BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Faculty of Science and Technology | University of Macau - ECPv6.14.2//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Faculty of Science and Technology | University of Macau
X-ORIGINAL-URL:https://www.fst.um.edu.mo
X-WR-CALDESC:Events for Faculty of Science and Technology | University of Macau
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Asia/Macau
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:CST
DTSTART:20170101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Asia/Macau:20170112T100000
DTEND;TZID=Asia/Macau:20170112T110000
DTSTAMP:20260514T143529
CREATED:20170112T020012Z
LAST-MODIFIED:20220927T045328Z
UID:6018-1484215200-1484218800@www.fst.um.edu.mo
SUMMARY:Local One Dimensional Embedding for Hyperspectral Image Classification
DESCRIPTION:Instructors/Speakers\nProf. Hong LI\nProfessor\nSchool of Mathematics and Statistics\nHuazhong University of Science and Technology\nWuhan \nAbstract\nHyperspectral image (HSI) classification aims to allocate a unique label to each pixel in the HSI dataset. However\, limited number of labeled pixels and high dimensionality of the HSI dataset makes HSI classification a challenging task. To address these issues\, we propose local one dimensional embedding (L1DE)\, which makes full use of the characteristics of HSI dataset. First\, pixels have similar spectral signatures should be the same class. Second\, pixels in the same spatial area are more likely to be the same class. Advantages of L1DE can be summarized as follows. The L1DE maps the high dimensional feature vector into 1D space. And it ensures that if the coordinates of two pixels are adjacent in the 1D space\, they are more likely to be close to each other in the original spatial domain\, and have similar spectral signatures. Additionally\, the local strategy used in L1DE can reduce the computation burden significantly. By use of L1DE\, we propose two frameworks for HSI classification: multiple L1DE interpolation (ML1DEI) and multiscale spatial information fusion (MSIF). Analysis of the computational cost for these frameworks are given in this report. Experimental results on four widely used HSI datasets indicate that\, the proposed frameworks show outstanding performance when compared with other state-of-the-art methods\, even when very limited labeled pixels are available. \nBiography\nProf. Hong Li is a Professor in School of Mathematics and Statistics\, Huazhong University of Science and Technology. Her research interests include Approximation and Calculation\, Wavelet Analysis and its Application\, Machine Leaning and Artificial Intelligence\, Pattern recognition and image processing\, Time-Frequency Analysis and Signal Processing. \n 
URL:https://www.fst.um.edu.mo/event/local-one-dimensional-embedding-for-hyperspectral-image-classification/
LOCATION:E11-1028
CATEGORIES:event_list,seminarslectures
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Macau:20170112T143000
DTEND;TZID=Asia/Macau:20170112T153000
DTSTAMP:20260514T143529
CREATED:20170112T063042Z
LAST-MODIFIED:20220927T045328Z
UID:6021-1484231400-1484235000@www.fst.um.edu.mo
SUMMARY:Synergy between Software Engineering and Big Data & Artificial Intelligence
DESCRIPTION:Instructors/Speakers\nProf. Tao Xie\nAssociate Professor\nDepartment of Computer Science\nUniversity of Illinois at Urbana-Champaign\nUSA \nAbstract\nBig data analytic or artificial intelligence (AI) systems are software systems too; thus\, software engineering for such software systems plays a critical role for improving development productivity and system dependability. On the other hand\, a huge wealth of various data exists in software life cycle\, including source code\, feature specifications\, bug reports\, test cases\, execution traces/logs\, and real-world user feedback\, etc. Data plays an essential role in modern software development\, because hidden in the data is information about the quality of software and services as well as the dynamics of software development. In recent years\, software analytics has emerged to utilize data-driven approaches to enable software practitioners to perform data exploration and analysis in order to obtain insightful and actionable information for completing various tasks around software and services. This talk presents an overview of recent achievements and future opportunities in the space of software engineering for big data & AI and big data for software engineering. \nBiography\nTao Xie is an Associate Professor and Willett Faculty Scholar in the Department of Computer Science at the University of Illinois at Urbana-Champaign\, USA. He worked as a visiting researcher at Microsoft Research. His research interests are in software engineering\, focusing on software testing\, program analysis\, software analytics\, software security\, and educational software engineering. He received a 2016 Microsoft Research Outstanding Collaborators Award\, a 2014 Google Faculty Research Award\, 2008\, 2009\, and 2010 IBM Faculty Awards. He is an ACM Distinguished Speaker and an IEEE Computer Society Distinguished Visitor. He is an ACM Distinguished Scientist. His homepage is at http://taoxie.cs.illinois.edu. \n 
URL:https://www.fst.um.edu.mo/event/synergy-between-software-engineering-and-big-data-artificial-intelligence/
LOCATION:E4-G051\, Macau
CATEGORIES:event_list,seminarslectures
END:VEVENT
END:VCALENDAR