The 2nd Evo* Technology-Transfer Event
New* Final Program
Following a successful first edition of EvoTransfer,
which took place at Evo* 2012
last year in Malaga, a second technology-transfer event will be held at
Evo* 2013 in Vienna. The aim
is to improve cooperation and communication between industry and the evolutionary
computation research community, at a moment when the economy is struggling
to emerge from a crisis, and when entrepreneurs are beginning again to look
to invest in solutions that could increase their competitiveness.
EvoTransfer will invite potential
industrial partners from all over Europe to meet Evo*
researchers in Vienna so that they can demonstrate how they can contribute
to finding solutions to real-world problems arising in all areas of business
and industry. Participating researchers will be able to showcase their expertise
in problem-solving with evolutionary algorithms, and industrial participants
can illustrate their particular problems arising in their own business.
This is a good opportunity for you to showcase any success story, tool,
or technique you may have, not necessarily the one described in your accepted
paper.
The event will comprise a mix of short presentations, demos, and face to
face meetings between “technology providers”,
ie researchers who have significant expertise in the application of evolutionary
methods to real-world problems and “technology users”,
ie the engineers, technical staff, managers, and decision makers from industry,
finance, and all areas of business who are interested in learning more about
what evolutionary computation might do to help them solve their problems.
Participation in EvoTransfer
is included in the general Evo* registration.
If you are interested in principle, please contact EvoTransfer
Chair Andrea
Tettamanzi now to ensure that time and space is reserved
for you. Specific details can be worked out later, but provisional bookings
must be made now, so that we can prepare an appealing programme for industry.
Hope you can participate!
Final EvoTransfer Programme
Thursday 4 April 1630-1810 Room 3
Matching Technology Providers and Technology Users
Chair: Andrea Tettamanzi
This technology-transfer event showcases some technology solutions that the evolutionary computation community can offer to industry. Five short presentations will be made, followed by some industrial participants illustrating the problems they are facing as technology users, and for which they are seeking solutions. An open discussion session will follow.
Technology Provider Presentations by
Ami Moshaiov
“Supporting concept selection for design and planning by evolutionary
multi-objective optimization”
The conceptual design stage is a crucial design step. We introduced a novel
methodology to support concept selection, which we term Set-Based Concept
(SBC) approach. The SBC approach constitutes a revolution to design space
exploration and concept selection. According to this approach design space
exploration is simultaneously done at two levels including the conceptual
solution level and the detailed solution level. The presentation will include
an introduction to the SBC approach and a discussion on its variants, and
in particular those that have been developed at Tel-Aviv University. Currently
we collaborate with the aircraft industry to implement our tools to a conceptual
design problem of interest to that industry. Here, we propose to collaborate
with other industries to check the potential of our tools to support concept
selection by the industrial partner.
Contact: moshaiov@post.tau.ac.il
Gabriel Kronberger
“Applications of Evolved Virtual Sensors in the Automotive Industry”
We will show two concrete successful applications of genetic programming
to evolve virtual sensors. In the first application we used a symbolic regression
approach to evolve virtual sensors for NOx and soot emissions of diesel
engines based on data from an engine test bench. The evolved virtual sensors
are highly accurate and compact and can be used to estimate emissions based
solely on easily measureable engine data (e.g. RPM, fuel consumption, temperatures).
In the second application we used the same approach to evolve virtual sensors
for the blast furnace process for the production of molten iron. The resulting
models accurately model the unobservable internal state of the blast furnace
and can be used to improve the control and stability of the process.
Contact: gabriel.kronberger@fh-hagenberg.at
Andreas Beham
“Pick-optimized Storage Assignment in Production Warehouses”
Picking and routing are two time-consuming processes in warehouse operations.
We have taken a look on how to optimize the location of items in the warehouse
of one of our industry partners in the automotive industry. In the presentation
we will give an overview of the implemented approach, the software solution,
and some of the lessons learnt.
Contact: andreas.beham@fh-hagenberg.at
Stephan Hutterer
“Smart Electric Grid Engineering with HeuristicLab”
Soft computing techniques become of increasing importance for future power
systems, with manifold applications ranging from real-time generation scheduling
over power flow control to processing of huge demand or supply data. HeuristicLab
provides a generic workbench comprising soft computing techniques, suitable
to be used for typical power grid engineering problems. Different show cases
shall demonstrate the application to data mining issues, where accurate
forecasting models are built for customer demand prognosis or renewable
plants' generation prediction based on measurement data. A second application
area illustrates the utilization of HeuristicLab for optimization of smart
grid control and planning tasks.
Contact: stephan.hutterer@fh-wels.at
John Woodward
“DAASE (Dynamic Adaptive Automated Software Engineering)”
http://daase.cs.ucl.ac.uk/
Current software development processes are expensive, laborious and error
prone. They achieve adaptivity at only a glacial pace, largely through enormous
human effort, forcing highly skilled engineers to waste significant time
adapting many tedious implementation details. Often, the resulting software
is equally inflexible, forcing users to also rely on their innate human
adaptivity to find "workarounds". Yet software is one of the most
inherently flexible engineering materials with which we have worked, DAASE
seeks to use computational search as an overall approach to achieve the
software's full potential for flexibility and adaptivity. In so-doing we
will be creating new ways to develop and deploy software. This is the new
approach to software engineering DAASE seeks to create. It places computational
search at the heart of the processes and products it creates and embeds
adaptivity into both. DAASE will also create an array of new processes,
methods, techniques and tools for a new kind of software engineering, radically
transforming the theory and practice of software engineering.
Contact: jrw@cs.stir.ac.uk
Prof. Andrea G. B. Tettamanzi, EvoTransfer
Chair
Université de Nice Sophia Antipolis
andrea.tettamanzi(at)unice.fr
