Category Archives: Publications

TDMR 2.0 now available on CRAN

The R package TDMR (Tuned Data Mining in R) is now available on CRAN in a major new release 2.0. It supports the new R package SPOT 2.0 (Sequential Parameter Optimization Toolbox) with its largely redesigned and simplified interface. TDMR 2.0 has as well a simplified interface. Documentation and tutorials have been rewritten to account for the simpler interface.

Tuned Data Mining in R (‘TDMR’) performs the complete tuning of a data mining task (predictive analytics, that is classification and regression). Preprocessing parameters and modeling parameters can be tuned simultaneously. It incorporates a variety of tuners (among them ‘SPOT’ and ‘CMA’ with package ‘rCMA’) and allows integration of additional tuners. Noise handling in the data mining optimization process is supported, see Koch et al. (2015) <doi:10.1016/j.asoc.2015.01.005>.

Forschungsbericht on-line

Der aktuelle Jahresbericht des an der TH Köln im Forschungsschwerpunkt CIplus angesiedelten SPOTSeven Labs ist online.
Auf ca. 100 Seiten werden die aktuellen Forschungsgebiete, Promotionen und Veröffentlichungen dargestellt. Der Bericht kann hier heruntergeladen werden.

Jahresbericht SPOTSeven Lab

Summary of the European Expert Seminar “Combining Practice-Orientated and Theoretical Learning in Higher Education”

A summary of the European Expert Seminar “Combining Practice-Orientated and Theoretical Learning in Higher Education” is available online.
On 20 April 2015 37 participants from 13 different EU Member States (representatives from ministries, permanent representations and stakeholder organisations) as well as EU institutions (European Commission, European Parliament) came together in Brussels to discuss different models of “dual learning” (= combining practice orientated and theoretical learning) in higher education.

CUAS: Practice and theory combined in a flexible way
The example from Cologne University of Applied Science (presented by Prof. Bartz-Beielstein) was mentioned as follows:
“Jochen Goeser from the University of Applied Sciences Aachen and Prof. Dr. Bartz-Beielstein from the University of Applied Sciences Cologne both in Germany presented concrete examples of how theory and practice can be combined. In the example of Aachen students are following a classic “dual study programme”. The programme alternates between study phases at university and practical training in companies, especially foreseen for semester breaks and when students are working on their BA thesis. The workload for these students is particularly high. They are, however, compensated, for example by a salary paid by employers and excellent job prospects after graduation. The example from Cologne showed how practice and theory can be combined in a more flexible way, such as through project work with industry, internships and close cooperation with companies in all study phases.”

Please click here to read the summary of the European expert seminar.

Uncertainty Management in Simulation-Optimization of Complex Systems

The book “Uncertainty Management in Simulation-Optimization of Complex Systems – Algorithms and Applications”, Editors:  Gabriella Dellino and Carlo Meloni is announced on Springer’s Web page. Due date: July 14th, 2015.
It includes the publication “Uncertainty Management Using Sequential Parameter Optimization” (Thomas Bartz-Beielstein, Christian Jung, Martin Zaefferer).

Results from the Cooperation Between University of British Columbia and Cologne University of Applied Sciences

Steven Ramage from University of British Columbia (UBC) describes the SPO development and the results from the cooperation between UBC and the SPOTSevenLab (Cologne University of Applied Sciences) as follows:

Experimental Methods

Results from the cooperation between UBC and SPOTSeven are published in the book “Experimental Methods for the Analysis of Optimization Algorithms”.

“Bartz-Beielstein et al. [2005] adapted EGO to the optimization of algorithms, with their Sequential Parameter Optimization (SPO) method. SPO uses the same acquisition functions as EGO, but a slightly different model, which includes a second order polynomial fit as well as the standard Gaussian process model. Unlike EGO, their approach is able to deal with random response values through a continual resampling of the best observed points using a doubling strategy, which allows the estimate to converge to the true value over time. Finally, as opposed to fitting the model with each sample point individually, as done by SKO, SPO merges the samples for each point into a better estimate of the objective at that point, and then fits the model on these merged estimates.
Hutter et al. [2009a] directly compared SPO and SKO and their suitability for algorithm configuration. They found that SPO in general outperformed SKO on the algorithms they studied. They also introduced SPO+, which introduced some modifications to the original algorithm….” Continue reading

New issue of SIGEVOlution is now available

Pier Luca Lanzi announces that the new issue of SIGEVOlution is now available for you to download from

The issue features:

* Rule-Based Machine Learning by Ryan J. Urbanowicz
* Racing Line Optimization by Ricky Vesel
* K-Expressions Visualization by Alwyn V. Husselmann
* Women @ GECCO Workshop by Carola Doerr & Gabriela Ochoa
* 2014 Symposium on Search-Based Software Engineering by Nadia Alshahwan
* New Theses
* Calls and Calendar