The activities of this research group can be summarised in the following research lines:
- Artificial Neural Networks
- Fuzzy Systems
- Genetic Algorithms and Evolutive Strategies
- Soft Computing Hybrid Systems
- Pattern Recognition and Computer Vision
These research lines are not developed in an independent way, but they are
strongly connected. The first three lines integrate complementary methodologies
with a similar goal: the resolution of complex problems that cannot been
efficiently solved by means of traditional computational methods (hard
computing).
Main idea behind the fourth research line is the design or generation of
hybrid intelligent systems merging several soft computing
methodologies to tackle with more complex problems and their more difficult
resolution.
Finally, the last line copes with an enormous application field where the
performance of AI systems is lower than the human one, and where the soft
computing techniques have a great potential.
Nevertheless, the soft computing meaning has not an universally
accepted definition, it is possible to characterise if we compare it with the
traditional computation, usually known as hard computing. Soft computing
technologies try to emulate the techniques and pragmatic methods used by humans
to cope efficiently with both kind of problems: regular and extreme problems
(critical situations).It can be said as the trial to emulate what has been named
as the human intuition.
Participants
René Alquézar, Lluís Belanche, Àngela Nebot, Enrique Romero, Julio J. Valdés
External Collaborations
- Alberto Sanfeliu and Rafael Huber (Instiute of Robotics and Industrial Informatics, IRI, CSIC-UPC).
- Josep Maria Sopena (Neuro-computing group, Dept. of Basic Psychology, University of Barcelona)
- François E. Cellier (Artificial Intelligence and Simulation group, Arizona University)
Projects
CICYT TAP98-0473, CICYT TAP96-0882, CICYT TAP96-0629-C04-02
Relevant Publications
- A. Nebot, J.J. Valdés, M. Guiot, R. Alquézar and M.
Vallverdú. Fuzzy inductive reasoning approaches to the identification
of models of the central nervous system control. Proc. of Int. ICSC
Symposium on Engineering of Intelligent Systems (EIS'98). Tenerife, Spain
. Vol.1, pp.190-196, 1998.
-
- J.J. Valdés, L. Belanche and R. Alquézar. Fuzzy heterogeneous
neurons for imprecise classification problems. To appear in International
Journal of Intelligent Systems, 1998.
-
- R. Alquézar, J. Cueva, J.J. Valdés, A. Nebot and P. Caminal.
Learning a multi-subject model of the central nervous system control using
neural networks. Proc. of Int. ICSC Symposium on Engineering of Intelligent
Systems (EIS'98). Tenerife, Spain. Vol.2, pp.206-212, 1998.
-
-
R. Alquézar, A. Sanfeliu and F. Serratosa. Synthesis of
function-described graphs. Advances in Pattern Recognition. Proc. of Joint
IAPR Int. Workshops SSPR'98 and SPR'98. Sydney, Australia. Springer-Verlag
, LNCS-1451, pp.112-121, 1998.
-
-
L. Belanche, J.J. Valdés and R. Alquézar. Fuzzy heterogeneous
neural networks for signal forecasting. Proc. of the 8th Int. Conference
on Artificial Neural Networks (ICANN'98). Skövde, Sweden. Vol.2,
pp.1089-1094, 1998.
-
-
L. Belanche, J.J. Valdés, J. Comas, I. Roda and M. Poch. Modeling the
input-output behaviour of wastewater treatment plants using soft computing
techniques. Proc. of ECAI'98 Workshop on Binding Environmental Sciences and AI (BESAI'98). Brighton, UK, pp. 81-94. August 1998.
-
- R. Alquézar and A. Sanfeliu. Recognition and learning of a class of
context-sensitive languages described by augmented regular expressions.
Pattern Recognition 30(1):163-182, 1997.
-
-
J. Cueva, R. Alquézar and A. Nebot. Experimental comparison of fuzzy
and neural network techniques in learning models of the central nervous
system control. Proc. of 5th European Congress on Intelligent
Techniques and Soft Computing (EUFIT'97) . Aachen, Germany. Verlag Mainz,
Vol.II, pp.1014-1018, 1997.
-
-
T. Jerez and A. Nebot. Genetic algorithms vs. classical search techniques for
identification of fuzzy models. Proc. of 5th European Congres
s on Intelligent Techniques and Soft Computing (EUFIT'97) . Aachen,
Germany. Verlag Mainz, Vol.I, pp.769-773, 1997.
-
-
A. Nebot, F.E. Cellier and M. Vallverdú. Mixed quantitative/qualitative
modeling and simulation of the cardiovascular system.
Computer Methods and Programs in Biomedicine 55(3), pp.-, 1997.
-
-
A. Nebot and J.J. Valdés. The use of fuzzy techniques in the study of
non-invasive mechanical ventilation therapies.
Proc. of Sixth IEEE Int. Conference on Fuzzy Systems (FUZZIEEE'97). Barcelona, Spain, pp. 241-246, 1997.
-
- R. Alquézar and A. Sanfeliu. An algebraic framework to represent
finite-statemachines in single-layer recurrent neural networks. Neural Computation 7(5):931-949, 1995.
See the AI Section Publications for an extensive list of publications
