Oversea speaker

April 12 2024 (Friday) 3:30-4:30pm
This presentation explores machine learning (ML) integration with animal behavior studies and its transformative applications across neuroscience, human mobility analysis, and engineering. At the core of our research is the affinity between the complex behaviors observed in animal society and the predictive capabilities of ML algorithms.
In neuroscience, we introduce the development of robotic microscopes and feedback projections, offering insights into animal behavior at macroscopic and microscopic levels. This foundation supports our further applications in diverse fields such as retail analytics, human relationships estimation, and mobility service design. In the engineering domain, our work extends to preventive maintenance (condition-based maintenance: CBM) in manufacturing and transportation, drawing from the predictive nature of ML to foresee and mitigate equipment failures. Moreover, we introduce ML for digital twinning to create dynamic virtual models of physical systems.
This array of applications highlights the critical role of integrating computer vision and ML into problem-solving workflows across various production plants. This presentation emphasizes the essential need for interdisciplinary collaboration, bridging the gap between biologists, data scientists, and engineers.

April 5 2024 (Friday) 4:30-5:30pm
Unstructured documents often come with embedded structured data. Representing valuable and structured information as tables is popular in health, financial, and many domains. However, manual extraction of structured information from documents typically costs tremendous time and labor, motivating the need for a system for automating the process. After such tables have been extracted, the data can be used for a wide variety of tasks such as question answering and various “down-stream” analytics tasks. In this talk, we will discuss how to leverage ground breaking pre-trained language models (e.g., BERT, ChatGPT) to develop tools for automated table extraction from various types of documents. We will present different applications from cancer registry reporting, cancer care, and psychiatry hospitalization prediction.

February 2 2024 (Friday) 2:30-3:30pm
Neurological conditions affect one in six people, imposing significant health, economic and societal burden. Bioelectronic medicine aims to restore or replace neurological function with the help of implantable electronic devices. Unfortunately, significant technological limitations prohibit these devices from reaching patients at scale, as implants are bulky, require invasive implantation procedures, elicit a pronounced foreign body response, and show poor treatment specificity and off-target effects. Over the past decade, new devices made using methods from microelectronics industry have been shown to overcome these limitations. Recent literature provides powerful demonstrations of thin film implants that are miniaturised, ultra-conformal, stretchable, multiplexed, integrated with different sensors and actuators, bioresorbable, and minimally invasive. I will discuss the state-of-the-art of these new technologies and the barriers than need to be overcome to reach patients at scale.

Speaker: Academician C.C. Chan, Honorary Professor, The University of Hong Kong, Distinguished Chair Professor, Hong Kong Polytechnic University, Academician, Chinese Academy of Engineering, Fellow, Royal Academy of Engineering   About the TechTalk We would like to extend our sincere gratitude and appreciation to Academician C.C. Chan for sharing with us two videos of his speech on …

TechTalk – Insights on the Future Development of Engineering and Technologies in China Read More »

December 13 2023 (Wednesday) 3:30-4:30pm
Although recent research efforts in material development, device designs, and fabrication strategies have resulted in meaningful progresses to the goal of the human-centric optoelectronics, significant challenges still exist toward high-performance soft light emitting devices and curved photodetector arrays. In this talk, material assembly and fabrication strategies for the soft human-centric optoelectronics will be presented. First, recent processes in flexible, foldable, and stretchable quantum-dot light emitting diodes (QLEDs) will be presented. Technologies for high-resolution quantum dot patterning as well as passive matrix array of QLEDs with unconventional form factors will be explained. After that, wide FoV, miniaturized module-size, minimal optical-aberration, high-sensitivity, and deep depth-of-field artificial vision systems inspired from aquatic animal eyes will be presented. Unique stretchable image sensors whose image planes are well matched to the single-lens-based optical system enable such artificial visions. More recent progresses in the bio-inspired artificial visions with amphibious imaging and light-balancing capabilities will be also explained. These deformable QLEDs and bio-inspired artificial visions are expected to provide new opportunities for the advanced mobile electronics and robotics.

November 27 2023 (Monday) 4:00-5:00pm
Professor Gregory Abowd have been speaking and writing about the idea of an Internet of Materials (IoM) for nearly a decade. It started as a way to rethink Mark Weiser’s vision of ubiquitous computing in a more modern context, with the same hopeful zeal that Weiser presented in his writings from the late 1980s and early 1990’s. Professor Abowd will summarize how that re-interpretation has inspired his work, and the work of a growing community, for nearly a decade. From those involved in the fundamental understanding of computation to those involved in the practical development and deployment of computation, the future seems bright. We are moving towards a world of increased ubiquity of computation. There appears to be no end in sight for the increased ubiquity of all things computational. From a technical perspective, this is wonderful. More recently, professor Abowd have been forced to think about this vision through a different lens. How we justify any new vision of a technological future must be better grounded in the human motivation and potential impact. After explaining the “successes” of IoM, he will explain why he has fallen far short of a compelling motivation. But there are more compelling motivations, having to do with health, usable security and privacy, and, most importantly, sustainability. We MUST begin questioning a lot of the assumptions on how to make, operate, and dispose of computational objects. IoM is no longer a journey for a hopeful “visionary” to play out his fanciful predictions for the future. It is a mandate to address the fundamental hazards of our current trajectory towards ubiquitous computing.

November 13 2023 (Monday) 3:00-4:00pm
The number of colors in fluorescence microscopy is far less than the types of intracellular compartments. I will present our recent progress in super resolution imaging and deep convolutional neuronal networks to segment 15 subcellular structures. This approach bypasses the limitations of multi-color imaging, accelerates the imaging speed by one order of magnitude, and can accurately segment vesicle organelles with similar shapes and sizes. The super-resolution advantages were demonstrated in resolving the 3D anatomic nanostructures at different mitotic phases and tracking the fast dynamic interactions among nine intracellular compartments in live cell. We show transfer learning ability of our networks among different microscopes, different cell types, and even complexed system of living tissues.