Bachelorarbeiten

Masterarbeiten zu Software

Thema:Real-time anomaly detection for particle identification
Zusammenfassung: A new experiment at LUXE (Laser Und XFEL Experiment), but also particle physics experiments like Belle II, have to discriminate signal (photons) from background (neutrons). You will be using photon test-beam data to develop state-of-the-art deep learning algorithms for anomaly detection to reject non-photon events in calorimeters. The algorithms will be ultimately deployed on GPUs and FPGAs for offline and real-time analysis with inference times of a few 100 ns only.
Sie lernen kennen:machine learning, detector development, GPU and FPGA usage
Referent:Prof. Dr. Torben Ferber
Ansprechpartner:Prof. Dr. Torben Ferber
Letzte Änderung:23.01.2023
Thema:Detector studies for future beam dump experiment
Zusammenfassung: Light dark sector particles can be searched for at high intensity beam dump experiments like LUXE (Laser Und XFEL Experiment) at DESY or SHADOWS at CERN. Axionlike particles would be detected by reconstructing its decay products: Two photons with a distinct angular and energy correlation. During the MSc thesis you will design and optimize possible detector options to measure energy, time, and direction of the decay photons using state-of-the-art simulation software.
Sie lernen kennen:Particle physics (ALPs), GEANT4, data analysis, Python-programming, C++-programming
Referent:Prof. Dr. Torben Ferber, Prof. Dr. Markus Klute
Ansprechpartner:Prof. Dr. Torben Ferber
Letzte Änderung:23.01.2023
Thema:Improvement of the Machine Learning–based Track Quality Indicator for the Belle II Experiment
Zusammenfassung: The interpretation of the signals obtained by the tracking sub-detectors of the Belle II experiment is vital for the understanding of any event observed by the detector. An important step of this track reconstruction is the evaluation of the quality of a found track candidate. This evaluation is conducted with the help of multivariate analysis techniques, the performance of which must be validated on data recorded by the Belle II detector. In the scope of this project, a procedure to validate this track quality indicator shall be developed and applied. Furthermore, the findings of such a study can be utilized to improve the quality estimation.
Sie lernen kennen:Principles of track finding and track reconstruction, data analysis, Python-programming, machine learning, C++-programming
Referent:Prof. Dr. Torben Ferber
Ansprechpartner:Dr. Pablo Goldenzweig
Letzte Änderung:23.01.2023
Thema:Development of a Machine Learning–based Bremsstrahlung Finder for the Belle II Experiment
Zusammenfassung: Electrons are subject to Bremsstrahlung when traversing the volume of the Belle II detector. The photon which is emitted in this process carries energy away from the electron and produces an additional signal in the electromagnetic calorimeter. The aim of this project is the development of a method to recover possible Bremsstrahlung photons for a given set of particle tracks using multivariate analysis techniques. The method is compared to an existing classical solution to the problem with the ultimate goal to outperform it.
Sie lernen kennen:Machine learning, data analysis, Python-programming, C++-programming
Referent:Prof. Dr. Torben Ferber
Ansprechpartner:Dr. Pablo Goldenzweig
Letzte Änderung:23.01.2023