2D-Bewegungsanalyse mit Machine Learning

Type of work:
Programming

Motivation:
In the field of oil mist filtration, the finest droplets are filtered out of a gas stream using so-called coalescence filters, which usually consist of a tangle of fibers. The aim of current work is to gain a fundamental understanding of the mechanisms at work between fibers and droplets under vibrating ambient conditions.

Job Description:
In this context, the movement behavior of individual drops on a fiber is analyzed. A large number of videos are to be analyzed using machine learning to differentiate between different forms of movement of the droplet. The forms of movement and their temporal extent are to be determined. In addition, the videos are to be prepared by signal processing in such a way that meaningful features can be derived for the analysis.

If I have already aroused your interest at this point, then just come by my office. Then I'll show you the topics in detail and we can design your work according to your wishes.

What is important to me:

  • Critical questioning of your own results
  • Interest in the topic of Machine Learning
  • Knowledge of Matlab and Machine Learning is helpful

Best regards,
Alexander
 

Contakt: Alexander Schwarzwälder, M.Sc.
E-Mail: alexander.schwarzwaelder∂kit.edu
Tel.: +49 721 608-46573
Straße am Forum 8
Gebäude: 30.70,  Raum 109