Logo
Yuhao Zhong

Yuhao Zhong (钟毓豪)

Ph.D. Candidate, advised by Prof. Satish Bukkapatnam
Wm Michael Barnes '64 Department of Industrial and Systems Engineering
Texas A&M University

[hirobin_zhong at tamu.edu] [CV] [Google Scholar] [Linkedin]


My research focuses on advancing Data Science methodologies to address fundamental challenges related to quality, safety, and performance assurance, as well as knowledge discovery, primarily in Manufacturing processes and systems in the context of Industry 4.0/5.0. I am currently on the job market!

Current Research Areas

  • Advancement of explainable AI and generative AI methods
  • Process-structure-property (PSP) knowledge discovery and uncertainty quantification
  • Anomaly detection and localization
  • Human-centric autonomous robotic control and monitoring

Awards

Latest News

See all news →

Selected Papers

  • Paper Image

    EBLIME: Enhanced Bayesian Local Interpretable Model-agnostic Explanations

    Authors: Yuhao Zhong, Anirban Bhattacharya, Satish Bukkapatnam

    In: arxiv preprint, 2024

    TLDR: A Bayesian regularized approach to locally explain black-box model and quantify the explanation uncertainty more accurately. It can also be applied to defect segmentation and knowledge discovery.

  • Paper Image

    Detecting Anomalous Robot Motion in Collaborative Robotic Manufacturing Systems

    Authors: Yuhao Zhong, Yalun Wen, Sarah Hopko, Adithyaa Karthikeyan, Prabhakar Pagilla, Ranjana K. Mehta, and Satish T.S. Bukkapatnam

    In: IEEE Internet of Things Journal, 2024

    TLDR: External IoT surveillance cameras combined with marker pose estimation and LSTM to track fast-moving robot and detect anomalous robot motion based on risks in human-robot collaborative industrial environment.

  • Paper Image

    Identifying the Influence of Surface Texture Waveforms on Colors of Polished Surfaces using an Explainable AI Approach

    Authors: Yuhao Zhong, Akash Tiwari, Hitomi Yamaguchi, Akhlesh Lakhtakia, Satish T.S. Bukkapatnam

    In: IISE Transactions, 2023

    TLDR: Consolidating LIME local explanations into consistent global knowledge using a query-by-expert algorithm. We identified the influence of surface morphology on the colors exhibited by stainless steel 304 parts polished through the Magnetic Abrasive Finishing (MAF) process. This discovered physical knowledge was validated through confirmatory experiments and blind tests.

See all publications →