[Computational-biology] CFP: First IEEE International Workshop on Semantic Aspects in Data Mining (SADM'08)

Maurizio Atzori via comp-bio%40net.bio.net (by icdm08-publicity from isti.cnr.it)
Fri Jul 4 17:00:52 EST 2008

*** We apologize in advance if you receive multiple copies of this CFP ***

First International Workshop on Semantic Aspects in Data Mining (SADM'08)
In conjunction with the 2008 IEEE International
Conference on Data Mining (ICDM 2008)
Pisa, Italy, December 15 - 19, 2008


Preliminary Call For Papers
Knowledge Discovery is generally described as a process of automatic
extraction of interesting useful, and previously unknown knowledge from
data. It is expected that data characteristics, data semantics as well
as the knowledge that already exists about the data can be directly
incorporated into the knowledge discovery process. However, semantic and
reasoning aspects may intervene in several steps of the discovery
process, and now the questionis how these aspects interact within the
process, and the forms that this can take. In data pre-processing,
semantic aspects may help in (1) identifying source data of interest,
(2) enriching the data with additional domain information, and (3)
generating more meaningful and human understandable patterns, once the
generated patterns are directly related to the input data. During the
mining task, semantics may be used as constraints, thus allowing (1)
search space reduction, (2) pattern pruning, and (3) the development of
more efficient algorithms. Background knowledge may intervene in the
post-processing step helping in the explanation of large amounts of
patterns, typically difficult to interpret.

The objective of SADM is to introduce standardized formal methods which
can explicitly consider data semantics, background knowledge, or
reasoning in the mining process. This knowledge has to be
represented/formalized in a knowledge repository, such as ontologies,
conceptual schemas, knowledge bases, etc. The main aspect is that this
knowledge has to be explicitly incorporated into the KDD process, where
the algorithms for data preprocessing, data mining or post-processing
make use of this knowledge to improve the KDD process. The key idea is
to develop a more general understanding about how to exploit data
semantics and background knowledge, and to create standardized
procedures for designing more intelligent data mining methods. We
believe that such an effort can lead to the development of the science
of semantic data mining.

Invited Talk:
Prof. Jean Francois Boulicaut from University of Lyon, will give a talk.
The preliminary  title is: "If constraint-based mining is the answer,
what is the constraint?"

Special Issue
The organizers intend to publish a selected and extended paper (the Best
Paper) as a special issue of an international journal (to be confirmed).
Topics of Interest:
The workshop will seek submissions where semantic information plays an
explicit role in the knowledge discovery process. The intent of the
workshop is to bring together researchers and practitioners interested
in semantic aspects in data mining from a wide range of possible data
mining subareas, including: web mining, medical data mining,
spatio-temporal data mining, ubiquitous knowledge discovery, and
privacy-preserving data mining. The aim of the workshop is to receive
contributions in the following topics, which are not exclusive:

- Techniques to embed semantics into the discovery process
- Semantics in data pre-processing and post-processing
- Semantic-based pruning
- Knowledge-based data mining algorithms
- Semantic-based techniques for feature selection
- Ontologies and data pre-processing
- Ontology-based evaluation of discovered patterns
- Data Mining Query Languages
- Constraint-based data mining
- Semantics for Knowledge representation, interpretation, and reasoning
- Semantics in SBIA Spatial and Spatio-temporal data mining
- Conceptual modeling and data mining
- Semantic-based KDD processes and frameworks
- Semantics in biological data mining
- Semantics for uncertainty handling in data mining
- Semantics in Privacy-Preserving Data Mining
- Semantics in Social Network Data Mining

  Researchers interested in domain-driven data mining may want to submit
their papers to DDDM'08 workshop on Domain Driven Data Mining

Important Dates:

- Submission Deadline: 1 August 2008
- Notification acceptance: 15 September 2008
- Camera-ready: 7 October 2008
- Workshop day: 15 or 19 december 2008

Preliminary Program Committee List (***to be completed***):

    * Luis Otavio Alvares, UFRGS, Brazil
    * Maurizio Atzori, - ISTI-CNR, Italy
    * Miriam Baglioni, Dept of Computer Science, University of Pisa, Italy
    * Toon Calders, Eindhoven Technical University, The Netherlands
    * Saso Dzeroski, Jozef Stefan Institute, Dept. of Knowledge
Technologies, Slovenia Oracle
    * Baris Kazar, Oracle, USA
    * Vipin Kumar University of Minnesota USA
    * Jin Soung Yoo, Indiana University, USA
    * Jose Antonio de Macedo, EPFL, Switzerland
    * Mirco Nanni, ISTI CNR, Italy
    * Giuseppe Psaila, University of Bergamo, Italy
    * Yucel Saygin, Sabanci University, Turkey
    * Yannis Theodoridis, Univ Pireus, Athens, Greece
    * Monica Wachowicz, UPM, Madrid, Spain
    * Mohammed Zaki, Department of Computer Science Rensselaer
Polytechnic Institute, USA

Submission Guidelines and Review Process:
High quality research papers in the relevant areas are solicited.
Original papers exploring new directions will receive especially careful
consideration. Papers that have already been accepted or are currently
under review for other conferences or journals will not be considered.
All accepted workshop papers will be included in the IEEE ICDM Workshop
to be published by the IEEE Computer Society Press. Therefore, at least
one author of the accepted paper must register to attend the workshop.
Paper submissions should be limited to a maximum of 8 pages  in PDF
format, in the IEEE 2-column style (see the IEEE Computer Society Press
Proceedings Author Guidelines at
All papers will be reviewed by the Program Committee on the basis of
technical quality, relevance to workshop topics, originality,
significance, and clarity. We will follow the double blind review
process. Authors must hence not use identifying information in the text
of the paper and bibliographies must be referenced to preserve
anonymity. Please use the Submission Form on the ICDM'08 website to
submit your paper.



Dr. Vania Bogorny,
Instituto de Informatica,
Universidade Federal do Rio Grande do Sul,
E-mail: vbogorny [at] inf.ufrgs.br

Dr. Hui Xiong,
Management Science and Information Systems Department,
Rutgers, the State University of New Jersey,
Email: hxiong [at] rutgers.edu

Dr. Chiara Renso,
KDD Laboratory, ISTI-CNR Pisa, Italy,
Via G. Moruzzi 156124 PISA - Italy
Email: chiara.renso [at] isti.cnr.it

More information about the Comp-bio mailing list