Jiyu Xin
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
Jiyu Xin has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
- Mitsuyoshi Akiyama
Department of Civil and Environmental Engineering, Waseda University
9 shared publications - Dan M. Frangopol
Department of Civil and Environmental Engineering, ATLSS Center, Lehigh University
7 shared publications Dan M. Frangopol
Lehigh University Bethlehem Pennsylvania USA
6 shared publicationsMitsuyoshi Akiyama
Waseda University Tokyo Japan
6 shared publications- Lianzhen Zhang
School of Transportation Science and Engineering, Harbin Institute of Technology, Harbin 150090, China
4 shared publications - Kaizhong Deng
School of Transportation Science and Engineering, Harbin Institute of Technology, Harbin 150090, China
3 shared publications
Latest Publications
- Open Access
- 5 February 2026
- Published by Elsevier in Engineering
Three-Dimensional Geometric Digital Twin of Cable-Stayed Bridges: UAV- and TLS-Based Point Cloud Registration, Fusion Modeling, and Damage Inspection
- 5 February 2026
- Published by Elsevier in Engineering
Open AccessThree-Dimensional Geometric Digital Twin of Cable-Stayed Bridges: UAV- and TLS-Based Point Cloud Registration, Fusion Modeling, and Damage Inspection
- 21 November 2025
- Published by Elsevier in Measurement
- Vol. 260
Anomaly discrimination via spatiotemporal correlation analysis of time-varying sensor systems under sparse traffic loads
- 21 November 2025
- Published by Elsevier in Measurement
- Vol. 260
Anomaly discrimination via spatiotemporal correlation analysis of time-varying sensor systems under sparse traffic loads
- Open Access
Advancements Toward a Standard System for Intelligent Operation and Maintenance of Buildings and Municipal Facilities
The building and municipal facility sectors in many countries are shifting from rapid construction to a balanced focus on construction and operation & maintenance (O&M). However, O&M practices remain largely manual, with poor digital integration, fragmented data management, and inconsistent performance standards. The absence of a unified theoretical and standardization framework for intelligent O&M represents a critical research and practice gap. To address this, this paper proposes a comprehensive framework for intelligent O&M standards, grounded in operations management theory and supported by extensive research. The framework is structured across three dimensions: (a) functional services, including perception, data fusion, decision-making, and disaster prevention; (b) system hierarchy, ranging from perception layer and algorithm layer to human–computer interaction layer; and (c) intelligence characteristics, spanning presentation and monitoring to autonomous maintenance. In addition, existing standards and representative applications are reviewed to provide valuable references for the future development of intelligent O&M standard systems.
Open AccessAdvancements Toward a Standard System for Intelligent Operation and Maintenance of Buildings and Municipal Facilities
The building and municipal facility sectors in many countries are shifting from rapid construction to a balanced focus on construction and operation & maintenance (O&M). However, O&M practices remain largely manual, with poor digital integration, fragmented data management, and inconsistent performance standards. The absence of a unified theoretical and standardization framework for intelligent O&M represents a critical research and practice gap. To address this, this paper proposes a comprehensive framework for intelligent O&M standards, grounded in operations management theory and supported by extensive research. The framework is structured across three dimensions: (a) functional services, including perception, data fusion, decision-making, and disaster prevention; (b) system hierarchy, ranging from perception layer and algorithm layer to human–computer interaction layer; and (c) intelligence characteristics, spanning presentation and monitoring to autonomous maintenance. In addition, existing standards and representative applications are reviewed to provide valuable references for the future development of intelligent O&M standard systems.
- 16 September 2025
- Published by Taylor & Francis in Structure and Infrastructure Engineering
- Vol. 22 (2) , 358-386
Life-cycle performance, design, maintenance, optimization, and decision-making of asphalt pavement under uncertainty: a review
- 16 September 2025
- Published by Taylor & Francis in Structure and Infrastructure Engineering
- Vol. 22 (2) , 358-386
Life-cycle performance, design, maintenance, optimization, and decision-making of asphalt pavement under uncertainty: a review
- 21 April 2025
- Published by SAGE Publications in Structural Health Monitoring
- Vol. 25 (5) , 2925-2943
TPS-GNN: Predictive model for bridge health monitoring data based on temporal periodicity and global spatial distribution characteristics
In recent years, the investigation of spatiotemporal dynamics in bridge health monitoring data has gained substantial prominence, with spatiotemporal models becoming a focal point of research in this domain. Traditional multilayer graph neural networks (GNNs) struggle to effectively distinguish the influence of sensor data from various cross-sectional positions on target nodes due to the oversmoothing issue when capturing spatial dependencies. Similarly, recurrent neural networks exhibit limitations in managing long-term dependencies and capturing periodic patterns, reducing their efficacy in applications like bridge monitoring, where an in-depth analysis of long-term trends is essential. To address these challenges, we introduce the concept of temporal periodicity and global spatial (TPS) and propose a predictive model named TPS-GNN. This model is specifically designed to leverage the temporal periodicity of data and the global spatial distribution characteristics. For spatial features, TPS-GNN directly employs representations from different hop neighborhoods, allowing it to accurately capture the spatial dependencies of sensor data across varying hop distances. This approach effectively retains node feature information and capitalizes on both local and global information, enhancing the model’s capacity to represent complex spatial relationships. Regarding temporal features, we introduce a position-encoding scheme that integrates daily, weekly, and seasonal periodic information into the flow data. The current and historical models process continuous and periodic time series data separately, thus better capturing temporal dependencies. Experimental results on two real-world bridge health monitoring datasets demonstrate that TPS-GNN significantly outperforms existing state-of-the-art predictive models, achieving up to a 78% improvement in prediction performance. This highlights the model’s ability to accurately predict bridge health monitoring data, enhancing the precision of data forecasts and providing reliable support for bridge maintenance and management.
