divis GmbH News

News about design of experiments software

News at a glance

04.10.2017

New research results will be presented

At this year’s IEEE Conference on Systems, Man, and Cybernetics and IEEE International Conference on Intelligent Transportation Systems, new research results from Prof. Bäck’s team will be presented.

At this year’s IEEE Conference on Systems, Man, and Cybernetics (http://www.smc2017.org/), the contribution entitled “Moment-Generating Function Based Acquisition Function for Bayesian Optimization” will be presented. The authors illustrate in this article, how improvement-based variants of the so-called acquisition function in efficient global optimization can be generalized. By means of a continuous control parameter, the generalization facilitates a smooth transition from exploration to exploitation. First experimental results clearly indicate this to provide a powerful extension of the approach. 

At the der IEEE International Conference on Intelligent Transportation Systems (http://www.itsc2017.org/), the contributions „A Multi-Method Simulation of a High-Frequency Bus Line” and “Reconstructing Fixed Time Traffic Light Cycles by Camera Data Analysis” will be presented. In cooperation with Arriva (Leiden, NL), the first one applies a simulation approach, calibrated with real-world data, for understanding and optimizing phenomena of service bus operations (in this case the avoidance of bus bunching, i.e., the emerging direct sequencing of two or more buses of the same line). The second article (in cooperation with BMW) deals with the reconstruction of traffic light cycles by using cameras in vehicle, aiming at the learning of cycles for optimizing traffic flow and reducing the emission of greenhouse gases. 

Contact

+49 231 97 00 342

Breaking News

19.06.2018

CoPro ISP Meeting

On May 29 our colleagues Sina Däubener and Thomas Bäck participated a meeting in...

Case studies

Case studies give you an inspiration for possible optimization solutions in your own company.

Read more

Customers login

Please log in, you will be redirected automatically.

Contact details

divis intelligent solutions GmbH
Joseph-von-Fraunhofer-Str. 20
44227 Dortmund
+49 231 97 00 341
contact(at)divis-gmbh.com