CfP NISH 2014: Needles In a Stream of Hay

[Wouter Duivesteijn]

Call for Papers --- NISH 2014: Needles In a Stream of Hay
Dr. Wouter Duivesteijn, Prof. Dr. Katharina Morik, and Prof. Dr. 
Kristian Kersting

============
Motivation
============

Big Data can come in many challenging ways. One particular form that
occurs naturally in many situations comes with its own particular set
of challenges: streaming data.  In this setting the data arrives at our
doorstep with a high speed and in a high volume.  The main challenge
for the data miner is to immediately extract only the relevant
information from a data point, knowing that the discarded information
can never be retrieved again.

Many practical data mining applications involve searching for
exceptional behavior: finding the needles in a hay stack. Which items
are unusually frequently bought together? In what type of electoral
districts does a particular political party perform exceptionally well?
Can we identify patient groups that react better than the norm on
particular medication? Relatively simple instances of `exceptional
behavior' have been thoroughly investigated, but encompassing the full
range of interesting kinds of exceptionalities is still a distant goal.

At the place where these two research areas meet, we find some
tremendously challenging research questions. While monitoring the
movement of pedestrians, can we identify suspicious behavior? Within
the data observed by a neutrino telescope, can we find those neutrinos
that originated from outside of our solar system? Finding such needles
in static stacks of hay is not easy, but how can we still find needles
when we find ourselves in the middle of a stream of hay?

============
Workshop Structure
============

Since this workshop concerns a research topic where two branches of
data analysis meet, we will especially focus on fostering interaction.
The plenary program will feature several invited talks on the
combination of stream mining and exceptionality detection,
mini-tutorials on each of these branches separately, and a selection of
the best contributed papers.

============
Submission
============

Submissions are possible as either a full paper or extended abstract.
Full papers should present original studies that combine aspects of
both the following branches of data analysis:

* Stream Mining: extracting the relevant information from data
   that arrives at such a high throughput rate, that analysis or even
   recording of records in the data is prohibited.
* Local Exceptionality Mining: finding subsets of the data where
   something exceptional is going on.

In addition, extended abstracts may present position statements or
interesting cases of unsolved relevant problems for which the authors
would like input from the community.

Full papers may consist of a maximum of 12 pages; extended abstracts of
up to 4 pages, following the LNI formatting guidelines (see
http://www.gi.de/service/publikationen/lni).  The
only accepted format for submitted papers is PDF. Each submission will
be reviewed by at least two members of the program committee.

============
Important Dates
============

Workshop paper submission deadline: April 22, 2014.
Workshop paper acceptance notification: May 20, 2014.
Workshop paper camera-ready version deadline: June 23, 2014.

============
Website
============

http://www-ai.cs.uni-dortmund.de/nish.html