Embedded Files
Physics-constrained Machine Learning of Spatiotemporal System Dynamics
Physics-constrained Machine Learning of Spatiotemporal System Dynamics
Objective: Integrate cutting-edge advancements in machine learning and physics-based principles for robust predictive modeling of complex systems.
Approach: We have developed physics-constrained deep learning approaches to investigate spatiotemporal sensing data for robust modeling of cardiac electrodynamics.
Selected References:
B. Yao, F. Leonelli, and H. Yang, “Simulation Optimization of Spatiotemporal Dynamics in 3D Geometries”, accepted, IEEE Transactions on Automation Science and Engineering, 2025. [code] https://doi.org/10.1109/TASE.2024.3524132
B. Yao, “Multi-source Data and Knowledge Fusion via Deep Learning for Dynamical Systems: Applications to Spatiotemporal Cardiac Modeling”, accepted, IISE Transactions on Healthcare Systems Engineering, 2024. [code] https://doi.org/10.1080/24725579.2024.2398592
J. Xie* and B. Yao, “Hierarchical Gaussian Process for Defect Localization in 3D Systems”, IISE Transactions on Healthcare Systems Engineering, vol. 14(2), pp. 115-129, 2023. https://doi.org/10.1080/24725579.2023.2233992
J. Xie* and B. Yao, “Physics-constrained Deep Learning for Robust Inverse ECG Modeling”, IEEE Transactions on Automation Science and Engineering, vol. 20(1), pp.151-166, 2023. https://dx.doi.org/10.1109/TASE.2022.3144347
J. Xie* and B. Yao, “Physics-constrained Deep Active Learning for Spatiotemporal Modeling of Cardiac Electrodynamics”, Computers in Biology and Medicine, vol. 146, pp. 105586, 2022. https://doi.org/10.1016/j.compbiomed.2022.105586
B. Yao, “Spatiotemporal Modeling and Optimization for Personalized Cardiac Simulation”, IISE Transactions on Healthcare Systems Engineering, vol. 11(2), pp. 145-150. 2021. https://doi.org/10.1080/24725579.2021.1879322
Advanced Machine Learning of EHR Data for Automated Disease Detection
Advanced Machine Learning of EHR Data for Automated Disease Detection
Objective: Develop advanced machine learning models to study complexly structured electronic health records (EHR).
Approach: We have developed Multi-branching Temporal Convolution Network models to cope with the long-lasting challenges (e.g., missing values, imbalanced data) in longitudinal EHR datasets for reliable disease prediction.
Selected References:
Z. Wang*, S. Chen, T. Liu, and B. Yao, “Multi-Branching Temporal Convolutional Network with Tensor-based Imputation for Diabetic Retinopathy Prediction”, Early Access, IEEE Journal of Biomedical and Health Informatics, 2024. https://doi.org/10.1109/JBHI.2024.3351949
Z. Wang* and B. Yao, “Multi-Branching Temporal Convolutional Network for Sepsis Prediction”, IEEE Journal of Biomedical and Health Informatics, vol. 26(2), pp.876-887, 2022. [code] https://doi.org/10.1109/JBHI.2021.3092835
Z. Wang*, C. Liu, and B. Yao, “Multi-Branching Neural Network for Myocardial Infarction Prediction”, Proceedings of IEEE 18th International Conference on Automation Science and Engineering (CASE), Aug. 20-24, 2022, Mexico City, Mexico. https://doi.org/10.1109/CASE49997.2022.9926714
S. Chen, Z. Wang*, B. Yao, and T. Liu, “Prediction of Diabetic Retinopathy Using Longitudinal Electronic Health Records”, Proceedings of IEEE 18th International Conference on Automation Science and Engineering (CASE), Aug. 20-24, 2022, Mexico City, Mexico. https://doi.org/10.1109/CASE49997.2022.9926605
Deep Learning of Waveform Signals for System Diagnosis
Deep Learning of Waveform Signals for System Diagnosis
Objective: Develop advanced deep learning models to study waveform data for effective system diagnosis.
Approach: We have hierarchical deep learning frameworks with generative adversary networks to address the challenges (e.g., data-lacking and imbalanced data issues) in analyzing medical waveform data for automatic heart disease detection.
Selected References:
Z. Wang*, S. Stavrakis, and B. Yao, “Hierarchical Deep Learning with Generative Adversarial Network for Automatic Diagnosis of ECG Signals”, Computers in Biology and Medicine, vol. 155, pp. 106641, 2023. [code] https://doi.org/10.1016/j.compbiomed.2023.106641
J. Xie*, S. Stavrakis, and B. Yao, “Automated Identification of Atrial Fibrillation from Single-lead ECGs Using Multi-branching ResNet”, Frontiers in Physiology, vol. 15, 2024. https://doi.org/10.3389/fphys.2024.1362185
We sincerely thank our sponsors:
We sincerely thank our sponsors:
Google Sites
Report abuse