Computer Science Colloquium
Big data processing with applications in TelecommunicationsFri 20.11.2015, 10:15, 60 minutes
Science Park 3, 055
AbstractIn this talk we will give an overview of the processing techniques for large amounts of telecommunications data. Big data is "defined" by IBM as Volume, Variety, Veracity and Velocity of the data flow. In this talk we will give an introduction to the subject of processing data which conform to one or more of the V's mentioned. A gentle introduction to computing platforms and common data processing languages will be given. Applications of big data processing including anomaly detection and clustering wanted artifacts will exemplify processing steps. An example of data clustering according to a "good" or "bad" network connection will be shown. One example from a real 3G dataset are included with an application of caching network to reduce network latency will be eluded. Open issues within big data processing such as privacy preservation for data releases, and legal issues with capture and retention of big telecom data will conclude the talk.
BioIan Marsh received his B.Sc degree in Physics and Computer Science and his M.Sc degree in System Design, both from Manchester University. Based on his research on quality aspects of Internet Telephony, he received his Ph.D. degree in Telecommunications from KTH, Sweden, in 2009. Since 1995, he is with the Swedish Institute of Computer Science (SICS), and he has been working as a Post-doctoral Researcher at the University of Porto, Portugal, from 2009 to 2011. His current research interests include caching of popular Internet objects and distributed Internet measurements using commodity hardware and community software.
Invited by Univ.-Prof. Dr. Andreas Springer, Institute for Communications and RF-Systems
The Computer Science Colloquium is organized by the Department of Coputer Science at JKU, the Österreichische Gesellschaft für Informatik (ÖGI) and the Österreichische Computergesellschaft (OCG).