Sudao HE

Sudao HE

Hong Kong University of Science and Technology

I am currently a Postdoctoral Fellow in the Department of Civil and Environmental Engineering at The Hong Kong University of Science and Technology . I am fortunate to work with Prof. Shenghan ZHANG since Sept. 2023.

I received my Ph.D. in Automation Engineering at Nanjing University of Aeronautics and Astronautics (NUAA), where I was fortunate to join the Fault Detection and Diagnostics Group led by Prof Bin JIANG (advised by Prof. Fuyang CHEN). During 2023, I was also a Postdoctral Research Associate at The Hong Kong Polytechnic University and National Rail Transit Electrification and Automation Engineering Technology Research Center (Hong Kong Branch), working with Prof. Yi-Qing NI. Prior to this, I obtained my bachelor’s degree from NUAA.

I have a broad research interest in leveraging data-efficient learning for advanced Structural Sensing, Inspection, and Monitoring, with an ultimate goal to develop Generalized Digital Twin Paradigms for mechanical and thermodynamic systems. My topics include Visual Measurement, Multi-modal Learning, Domain Adaptation / Generalization, Zero-shot / Few-shot Learning, Data Stream Mining, Incremental Learning, Label-noise Learning and Federated Learning.

I have published several papers at the top journals such as IEEE Transactions on Neural Networks and Learning Systems, Reliability Engineering & System Safety and IEEE Transactions on Instrumentation and Measurement.

If you are seeking any form of academic cooperation, please feel free to email me at sudao.he@ust.hk.

🔥 News

  • 2025.06: 🎊 Prof Shenghan Zhang presented our recent work UHGAN for bottom-up structure-level damage assessment on ICOSSAR’25.
  • 2025.06: 🎊 I present my recent work DMPN for trustworthy structural damage assessment by fusing heterogeneous data on ICOSSAR’25.
  • 2025.03: 🎉 Physical-Constrained FiberNet on strain distributions interpretation, collaborated with Xuanyi Lu and Shenghan Zhang, has been published in Automation in Construction.
  • 2025.02: 🎉 One work collaborated with Tongji University on steel fatigue cracks detection using geometric computer vision technology has been published in Structural Control and Health Monitoring.
  • 2025.01: 😁 I have been honored with the title of Outstanding Reviewer for IEEE TIM.
  • 2024.12: 🎉 Weakly-aligned Cross-modal Learning Framework for subsurface defect segmentation on building façades has been accepted for publication in Automation in Construction.
  • 2024.09: 📖 I am honored to give a guest lecture again on Machine Learning in Structural Sensing and Health Monitoring.
  • 2024.06: 😁 I will exhibit my work with Prof. Zhang, Dr. Mishra and Prof. Yuen on subsurface defect segmentation in EWSHM 2024.
  • 2024.06: 🎊 I will serve as Associate Editor for IEEE Transactions on Instrumentation and Measurement.
  • 2024.02: 🎉 My paper collaborated with Dr. AO Wai Kei and Prof. NI Yi-Qing has been accepted for publication in IEEE TIM.
  • 2023.09: 📖 I give a guest lecture on Machine Learning in Structural Sensing and Health Monitoring.
  • 2023.09: 🚀 I join the group of Prof. Shenghan ZHANG at The Hong Kong University of Science and Technology.

📝 Selected Research Papers

🔶 ML with Incomplete Data

IEEE TNNLS
sym

Sudao He, Fuyang Chen, Hongtian Chen. A latent representation generalizing network for domain generalization in cross-scenario monitoring, IEEE Transactions on Neural Networks and Learning Systems. (JCR Q1, IF: 10.4) (cite)

  • LRGN: A framework for Cross-scenario Monitoring without data of concerned events (such as faults, defect and physical intrusion) in a new scenario.
  • Academic Impact: Efficient domain generalization with agnostic embedding space by estimating domain shifts of vibration signals by a sequential- variational generative adversarial network.
  • Industry Impact: Verification based on real-field data from distributed optical fiber sensors in Jinliwen line and Nanjing Metro Line S7.
IEEE TIM
sym

Sudao He, Fuyang Chen, Ning Xu, Hongtian Chen. Online monitoring for non-stationary operation via a collaborative neural network. IEEE Transactions on Instrumentation and Measurement, vol. 71, pp. 1-12, 2022. (JCR Q1, IF: 5.6)(cite)

