Research Lines
Research Interests
Though, coming from an engineering background I am very keen
on basic research without losing sight of potential
applications. Naturally, the field of Computational
Intelligence offers vast opportunities to utilize the
results of basic research for various applications. The
areas I am currently working in are:
- Evolutionary Computation
- Artificial Neural Networks
- Evolutionary Robotics
- Computational Neuroethology
- ANN Game Playing
- Industrial Applications of Computational Intelligence
Work Groups
Research at our university is organized in formal work
groups with their own legal status. I am a member of the
following groups (units):
The neurodynamics group consists mainly of biologists working in
various fields of neurobiology. Besides having learned a lot on
neurobiology from excellent researchers in numerous seminars in the
last couple of years, my part in this group is computational
modelling of nervous systems (to avoid the term "brains"..;-).
Currently, we are working on a simulation of the evolution of
bird behavior, more specifically, the evolution of (simple)
brains of migratory and sedentary birds. Our goal is to investigate,
if simulated evolution generates differences in brain structure
similar to those found in real birds.
In the scientific computation group I play the role of a user, as e.g.,
the evolution of artificial neural networks is a computationally
very expensive endeavor. Currently, (amongst other things) we
utilize the computational
power of our cluster for ANNs learning to play the game of Go
employing evolutionary and reinforcement training methods.
The applied algorithmics group is home to industrial applications of
computational intelligence. Having designed and implemented a
generic evolutionary framework for resource allocation problems,
which is currently accustomed to user needs at our test site in a
drama school, we are now working with two companies on different topics.
In a cooperation with ANDATA two
master students work on their thesis in the fields of car crash
detection and autonomous traffic control employing computational
intelligence methods. In a project with Pöyry Infra GmbH we work on the automatic
classification of geological formations based on data from a
tunnel boring machine, which are processed by statistical and neural
pattern recognition approaches.
Industrial Cooperations
- since 07 - Asynchronous Replication
in a Loosely Coupled Data Base Cluster, Raiffeisenverband Salzburg
- since 06 - Automatic classification of geological
formations during tunnel boring, Pöyry Infra GmbH
- since 05 - Car crash detection and autonomous traffic
control, ANDATA
- since 04 - Data mining in sales prognosis, Wüstenrot AG
- 00-02 - Automated quality control of sintered metal
parts,
Miba
AG
- 96 - Steel quality prognosis based on
manufacturing data, VOEST-Alpine-Industrieanlagenbau (VAI)
- 95 - Industrial prognosis, details to be kept
secret
More Cooperations
History
The above lines of research emerged from our previous research group siGis (Salzburg Interest Group on Integrated Systems), which has been formed in spring '94 with the initiative of Roland
Schwaiger under the supervision of Prof. Horst D. Clausen and Prof. Jochen Pfalzgraf (then with RISC Linz). The foundation members were:
By time members came and went, among those were Karl Fürlinger , Marc Strapetz , Bernhard Krön ,
Joachim Steinwendner, Christian Blaschke, Wolfgang Brauneis, and Gerhard Katstaller.
I would like to thank all participants for their support and encouragement, and can assure that the siGis spirit will certainly prevail in our work!
Helmut A. Mayer
Last modified: Dec 7 2012