💻 Previous Projects

• 2023.09 - 2024.06 Designing a high-performance airfoil by advanced CFD and machine-learning methods (Final year design project for aerospace engineering, Prof. Fu Lin@HKUST)
  • Designing, implementing and evaluating machine-learning-based methods for airfoil shape optimization, and comparing results with numerical adjoint methods and experimental results
  • Inspiration:
    • Machine learning methods excel in identifying coarse global optima, while numerical adjoint methods excel in refining local optima
    • Combining these two methods could potentially yield improved results
• 2023.09 - 2024.06 Adversarial or reinforcement learning-based closed-loop training strategy for PINN-based fluid simulators that generalize (Final year project for computer science, Prof. Dit-Yan YEUNG@HKUST)
  • Designing, implementing and evaluating a closed-loop training strategy for PINN-based fluid simulator with adversarial or reinforcement learning, to achieve enhanced generalizability
  • Inspiration:
    • Closed-loop strategy can more efficiently explore the solution space
    • Training strategies like RL and AL can be used to form a closed-loop process
• 2023.06 - 2023.08 Iterative surrogate model optimization for transient fluid structure interaction (Summer research, Prof. Dr. Robert Katzschmann@ETH Zurich)
  • Designing, implementing and evaluating surrogate models for fluid structure interaction, conducting optimization with the resultant surrogate models
  • Inspiration:
    • Modeling transient fluid flow as a Markov process to enable single-step prediction of flow evolution
    • Introducing shape representation from the field of computer vision to enable monolithic modeling of fluid-structure interaction
    • Introducing active learning techniques to reduce the number of samples required for optimization
• 2022.02 - 2023.08 Deep learning for medical image analysis (Undergraduate research, Prof. Chen Hao@HKUST)
  • Designing, implementing and evaluating a novel de-overlapping strategy for semi-transparent cervical cell segmentation
  • Inspiration:
    • Using extra information from the overlapping area and the non-overlapping area to guide the segmentation of the whole cell
  • Publication: CVPR2023: DoNet: Deep De-overlapping Network for Microscopy Instance Segmentation
• 2021.06 - 2021.09, Digitalization of wet lab project (Student helper, WeShare Tech Limited)
  • Implementing the hazard warning feature with pop-up windows
  • Role:
    • Front-end development with Vue.js