  • CoNN: A Collaborative Neural Network for non-stationary operation monitoring through online adaptation with theoretical guaranteed convergence.
  • Academic Impact: Concept-sharing feature layers for adaptation to prior knowledge changes and concept-exclusive classification layers to learn concept-specific posterior knowledge.
  • Industry Impact: CoNN is verified based on actual data from Nanjing Metro Line S7.
Neurocomputing
sym

Sudao He, Fuyang Chen, Bin Jiang. Physical intrusion monitoring via local-global network and deep isolation forest based on heterogeneous signals. Neurocomputing, vol. 441, pp. 25-35, 2021 (JCR Q2, IF: 6)(cite)

  • We propose a local–global semi-sharing network for heterogeneous signals in physical intrusion monitoring
  • Academic Impact: A deep isolation forest is developed to learn from high-dimensional and extremely-imbalanced data.
  • Industry Impact: An F1 score of 0.780 under a class ratio of 83.3 is achieved based on real-field data from Nanjing Metro Line S7.

🚩 ML with Unreliable Data

IEEE TIM
sym

Sudao He, Wai Kei Ao, Yi-Qing Ni. A Unified Label Noise-Tolerant Framework of Deep Learning-based Fault Diagnosis via A Bounded Neural Network, IEEE Transactions on Instrumentation and Measurement, 2024. (JCR Q1, IF: 5.6)(code)

  • A unified framework for label-noise fault diagnosis of mechanical system.
  • Academic Impact: Theoretical guarantee and enhancement of label noise tolerance.
  • Industry Impact:
    • Applicable to different deep learning models.
    • Implementation of multiple variants and SOTA methods.
    • Real-field tests on automatic train control antenna beam of high-speed train.
IEEE Sensors Journal
sym

Fuyang Chen, Sudao He, Yiwei Li, Hongtian Chen. Data-driven monitoring for distributed sensor networks: an end-to-end strategy based on collaborative learning, IEEE Sensors Journal, vol. 22, no. 22, pp. 21795-21805, 15 Nov.15, 2022. (JCR Q1, IF: 4.3)(cite)

  • A collaborative soft-label network for label-noise learning in distributed sensor networks.
  • Academic Impact: Introduce local similarities for modifying hard samples through a dual-space smoothing technique.
  • Industry Impact: An accuracy of 88.33 is achieved when 40% of the labels are not correct using real-field data from Nanjing Metro Line S7. It can be extended to an unsupervised learning task.

💻 Publications

My full paper list is shown at my Google Scholar. Different research topics are highlighted using 🔶 Sensing, 🚩 Inspection, 🚄 Monitoring

First-author Papers

🔶🚩J6. Sudao He, Gang ZHAO, Jun CHEN, Shenghan ZHANG, Dhanada MISHRA, Matthew Ming-Fai YUEN. Weakly-Aligned Cross-Modal Learning Framework for Subsurface Defect Segmentation on Building Facades Using Unmanned Aerial Vehicles. Automation in Construction. (JCR Q1, IF: 9.6)(cite)(code 1)(code 2)(toolbox)

🚄J5. Sudao He, Wai Kei Ao, Yi-Qing Ni. A Unified Label Noise-Tolerant Framework of Deep Learning-based Fault Diagnosis via A Bounded Neural Network, IEEE Transactions on Instrumentation and Measurement, vol. 73, pp. 1-15, 2024, Art no. 3513515. (JCR Q1, IF: 5.6)(cite)(code)

🚄J4. Sudao He, Fuyang Chen, Hongtian Chen. A latent representation generalizing network for domain generalization in cross-scenario monitoring, IEEE Transactions on Neural Networks and Learning Systems, vol. 35, no. 11, pp. 16644-16658, 2024. (JCR Q1, IF: 10.4) (cite)

🚄J3. Sudao He, Fuyang Chen, Ning Xu. High-speed train localization algorithm via cooperative multi-classifier network using distributed heterogeneous signals, Journal of the Franklin Institute, 2023, 360(12): 8096-8117. (JCR Q1, IF: 4.1)(cite)

🚄J2. Sudao He, Fuyang Chen, Ning Xu, Hongtian Chen. Online monitoring for non-stationary operation via a collaborative neural network. IEEE Transactions on Instrumentation and Measurement, vol. 71, pp. 1-12, 2022. (JCR Q1, IF: 5.6) (cite)

