IFSA 2007 World Congress
SPECIAL SESSION: 14SS
ORGANIZERS:
Eduardo Gomez-Ramirez, Patricia Melin, and Oscar
Castillo
SCOPE: This Special Session is being organized as one of the
activities of the Task Force on Hybrid Intelligent Systems and will consist=
of
papers that integrate different Soft Computing (SC) methodologies for the
development of hybrid neural intelligent systems for modeling, simulation a=
nd
control of non-linear dynamical systems. SC methodologies at the moment inc=
lude
(at least) Neural Networks, Fuzzy Logic, Genetic Algorithms and Chaos Theor=
y.
Each of these methodologies has advantages and disadvantages and many probl=
ems
have been solved, by using one of these methodologies. However, many real-w=
orld
complex industrial problems require the integration of several of these
methodologies to really achieve the efficiency and accuracy needed in pract=
ice.
In this Special Session, an overview of SC methodologies, and their
applications to modeling, simulation and control, will be given in an
introductory paper by the Organizers. Then, detailed methods for integrating
the different SC methodologies and neural networks in solving real-world
problems will be given in the papers by the other authors in the Special
Session. The Special Session will include applications on the following are=
as:
Robotic Dynamic Systems, Non-linear Plants, Manufacturing Systems, and Time
Series Prediction.
=
=
1.&n=
bsp;
Successful new applications to real-world
problems of neural networks and soft computing techniques that are found to
achieve better results than conventional techniques. In this case, special
attention should be given to the metrics used to compare SC techniques with
conventional ones.
=
2.&n=
bsp;
Developments of innovative hybrid methods
combining neural networks with SC techniques and conventional techniques to
solve problems related to modeling, simulation and control of non-linear
dynamical systems. In this case, the problems to be considered in these pap=
ers
may not be as complex as the ones in the previous point, but the authors ha=
ve
to explain very carefully how their proposed method could be used, in the
future, to solve real-world problems.
=
3.&n=
bsp;
Papers considering original research on new
neural network techniques are also welcome, but the authors would have to m=
ake
a detailed description of how their proposed approach is compared with other
related techniques.
=
=
Papers
must be send by email, by the prospective author=
s, to
the Organizers. The papers must be send as a PDF=
or
word attachment with their email message. The papers will then be distribu=
ted to
the Reviewers for evaluation according to their originality, technical
soundness, writing, etc. (At least two reviewers per paper). Based on the
evaluations by the reviewers, the Organizers will select the Best papers for
the Special Session. Notifications of acceptance or rejection will then be =
send to the authors by email. The authors of accepted =
papers
would then be asked to send their final papers in the appropriate format and
also giving careful consideration to the comments and suggestions made by t=
he
reviewers.
Important DatesPaper Submission deadline: &nbs= p; December 11th,, 2006 Revised final manuscript due date: February 8th, 2007 Conference: &n=
bsp; =
; &n=
bsp; =
; June
18-21, 2007 |
Contact
information: Prof Eduardo Gomez, Prof. Patricia Melin, and Prof. Oscar Castillo Emails:
egr@ci.ulsa.mx pm<=
span
style=3D'mso-bookmark:_Hlt119140274'>elin@tectijuana.mx=
: ocastillo@tectijuana.mx |