- 21 April 2025
- Published by SAGE Publications in Structural Health Monitoring
- Vol. 25 (5) , 2925-2943
TPS-GNN: Predictive model for bridge health monitoring data based on temporal periodicity and global spatial distribution characteristics
In recent years, the investigation of spatiotemporal dynamics in bridge health monitoring data has gained substantial prominence, with spatiotemporal models becoming a focal point of research in this domain. Traditional multilayer graph neural networks (GNNs) struggle to effectively distinguish the influence of sensor data from various cross-sectional positions on target nodes due to the oversmoothing issue when capturing spatial dependencies. Similarly, recurrent neural networks exhibit limitations in managing long-term dependencies and capturing periodic patterns, reducing their efficacy in applications like bridge monitoring, where an in-depth analysis of long-term trends is essential. To address these challenges, we introduce the concept of temporal periodicity and global spatial (TPS) and propose a predictive model named TPS-GNN. This model is specifically designed to leverage the temporal periodicity of data and the global spatial distribution characteristics. For spatial features, TPS-GNN directly employs representations from different hop neighborhoods, allowing it to accurately capture the spatial dependencies of sensor data across varying hop distances. This approach effectively retains node feature information and capitalizes on both local and global information, enhancing the model’s capacity to represent complex spatial relationships. Regarding temporal features, we introduce a position-encoding scheme that integrates daily, weekly, and seasonal periodic information into the flow data. The current and historical models process continuous and periodic time series data separately, thus better capturing temporal dependencies. Experimental results on two real-world bridge health monitoring datasets demonstrate that TPS-GNN significantly outperforms existing state-of-the-art predictive models, achieving up to a 78% improvement in prediction performance. This highlights the model’s ability to accurately predict bridge health monitoring data, enhancing the precision of data forecasts and providing reliable support for bridge maintenance and management.
- Open Access
- 12 July 2024
- Published by Taylor & Francis
- p. 1916-1921
Connectivity analysis of transportation networks incorporating bridges and pavements under uncertainty
Currently, a comprehensive management system for transportation networks incorporating bridges and pavements is still missing. In this study, both bridges and asphalt pavements are considered critical components in the connection among all nodes in the network. A framework for estimating the probabilistic life-cycle connectivity of transportation networks is proposed. Specifically, flexural and shear failure modes are considered for bridges. Four failure modes, including international roughness index, rut depth, alligator cracking, and transverse cracking, are considered for asphalt pavement using a neural network-based deep learning (DL) model trained by the Long-Term Pavement Performance (LTPP) database. In the case study of an existing transportation network located in Chester, Pennsylvania, the matrix-based system reliability method is applied to investigate the life-cycle connectivity and component importance based on the obtained reliability associated with individual bridges and asphalt pavement segments. The results show that both bridges and asphalt pavements make a significant contribution to the probability of network connectivity.
- 12 July 2024
- Published by Taylor & Francis
- p. 1916-1921
Open AccessConnectivity analysis of transportation networks incorporating bridges and pavements under uncertainty
Currently, a comprehensive management system for transportation networks incorporating bridges and pavements is still missing. In this study, both bridges and asphalt pavements are considered critical components in the connection among all nodes in the network. A framework for estimating the probabilistic life-cycle connectivity of transportation networks is proposed. Specifically, flexural and shear failure modes are considered for bridges. Four failure modes, including international roughness index, rut depth, alligator cracking, and transverse cracking, are considered for asphalt pavement using a neural network-based deep learning (DL) model trained by the Long-Term Pavement Performance (LTPP) database. In the case study of an existing transportation network located in Chester, Pennsylvania, the matrix-based system reliability method is applied to investigate the life-cycle connectivity and component importance based on the obtained reliability associated with individual bridges and asphalt pavement segments. The results show that both bridges and asphalt pavements make a significant contribution to the probability of network connectivity.
- 1 September 2023
- Published by American Society of Civil Engineers (ASCE) in Journal of Bridge Engineering
- Vol. 28 (9)
Probabilistic Life-Cycle Connectivity Assessment of Transportation Networks Using Deep Learning
- 1 September 2023
- Published by American Society of Civil Engineers (ASCE) in Journal of Bridge Engineering
- Vol. 28 (9)
Probabilistic Life-Cycle Connectivity Assessment of Transportation Networks Using Deep Learning