IEEE Special Issue

[Alexander G. Parlos]

Call for Papers
IEEE Transactions on Neural Networks
Special Issue on Adaptive Learning Systems in Communication Networks

Communication networks and internetworks, and in particular the Internet,
have been characterized as the ultimate data-rich environments, dynamically
evolving and expanding practically without any centralized control. Such
data-rich, unstructured environments present a particular challenge for
traditional methods of analysis and design. Adaptive learning methods,
in general, including adaptive signal processing, neural networks,
fuzzy logic and other data-driven methods and algorithms are in the
unique position to offer credible alternatives.

The goal of the proposed special issue is two-fold: (1) to highlight the
on-going research in the field of adaptive learning systems, and
in particular adaptive signal processing and neural networks, as it is
applicable to computer and communication networks, and, (2) to
present to the neural networks community and to others interested
in adaptive learning systems, in general, a variety of new and
challenging problems and their proposed solutions, originating from
the rapidly expanding universe of computer and communication networks.

As the use of these technologies spreads, numerous modeling,
estimation, control, classification, clustering and signal processing
problems are emerging. Many of these problems currently have no
satisfactory solutions and some have been addressed with ad-hoc
solutions. A common underlying theme of these problems is that they
are data-rich, represent dynamically changing environments where
the lack of valid mathematical models is predominant, and, are
representative of systems with no centralized control. These problems
appear amenable to data-driven methods and algorithms, such as
adaptive learning methods, including neural networks and other
non-parametric or semi-parametric approaches. This special
issue will welcome contributions with proposed approaches to
existing problems, either with currently known or new solutions,
and to new problems in the subject areas of computer and
communication networks. The focus of the proposed solutions
will be on data-driven or the so-called measurement-based methods
and algorithms, rooted in the general areas of adaptive learning methods.

Papers are solicited from, but not limited to, the following topics:
Network Management Topics: (i) Methods and algorithms for
network traffic analysis, modeling and characterization; (ii) Network
performance measurement and analysis techniques; network fault
monitoring and diagnosis methods; (iii) Network security and privacy,
including intrusion detection methods; (iv) Approaches and methods
for Quality of Service in IP networks; (v) Scalable routing algorithms
and decentralized congestion control algorithms; (v) Novel admission
control algorithms; (vi) Control algorithms for high-speed network
access technologies; (vii) Application of "new approaches" in adaptive
learning systems to data-intensive tasks in complex networks.
Content Management Topics: (i) Approaches for scalable Web
caching and related optimization methods; (ii) Novel solutions
to operational problems in content delivery and distribution
networks; (iii) Web data mining and knowledge discovery - scalability
and comparison of methods; (iv) Web personalization methods;
(v) Information hiding techniques and digital rights management;
(vi) Novel solutions to information access and retrieval for dynamic
Web content; (vii) Efficient compression algorithms and coding for
continuous digital media - multimedia content; (viii) Architectures for
Quality of Service guarantees in real-time distributed applications;
(ix) Uncertainty management in real-time distributed applications;
(x) Concepts in real-time distributed applications enabled by new
communication network technologies.

Guest Editors:
Alexander G. Parlos, Texas A&M University, College Station,
Texas, USA (Coordinator)
Chuanyi Ji, Georgia Institute of Technology, Atlanta, Georgia, USA
K. Claffy, San Diego Supercomputer Center, University of California,
San Diego, California, USA
Thomas Parisini, University of Trieste, Trieste, Italy
Marco Baglietto, University of Genoa, Genoa, Italy

Manuscripts will be screened for topical relevance, and those that pass
the screening process will undergo the standard review process of the
IEEE Transactions on Neural Networks. Paper submission deadline is
November 1, 2003. Prospective authors are encouraged to submit
an abstract by September 1, 2003. This will help in the planning
and review process. The final Special Issue will be published in the
Fall of 2004. Electronic manuscript submission is mandatory and only
papers in pdf format will be considered for review. All manuscripts
should be sent to the Coordinator of the guest editorial team
at a-parlos at tamu.edu.