BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Department of Electrical and Computer Engineering (HKUECE) 電機與計算機工程系 - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://ece.hku.hk
X-WR-CALDESC:Events for Department of Electrical and Computer Engineering (HKUECE) 電機與計算機工程系
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:20250101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Asia/Hong_Kong:20260417T090000
DTEND;TZID=Asia/Hong_Kong:20260417T100000
DTSTAMP:20260511T035803
CREATED:20260402T024124Z
LAST-MODIFIED:20260402T024124Z
UID:115542-1776416400-1776420000@ece.hku.hk
SUMMARY:RPG Seminar – System Design for Wide-field Miniature Fluorescence Microscope
DESCRIPTION:Zoom Link:\nhttps://us05web.zoom.us/j/89432980495?pwd=LSDClCuSVwd9fL5oZaI532byF2aC1a.1 \nAbstract\nMiniature fluorescence microscope\, or miniscope\, is a compact fluorescence imaging system that integrates the excitation source\, optical filters\, imaging optics\, and image sensor into a small platform.  Among various technical approaches\, one-photon widefield miniscopes are especially attractive because of their relatively simple architecture\, strong engineering feasibility\, and compatibility with two-dimensional superficial imaging tasks. However\, existing miniscope systems still face important challenges\, particularly in balancing a large field of view with high spatial resolution\, maintaining image quality across the full field\, and achieving compact system integration. \nThis seminar focuses on the optical design of one-photon widefield miniature fluorescence microscopes for two-dimensional superficial imaging\, with the main emphasis placed on a single-channel system. The study investigates the key design considerations of excitation and emission light separation\, imaging optics configuration\, aberration control\, and system compactness\, aiming to achieve high-resolution fluorescence imaging over a relatively large field of view within a miniature platform. On this basis\, scalable multi-channel architectures are briefly considered as extensions to examine the feasibility of multi-channel integration in miniature fluorescence imaging systems. The work provides a system-oriented design framework for one-photon widefield miniscopes and highlights practical strategies for improving imaging performance\, structural integration\, and architectural scalability. \nSpeaker\nMr Wentao Ye\nDepartment of Electrical and Computer Engineering\nThe University of Hong Kong \nBiography of the Speaker\nWentao Ye is an MPhil student in the Department of Electrical and Computer Engineering at The University of Hong Kong\, supervised by Prof. Feifei Wang. He received his B.S. degree in Applied physics from Tianjin University in 2024. Her research interests include miniature fluorescence microscope and biomedical image processing. \nOrganiser\nProf. Feifei Wang \nDepartment of Electrical and Computer Engineering\, The University of Hong Kong \nAll are welcome.
URL:https://ece.hku.hk/events/20260417/
CATEGORIES:Seminar
ATTACH;FMTTYPE=image/jpeg:https://ece.hku.hk/wp-content/uploads/2024/11/rpg-seminar.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Hong_Kong:20260417T143000
DTEND;TZID=Asia/Hong_Kong:20260417T153000
DTSTAMP:20260511T035803
CREATED:20260413T015147Z
LAST-MODIFIED:20260413T015147Z
UID:115631-1776436200-1776439800@ece.hku.hk
SUMMARY:RPG Seminar – A General Deep Learning Framework for Wireless Resource Allocation under Discrete Constraints
DESCRIPTION:Zoom Link:\nhttps://hku.zoom.us/j/99219579381?pwd=IjEXStaAdwdBhtSyoZ0aYbLavr0zhX.1 \nAbstract\nDeep learning (DL)-based methods have achieved remarkable success in continuous wireless resource allocation\, yet its application to problems involving discrete variables remains hindered by the zero-gradient issue\, complex constraint enforcement\, and the lack of non-same-parameter-same-decision (non-SPSD) guarantees. To address these challenges\, this seminar presents a novel DL framework that leverages probabilistic modeling of the discrete support set to enable efficient\, end-to-end optimization. The speaker will further demonstrate the efficacy of this framework through two challenging mixed-discrete wireless resource allocation applications: (a) joint user association and beamforming in cell-free systems\, and (b) joint antenna positioning and beamforming in movable antenna-aided systems. The results demonstrate the superior performance of the proposed framework compared to the  state-of-the-art optimization algorithms and learning-based methods. \nSpeaker\nMr. Yikun WANG\nDepartment of Electrical and Computer Engineering\nThe University of Hong Kong \nBiography of the Speaker\nYikun Wang received the B.E. degree in Communication Engineering from Beihang University. He is currently pursuing the M.Phil. degree in the Department of Electrical and Computer Engineering at The University of Hong Kong\, under the supervision of Prof. Yik-Chung Wu. His research interests include deep learning-based optimization for wireless systems. \nOrganiser\nProf. Yik-Chung WU \nDepartment of Electrical and Computer Engineering\, The University of Hong Kong \nAll are welcome.
URL:https://ece.hku.hk/events/20260417-2/
CATEGORIES:Seminar
ATTACH;FMTTYPE=image/jpeg:https://ece.hku.hk/wp-content/uploads/2024/11/rpg-seminar.jpg
END:VEVENT
END:VCALENDAR