RIAIoT Lunch Seminar Series on 10 February : “Uncertainty Quantification for Reliable AI in Cancer Diagnosis” & “Sensation by Design: Tailoring Friction for Next-Gen Human-Machine Synergy”

 

We are excited to announce the RIAIoT Lunch Seminar Series, featuring two engaging talks from our members: “Uncertainty Quantification for Reliable AI in Cancer Diagnosis” by Prof. Xiaoge Zhang (1st speaker) and “Sensation by Design: Tailoring Friction for Next-Gen Human-Machine Synergy” by Prof. Yuan Ma (2nd speaker). This event will be held on 10 February, 2026, at The Hong Kong Polytechnic University.

 

Abstract & Biography

• Uncertainty Quantification for Reliable AI in Cancer Diagnosis

Abstract: Ensuring trustworthiness is fundamental to the development of artificial intelligence (AI) that is considered societally responsible, particularly in cancer diagnostics, where a misdiagnosis can have dire consequences. Current digital pathology AI models lack systematic solutions to address trustworthiness concerns arising from model limitations and data discrepancies between model deployment and development environments. To address this issue, we developed TRUECAM, a framework designed to ensure both data and model trustworthiness in non-small cell lung cancer subtyping with whole-slide images. TRUECAM integrates 1) a spectral-normalized neural Gaussian process for identifying out-of-scope inputs and 2) an ambiguity-guided elimination of tiles to filter out highly ambiguous regions, addressing data trustworthiness, as well as 3) conformal prediction to ensure controlled error rates. We systematically evaluated the framework across multiple cancer datasets, leveraging both task-specific and foundation models, illustrating that an AI model wrapped with TRUECAM significantly outperforms models that lack such guidance, in terms of classification accuracy, robustness, interpretability, and data efficiency, while also achieving improvements in fairness. These findings highlight TRUECAM as a versatile wrapper framework for digital pathology AI models with diverse architectural designs, promoting their responsible and effective applications in real-world settings.

Biography: Prof. Xiaoge Zhang received the Ph.D. degree in systems engineering and operations research from Vanderbilt University, Nashville, TN, USA, in 2019. He is currently an Assistant Professor in the Department of Industrial and Systems Engineering (ISE), The Hong Kong Polytechnic University, Hong Kong. His research centers on reliable AI, reliability and trustworthiness of autonomous systems, and uncertainty quantification. He has published more than 90 research articles in leading academic journals, such as Nature Communications, INFORMS Journal on Computing, IEEE Transactions on Systems, Man, Cybernetics: Systems, IEEE Transactions on Automation Science and Engineering, IEEE Transactions on Intelligent Transportation Systems, Reliability Engineering and Systems Safety, Risk Analysis, IEEE Transactions on Industrial Informatics, IEEE Transactions on Artificial Intelligence, IEEE Transactions on Reliability, IEEE Transactions on Cybernetics, etc. His research has gathered widespread attention from the academic community (more than 4900 citations and H-index 35 according to Google Scholar).

• Sensation by Design: Tailoring Friction for Next-Gen Human-Machine Synergy

Abstract: Over the last several decades, human-machine interactions have been limited to vision and audio channels. The introduction of haptics technologies has enabled users to receive mechanical feedbacks in the form of virtual touch. While the rapidly advancing haptics technologies in wearable devices and surface haptic devices have enabled many exciting applications in virtual reality (VR), augmented reality (AR), telecommunication, and teleoperation, they still suffer from issues in bulkiness, comfortability, and consistency. The solutions to these issues lie in the fundamental understanding of the multi-physics interactions in the human-machine interface, which include contact deformation, capillary formation, electric field, heat transfer, material non-linearity, and their complicated coupling effects. In this talk, Prof. Ma will discuss models on the multi-physics interactions in human-machine interface, with a special emphasis on modeling the finger friction variation on textured surfaces to design tactile sensations. This talk will also include how the multi-physics models have been applied in developing new wearable sensors, actuators, and surface haptics devices. The discussed models lay the foundation to develop haptics artificial materials (metamaterials) that can deliver any desired haptics performances for the next generation of human-machine mechanical interfaces and Metaverse.

Biography: Prof. Yuan Ma received his bachelor’s and M.S. degrees in mechanical engineering and materials science from Tsinghua University, Beijing in 2011 and 2013, respectively. He received his Ph.D. degree in mechanical engineering from the University of California, Berkeley in 2018. He is currently an Assistant Professor at the Hong Kong Polytechnic University. His research interest includes micro/nano scale mechanical and tribological behavior of human-machine interfaces, haptics metamaterials development, wearable devices with piezoelectret materials, and application of artificial intelligence in human-machine interactions. He has authored 12 peer-reviewed journal papers in Science Robotics, Advanced Materials, ACS Nano, Advanced Functional Materials, ACS Applied Materials and Interfaces, Applied Physics Letters, IEEE Transaction on Haptics, and IEEE Transaction on Magnetics.

 

Details

• Title: 

1. Uncertainty Quantification for Reliable AI in Cancer Diagnosis (1^st Speaker: Prof. Xiaoge Zhang)
2. Sensation by Design: Tailoring Friction for Next-Gen Human-Machine Synergy (2^nd Speaker: Prof. Yuan Ma)

• Date: 10 February 2026 (Tuesday)
• Time: 12:00 n.n. – 1:45 p.m.
• Venue: CD620, 6/F, Hong Kong Chinese Manufacturers' Association Building (Block C), The Hong Kong Polytechnic University (Capacity: 30, first-registered, first-served)
• Lunch Arrangement: A light lunch set (Food & drink from the PolyU gourmet shop) will be provided. You can choose your preferred option in the registration link before 4pm on 9 February. Please note that food orders placed after this time may not be counted, but you are still welcome to join the seminar.
• Register Methods: click https://polyu.hk/YsKcX or scan the QR code on the poster above

The seminar is primarily open to RIAIoT members, but please feel free to forward this email to invite Postdocs/Research staffs/PhD students in your team to register and attend.