Statistical Methods for ICT Applications


            Simon Wilson

Simon Wilson

Contact Details: School of Computer Science and Statistics,
Lloyd Institute (Room 133),
Trinity College,
Dublin 2,

+353 (0) 1 896 1759
+353 (0) 1 677 0711


Personal Page Here

    Summary of Research:

    As is discussed in the STATICA Research page, my research interests have centered around issues of applying Bayesian methods of statistical inference in a wide variety of applications, motivated by the “data explosion” of the last few decades.  By this I mean that there are many applications in science, engineering and the humanities where data are being collected not only in an ever-increasing quantity but also the data exhibit complex structure.  This structure must be taken into account if the questions, that the data are meant to address, are to be answered adequately.  This quantity and complexity present tremendous challenges for developing statistical techniques that can handle them.

    The data explosion shows little sign of coming to an end, fed most recently by the availability of new experimental methods, cheaper sensors, the development of “pervasive” computing and the continued exponential growth in data transmission rates and storage capacity. Multimedia data (e.g. images, video and sound), biological data (e.g. genome and proteomics), sensor network data (e.g. road traffic, communications networks) and environmental data (e.g. weather) are all examples of this explosion.

    My research is centered around applications in reliability, telecommunications, astronomy and ecology where large quantities of highly structured data must be analysed.  All of these problems have certain properties in common from a statistical point of view that often allow similar statistical techniques to be applied. For me, the wide variety of other scientists that I interact with is what makes statistics a great field of research to be involved in!

    Below is a brief description of the projects that I am currently working on. 

    Publications and Presentations:

    Go here for a complete list of my publications.

    More recent work can be found at the technical report page of the Discipline of Statistics.

    All of my work makes use of the principles of Bayesian inference. The slides from a 1 hour introduction to Bayesian methods, in conjunction with a seminar here by Prof. Simon Godsill, is available here.

    I recently gave a 2 hour seminar at Universidad Rey Juan Carlos in Madrid on two applications of Bayesian methods: content-based image retrieval and source separation. The latter is a STATICA area of research. The seminar can be downloaded here (WARNING: large file, 18MB).