Nautilus Systems, Inc. logo and menu bar Site Index Home
News Books
Button Bar Menu- Choices also at bottom of page About Nautilus Services Partners Case Studies Contact Us
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] [Subscribe]

DM: CFP -- Data Mining and Visualiation for Systems Management

From: Hanan Lutfiyya
Date: by (mbox firschng)(with Cubic Circle's cucipop (v1.31 1998/05/13) Thu Dec 9 15:05:04 1999)
        We apologize if you receive this message more than once.

        IEEE 4th International Workshop on Systems Management 
      (Theme:  Exploitation of Data Mining and Visualization Age)

                   Montreal Quebec, Canada
                       June 28-30, 2000 

This workshop is the fourth in a series of highly successful forums for the 
discussion of research in the area of systems management.  Previous workshops 
have been held in Los Angeles, California, Toronto, Ontario, and Newport, RI.

This year the scope of this workshop is mining, visualization, management, 
and acquisition of data for network and systems management. With the 
widespread adoption of standards for data collection (e.g., SNMP in 
data networks CMIP in telecommunications networks) and the growing 
acceptance of technologies for information modeling (e.g., UML, XML, and CIM), 
the next challenge for network and systems management is interpreting the data. 

These interpretations should be task oriented, such as for problem detection, 
problem diagnosis, and planning. The purpose of this workshop is to bring 
together researchers with in-depth knowledge of data interpretation and 
presentation to focus on challenges of network and systems management. 
These challenges include: heterogeneous data semantics, dealing with large data
volumes, noisely data, high dimensional data, dearth of labelled data for 
supervised learning, and the exploitation of underlying structure 
(e.g., based on network topologies). To aid in our objective,
several data sets will be provided in advance of the workshop, along with 
some background about the kinds of information that should be extracted. 

Workshop participants are encouraged to submit papers (or extended abstracts) 
that apply their techniques to these data.

The URL for our site is

Three kinds of participation are possible. The first are presenters of 
full papers that fall within the topic areas considered by this workshop. The 
second are those who report on the results of mining and/or visualizing 

network and systems management data made available for this workshop, which
can be found under Dataset Information at 
This data has been provided by Cooperative Association for Internet Data 
Analysis (CAIDA).  Also encouraged is participation by individuals 
seeking information on recent advances in the application of data mining 
and visualization to network and systems management.  

An award will be presented to the best paper that provides the best insight
into the analysis (visualisation or patterns) of the skitter data
(please see "Dataset Information" at

All submitted papers will be reviewed by experts in the area of submission.  
Individuals presenting the results of analyses of the data sets provided by 
this workshop should submit an extended abstract summarizing their methodology 
and results. All accepted contributions (including extended abstracts) will be 
eligible for publication in the bound proceedings of the workshop.  At least 
one of the authors of each paper must register for the workshop to present 
the paper. 

Papers are to be submitted in English.  The cover page should include 
paper title, author(s) full name, affiliations, complete address(es), 
telephone number(s), and electronic mail address(es). Full-length papers 
should have a brief abstract and be no longer than 12 pages (6,000 words),
including references and figures. 

Extended abstracts should be in the format of an extended abstract that is no 
longer than 2 pages (1,000 words), excluding figures. 

Proposals for panel discussions are also solicited.  Panels are scheduled 
for 1.5 hours.  Proposals should specify the topic, panel chair, and 
participants.  Please include a two page abstract that highlights key points 
for discussion and areas of controversy that will be addressed. 

All submissions should be sent by email
in postscript or pdf form to with the subject 
line "SMW4 Paper Submission: <file name>," where <file name> 
indicates the compression used if any (e.g.,

If electronic submission is not possible,
please submit 4 paper copies to the following address:

  Professor Hanan Lutfiyya
  Department of Computer Science
  The University of Western Ontario
  London, Ontario CANADA N6A 5B7

Application of data mining algorithms to network and systems management 

Scalable and effective visualizations for management tasks 

Efficient techniques for on-line pattern recognition (e.g., for detecting 
performance problems and security intrusions)
Scalable architectures for distributed data mining and visualization 

Case studies of data mining and visualization in systems and network management 

Agent technologies for building distributed mining and visualization 

Information models that aid in mining and visualizing network systems 
management data 

Papers, panels, and extended abstracts due: February 22, 2000 
Author notification: April 1, 2000 

Camera ready copy: April 28, 2000 

Hanan Lutfiyya 
Department of Computer Science 
The University of Western Ontario

Paul J. Brusil 
35 Brackenbury Lane 
Beverly, Massachusetts, USA 01915-3821

Joseph L. Hellerstein 
IBM Thomas J. Watson Research Center 
Hawthorne, New York, USA

[ Home | About Nautilus | Case Studies | Partners | Contact Nautilus ]
[ Subscribe to Lists | Recommended Books ]

logo Copyright © 1999 Nautilus Systems, Inc. All Rights Reserved.
Mail converted by MHonArc 2.2.0