COLLOQUIUM
             Computer Science Department, Boston University

Speaker: Michalis Vlachos
         IBM T.M. Watson Research Center

Date:  Friday, March 25
Time:  12:15
Place: Room MCS 135, 111 Cummington Street 
       (for directions, see www.cs.bu.edu/colloquium)

Title: Indexing, Searching and Exploring Time-Series Data

Abstract:

Time-series are probably the most prevalent form of data storage and
representation in most scientific fields. However, in order to efficiently
search and explore the ever-increasing amount of collected data, one needs
to deploy intelligent techniques for data compression/representation, data
organization/pruning and similarity characterization.

In this talk we address the above issues, with a specific focus on
multi-dimensional time-series. Such data can be encountered in numerous
disciplines such as environmental applications, animal mobility
experiments, video tracking/surveillance data, motion capture data, etc. We
will present an indexing structure that can significantly ease the
exploration of multi-dimensional data. The index can assist the flexible
discovery of objects with specific motion patterns by supporting multiple
distance measures such as the Euclidean, the Longest Common Subsequence and
the Dynamic Time Warping, without the need to restructure the data
organization. The proposed framework guarantees that no qualifying matches
will be missed and can also be tailored to provide much faster response
time at the expense of slightly reduced precision/recall. We will
demonstrate the high applicability of the described techniques on many real
world problems, such as motion-capture (MOCAP) matching, OCR recognition,
image classification, etc.

The talk will also examine many other applications of time-series data,
such as burst and periodicity detection of log data, representation of data
streams, shape recognition in image databases and online clustering of
image repositories.

Biography:

Michalis Vlachos is a Research Staff Member at IBM Research. He received
his PhD degree from University of California, Riverside.  His research
interests expand on the areas of data-mining, databases, time-series,
clustering and classification of multimedia data. He has received his BS in
Informatics with Highest Honors from Aristotle University in Greece, and he
was a recipient of the Fulbright Foundation scholarship for graduate
studies.

Host: George Kollios