🚄J1. Sudao He, Fuyang Chen, Bin Jiang. Physical intrusion monitoring via local-global network and deep isolation forest based on heterogeneous signals. Neurocomputing, vol. 441, pp. 25-35, 2021 (JCR Q1, IF: 5.5)(cite)

Papers as second and other authors

🔶J4. Xuanyi Lu, Sudao He, Shenghan Zhang. Deep learning for automated crack quantification with distributed fiber optic sensing: Addressing strain overlap and interface nonlinearity. Automation in Construction, Volume 176, 2025, 106280. (JCR Q1, IF: 9.6) (cite)

🚄J3. Qian-Qian Yu, Jie Wang, Xiang-Lin Gu, Sudao He, Shenghan Zhang. An Attention-Based Detection Method of Fatigue Cracks on Steel. Structural Control and Health Monitoring, 2025, 7487687, 21 pages. (JCR Q1, IF: 4.6) (cite)

🚄J2. Wentao Liu, Sudao He, Jianpeng Mou, Ting Xue, Hongtian Chen, Weili Xiong. Digital twins-based process monitoring for wastewater treatment processes. Reliability Engineering & System Safety, 2023: 109416. (JCR Q1,IF: 8.1)(cite)

🚄J1. Fuyang Chen, Sudao He, Yiwei Li, Hongtian Chen. Data-driven monitoring for distributed sensor networks: an end-to-end strategy based on collaborative learning, IEEE Sensors Journal, vol. 22, no. 22, pp. 21795-21805, 15 Nov.15, 2022. (JCR Q1, IF: 4.3)(cite)

Conference

🚩C3. Hanpeng Wang, Sudao He, Shenghan Zhang. An uncertainty-aware graph attention network for structural damage assessment leveraging heterogeneous information. Proceedings of 14th International Conference on Structural Safety and Reliability (ICOSSAR’25), June 1-6, 2025 in Los Angeles, CA, USA.

🚩C2. Sudao He, Hanpeng Wang, Shenghan Zhang. Trustworthy structural damage assessment using heterogeneous measurements. Proceedings of 14th International Conference on Structural Safety and Reliability (ICOSSAR’25), June 1-6, 2025 in Los Angeles, CA, USA.

🚩C1. Sudao HE, Shenghan ZHANG, Dhanada MISHRA, Matthew Ming-Fai YUEN. A graph learning approach for automatic subsurface defects segmentation in building façade using RGB and infrared images. Proceedings of the 10th European Workshop on Structural Health Monitoring (EWSHM 2024), June 10-13, 2024 in Potsdam, Germany. e-Journal of Nondestructive Testing. (cite)

🎖 Honors and Awards

  • 2025.01 Outstanding Reviewer of IEEE Transactions on Instrumentation and Measurement.
  • 2024.01 Outstanding Reviewer of IEEE Transactions on Instrumentation and Measurement.
  • 2021.10 Social Practice Outstanding Individual
  • 2020.10 Merit Postgraduate
  • 2019.10 Advanced Individual in Scientific Research and Innovation
  • 2016.09 NUAA Scholarship (1st Class)

📖 Educations

  • 2016.09 - 2022.10, Ph.D., College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing.
  • 2012.09 - 2016.06, Undergraduate, College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing.

💬 Invited Talks

ML in SSHM
sym
  • 2024.10, Machine Learning in Structural Sensing and Health Monitoring
  • 2023.09, Machine Learning in Structural Sensing and Health Monitoring

🤝 Experience

  • 2023.03 - 2023.08, Postdoctoral Research Associate at National Rail Transit Electrification and Automation Engineering Technology Research Center (Hong Kong Branch), The Hong Kong Polytechnic University, Hong Kong SAR.

  • Till now, I serve as a reviewer in many journals, including IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Instrumentation and Measurement, Journal of Vibration and Control, IEEE/CAA Journal of Automatica Sinica and ISA Transcations.

🌎 Service

Journal Editorship

Journal Reviewer

  • Journal of Computing in Civil Engineering
  • Journal of Vibration and Control
  • ISA Transactions
  • IEEE Transactions on Industrial Informatics
  • IEEE Transactions on Automation Science and Engineering
  • IEEE Transactions on Neural Networks and Learning Systems
  • IEEE Transactions on Instrumentation and Measurement
  • IEEE/CAA Journal of Automatica Sinica