Colloquium/Seminar

YearMonth
2017 Jan   Feb   Mar   Apr   May   Jun   Jul   Aug  
2016 Jan   Feb   Mar   Apr   May   Jun   Jul   Aug   Oct   Nov   Dec  
2015 Jan   Feb   Mar   Apr   May   Jun   Aug   Sep   Oct   Nov   Dec  
2014 Jan   Feb   Mar   Apr   May   Jun   Jul   Aug   Sep   Oct   Nov   Dec  
2013 Jan   Feb   Mar   Apr   May   Jun   Aug   Sep   Nov   Dec  
2012 Jan   Feb   Apr   May   Jun   Jul   Aug   Sep   Nov   Dec  
2011 Jan   Feb   Mar   Apr   May   Jun   Jul   Aug   Sep   Oct   Nov   Dec  
2010 Jan   Feb   Mar   Apr   May   Jun   Sep   Oct   Nov   Dec  
2009 Jan   Feb   Mar   Apr   May   Jun   Jul   Aug   Sep   Oct   Nov   Dec  
2008 Jan   Feb   Mar   Apr   May   Jun   Jul   Aug   Sep   Oct   Nov   Dec  
2007 Jan   Feb   Mar   Apr   May   Jun   Jul   Aug   Sep   Oct   Nov   Dec  
2006 Jan   Feb   Mar   Apr   May   Jun   Jul   Sep   Oct   Nov   Dec  
2005 Jan   Feb   Mar   Apr   May   Jun   Jul   Aug   Sep   Oct   Nov   Dec  
2004 Jan   Feb   Mar   Apr   May   Aug   Sep   Oct   Nov   Dec  

Event(s) on March 2013


  • Tuesday, 5th March, 2013

    Title: A shrinkage estimation for large dimensional precision matrices using random matrix theory
    Speaker: Mr. WANG Cheng, Faculty of Engineering and Information Technology, University of Technology Sydney, Australia
    Time/Place: 11:00  -  12:00
    FSC1217, Fong Shu Chuen Library, HSH Campus, Hong Kong Baptist University
    Abstract: In this work, a new data-driven shrinkage estimator for the population precision matrix has been introduced using random matrix theory. The new estimation is non-parametric without assuming a specific parameter distribution for the data and also there is no prior information about the structure of the population covariance matrix. We demonstrate by both theoretical and empirical studies that the new estimator, which is applicable for p > n, has good properties for a wide range of dimensions and sample sizes. Moreover, even if p < n, our new method always dominates the inverse sample covariance matrix and performs comparably with existing methods.


  • Monday, 18th March, 2013

    Title: High accuracy local absorbing boundary conditions for linear Korteweg-de Vries(KdV) equations
    Speaker: Ms. ZHANG Wei, Department of Mathematics, Hong Kong Baptist University, Hong Kong
    Time/Place: 10:00  -  11:30
    FSC1217, Fong Shu Chuen Library, HSH Campus, Hong Kong Baptist University
    Abstract: A high accurate absorbing boundary condition for linear Korteweg-de Vries (KdV) equations is proposed in our work. The artificial boundary condition in the Laplace domain is approximated by a truncated series with high accuracy. Then the original KdV equation on unbounded domain is replaced by an initial-boundary value problem defined on a finite interval. Different finite difference schemes are applied to solve the obtained PDEs and the order of convergence is verified numerically. Finally, numerical examples are implemented to demonstrate the stability and accuracy of the proposed method.


  • Thursday, 21st March, 2013

    Title: Pattern Recognition on Automation, Social Signal Processing, Visual Surveillance and Intelligent Transportation Systems
    Speaker: Dr. NGAN Yuk Tung, Department of Mathematics, Hong Kong Baptist University, Hong Kong
    Time/Place: 11:30  -  12:30
    FSC1217, Fong Shu Chuen Library, HSH Campus, Hong Kong Baptist University
    Abstract: Abstract: Pattern recognition is a popular multidisciplinary research among mathematics, engineering and computer science scientists. It can be found in various applications such as automation, social signal processing (SSP), visual surveillance (VS) and intelligent transportation systems (ITS). In this talk, there will be a general introduction of these pattern recognition applications. First, the automation application would be defect detection on patterned textures. Second, the SSP application would include an example of social group discovery on a protest activity. Third, the VS application would address visual tracking and classification in humans and vehicles. Lastly, the ITS application would demonstrate an outlier detection for massive traffic data from one of the busiest junctions in Hong Kong. The future work in various applications will be also discussed.


  • Thursday, 21st March, 2013

    Title: DLS: Stability of Laminar Shear Flow
    Speaker: Prof. Weinan E, Peking University and Princeton University
    Time/Place: 16:30  -  17:30 (Preceded by Reception at 4:00pm)
    RRS905, Sir Run Run Shaw Building, HSH Campus, Hong Kong Baptist University
    Abstract: In 1883, Reynolds published his classical work on the experimental study of the stability of shear shows. Since then the issue of the critical Reynolds number at which laminar flows become unstable has been studied by numerous people, including Sommerfeld, Heisenberg, C. C. Lin, Orazag, and more recently, Trefethen, Hof, Barkley, Eckhardt, etc. Despite this great deal of effort, the theoretical question as to how the critical Reynolds number should be determined still remains open. In this talk, we present an approach using ideas drawn from statistical physics and large deviation theory. This is joint work with Xiaoliang Wan and Haijun Yu.


  • Tuesday, 26th March, 2013

    Title: Fuzzy Topology
    Speaker: Prof. Liu Yingming, Department of Mathematics, Sichuan University, China
    Time/Place: 04:30  -  18:00
    Abstract: Sharing and discussion of: 《Fuzzy Sets and Systems》、 《Fuzzy Optimization &Decision Making》、 《J. Math. Anal. Appl.》


  • Thursday, 28th March, 2013

    Title: Big Data Analytics in Transportation -- Outlier Detection in Traffic Data Based on Dirichlet Process Mixture Model
    Speaker: Dr. NGAN Yuk Tung, Department of Mathematics, Hong Kong Baptist University, Hong Kong
    Time/Place: 11:30  -  12:30
    FSC1217, Fong Shu Chuen Library, HSH Campus, Hong Kong Baptist University
    Abstract: Big data age has come. Transportation is one of the most frequent areas, which requires big data analytics in storage and management. This talk presents a statistical method for modeling large volume of traffic data by Dirichlet Process Mixture Model (DPMM). Traffic signals are in general defined by their spatial-temporal characteristics, of which some can be common or similar across a set of signals, while a minority of these signals may have characteristics inconsistent with the majority. These are termed outliers. Outlier detection aims to segment and eliminate them in order to improve signal quality. It is accepted that the problem of outlier detection is non-trivial. As traffic signals generally share a high degree of spatial-temporal similarities within the signal and between different types of traffic signals, traditional modeling approaches are ineffective in distinguishing these similarities and discerning their differences. In regard to modeling the traffic data characteristics by DPMM, this work conveys three contributions. First, a new generic DPMM-based method is developed for unsupervised outlier detection of real-world traffic data. Second, it achieves a detection rate of 97.14% based on a database of 764,027 vehicles. Third, the proposed method can be readily extended to apply on big traffic data in entire road networks in the future.