transit networks—Laval, Canada, and Ames, USA—and consistently outperformed both classical and recent state-of-the-art baselines across multiple forecasting horizons.

4 August 2026 in Sustainable Cities and Society
Verified
Journal Article
Closed access
XZXinyi Zhou
Xinyi Zhou
Nizar BouguilaNizar Bouguila
Nizar Bouguila
ZPZachary Patterson
Zachary Patterson