Bachelorarbeiten zu Software
| Thema: | Graph Neural Network track reconstruction for low momentum particles at Belle II |
| Zusammenfassung: | Graph Neural Networks (GNNs) have shown impressive results for track reconstruction in High Energy Physics experiments. The GNNs reconstruction of tracks with low transverse momentum and hence high curvature in the detector’s magnetic field is particularly challenging if the tracks curl multiple times in the detector. As a bachelor student undertaking this thesis, you will develop a dedicated reconstruction algorithm to clean-up the GNN-predicted tracks and improve the track fitting efficiency for low momentum particles. By the end of this project, you will contribute to advancing track reconstruction techniques for low momentum particles, potentially paving the way for improved physics analyses and discoveries at Belle II. |
| Sie lernen kennen: | advanced track reconstruction techniques in particle physics, machine learning |
| Referent: | Prof. Dr. Torben Ferber |
| Ansprechpartner: | Lea Reuter |
| Letzte Änderung: | 08.05.2024 |
| Thema: | Advanced data visualization for Machine Learning algorithms |
| Zusammenfassung: | Data visualization plays a crucial role in understanding and interpreting complex phenomena in particle physics experiments. This thesis project focuses on leveraging advanced visualization techniques using Plotly, a powerful Python library for interactive plotting. As a bachelor student undertaking this thesis, you will explore the capabilities of Plotly to create dynamic and interactive visualizations tailored to the needs of particle physics analyses. Your tasks will include developing visualization tools to display detector geometries, particle trajectories, energy deposits, and other relevant data collected from the Belle II experiment with focus on Machine Learning reconstruction. Throughout the project, you will collaborate closely with physicists and data analysts to identify key visualization requirements and design intuitive interfaces for data exploration. By the conclusion of this project, you will have gained valuable experience in advanced data visualization techniques and made contributions to enhancing the visualization tools available for particle physics research. |
| Sie lernen kennen: | interactive data visualization techniques |
| Referent: | Prof. Dr. Torben Ferber |
| Ansprechpartner: | Isabel Haide |
| Letzte Änderung: | 08.05.2024 |
| Thema: | Input feature optimization for Graph Neural Network track reconstruction at Belle II |
| Zusammenfassung: | This thesis project focuses on optimizing input features for Graph Neural Network (GNN) track reconstruction at Belle II. As a bachelor student, you will explore techniques to enhance the performance of the GNNs developed within our Machine Learning team by refining the selection and representation of input features using simulated and real data of the large volume drift chamber of the Belle II experiment. Your tasks will involve analyzing the impact of different feature sets on track reconstruction efficiency and resolution. By the project's conclusion, you will have contributed to advancing track reconstruction techniques at Belle II through improved input feature optimization. |
| Sie lernen kennen: | advanced track reconstruction techniques in particle physics |
| Referent: | Prof. Dr. Torben Ferber |
| Ansprechpartner: | Lea Reuter |
| Letzte Änderung: | 08.05.2024 |
| Thema: | Performance optimization for Machine Learning reconstruction algorithms |
| Zusammenfassung: | This thesis project centers on optimizing the performance of Machine Learning (ML) reconstruction algorithms, particularly focusing on Python algorithms and their integration with C++ interfaces for the high-level trigger at Belle I running on a large computing cluster. As a bachelor student, your primary objective will be to streamline the execution of ML reconstruction algorithms on CPUs and GPUs. You will explore techniques such as algorithm parallelization, memory management, and code optimization to achieve optimal performance in both Python and C++ environments. Through rigorous benchmarking and profiling, you will evaluate the impact of your optimizations on the reconstruction speed and resource utilization. By the end of your thesis, you will have contributed to the development of robust and efficient ML reconstruction pipelines, essential for high-level trigger systems in particle physics experiments. |
| Sie lernen kennen: | advanced track reconstruction techniques in particle physics |
| Referent: | Prof. Dr. Torben Ferber |
| Ansprechpartner: | Dr. Giacomo De Pietro |
| Letzte Änderung: | 08.05.2024 |