Lucas Weber

Lucas Weber ist seit April 2022 wissenschaftlicher Mitarbeiter an unserem Lehrstuhl.

---

General Information and Interests

My research covers different topics from Knowledge Discovery and Mining:

• Machine Learning and Pattern Recognition for time series
• Change Point Detection in sensor signals
• Applied Machine Learning
• Robust Machine Learning
• Knowledge Discovery in Industrial Datasets

My primary interest lies in applying machine learning and pattern recognition techniques to sensor signals and knowledge discovery in time series sets.

Our current research project concerns the identification of sensor signals from complex industrial systems in collaboration with Siemens Energy. Some of the techniques used in this project are available as the Python-Pip package https://github.com/Lucew/changepoynt.

---

Open Topics

There are always several available topics for interested students and interested third parties. If you are on this page and have open topics related in any way to the fields listed above, get in contact using any of the contact information listed above. I would love to hear from you.

Currently, there are the following open topics:

Memory-aware implementation of Dynamic Time Warping in a low-level language like Rust or C++ with Python bindings

Architecture and Implementation of a Change Point Detection Testbench

Change Point Correlation for Knowledge Discovery in Time Series Datasets (Device Detection or Botnet Detection)

Unit-free classification of heterogeneous sensor signals from power plants (Using classical machine learning and Siamese Neural Networks)

All topics can be extended to a bachelor’s or master’s thesis, or scoped for a master’s project. Write me an E-Mail for more information about the topics. I’m also often looking for (paid) student assistants. Other topics can always be discussed.

---

Miscellaneous

I’m also a tutor for the Exercise in Knowledge Discovery in Databases held in the summer semester by persons at the chair. If you have any questions regarding the exercise, also get in contact with me.

Additionally, I’m always interested in sensor time series data sets. If you have open topics in the direction of pattern recognition and machine learning on sensor data, get in touch. In enjoy working with this data a lot.