Recent Submissions 

  1. Navigating the Latent Space of Simulation Data via Deep Reinforcement Learning 

    Herter, Johannes (2022)
    Latent sequential prediction for complex equations such as predicting fluid flows from a set of reduced parameters often results in drifting and accumulated error in theory and practice. Over prolonged time spans, this can lead to a polynomial increase in prediction errors which in turn can cause instability of the underlying time integration. In the present work, we propose a general framework based on imitation learning to robustly ...
    Bachelor Thesis
  2. The Development of a Recycled Plastic Wheel for Cardboard Collector Trollies - Improving the working conditions of informal cardboard recyclers in Durban, South Africa 

    Köttering, Fynn (2022)
    A large proportion of the global working population has jobs with poor working conditions and in- adequate governmental support. A typical example of such occupations are waste pickers, who earn their living by collecting and reselling recyclable waste material. Specifically, this thesis focuses on cardboard recyclers in Durban, South Africa, and the NGO AeT, who works with these recyclers and tries to improve their working conditions and ...
    Bachelor Thesis
  3. Low-cost compost screening technology to improve trash separation 

    Venetz, Nicolas (2022)
    Bachelor Thesis
  4. Automatic Inference of Stream Semantic Registers in LLVM 

    Rupf, Thomas (2022)
    Bachelor Thesis
  5. Feasibility of Waste Maize Husk Valorization as a Plastic Plate Replacement in Durban, South Africa 

    Loos, Sebastian (2022)
    The zero-waste project at the Warwick Junction area of Durban, South Africa promotes alternative solutions for local solid waste management. Asiye eTufelani, a local NGO and driving force of the project, has identified two unsustainable material flows that included waste maize husks generated at a local mealie (maize cobs) cooking site and polystyrene food packaging distributed at the markets. This study investigates the management, and ...
    Bachelor Thesis
  6. High-speed rail and its competitors on long-distance travel in Western Europe 

    Deutschel, Jakob L. (2022)
    High-speed rail has proven to be a viable and eco-friendly mode of transport on long-distance travel, challenging high-emission modes like the airplane or the privately owned car. This thesis is centred around the question of how a substantial mode shift from the mentioned high-emission modes to high-speed rail could be achieved in Western Europe. Firstly, different cases of highspeed rail lines across Europe were looked at in a literature ...
    Bachelor Thesis
  7. Sustainable Operation and Thermal Concept for SpaceHopper 

    Krasnova, Elena (2022)
    SpaceHopper is a three-legged, 5 kg heavy robot developed for the exploration of low gravity environments, with its main focus being the exploration of asteroids. To function in the extreme environment and maximise the science return of a mission, the robot must be able to function for as long as possible while keeping its temperature within the operating limits of the onboard electronics. This work describes the development of insulation, ...
    Bachelor Thesis
  8. Optimization for pixel farming 

    Keller, Michael (2022)
    This thesis explores three optimization methods for pixel farming, a farming method that attempts to utilize the benefits of intercrop effects within a single field. By reducing a one dimensional version of the problem to finding Hamiltonian Paths, we demonstrate the NP-completeness of the general problem. Further we develop three methods for exploring the large search space. The first method relaxes the pixel farming problem to a fractional ...
    Bachelor Thesis
  9. Bringing Quantization to the Transfer Learning World 

    Hussein, Mahmoud (2022)
    Bachelor Thesis
  10. Optimizing geodetic VLBI Simulation Parameters using Swarm Intelligence 

    Wicki, Juliette (2021)
    Mit Very Long Baseline Interferometry (VLBI) kann die Differenz der Ankunftszeit eines Signals gemessen werden, um geodätische Parameter wie die Erdorientierungsparameter zu bestimmen. Das empfangene Signal, das von extragalaktischen Quellen ausgesendet wird, ist sehr schwach, weshalb grosse Teleskope und eine hohe Samplingrate notwendig sind. Aus diesem Grund sind VLBI-Messungen zeitintensiv und teuer sowie Simulationen unumgänglich. Das ...
    Bachelor Thesis
  11. Prediction of atmospheric parameters from GNSS observations and weather models with machine learning 

    Halbheer, Mike (Michelle) (2021)
    Global Navigation Satellite Systems (GNSS) experience various delays as their signals propagate through the Earth’s atmosphere. Some sources of error, such as the ionospheric delay, can be accounted for with relative ease. Delays caused by the lowest atmospheric layer, the troposphere, however, are challenging to predict accurately due to their high spatial and temporal variability. Tropospheric delays depend on weather conditions, allowing ...
    Bachelor Thesis
  12. HPCG for FPGAs: A Data-Centric Approach 

    Steiger, Rahul (2022)
    Field programmable gate arrays (FPGAs) have become increasingly popular in the high-performance computing (HPC) community due to their versatility in providing application-specific hardware acceleration. The main advantage of an FPGA is that it can be reconfigured as needed for each application. This property places the FPGA between general-purpose hardware like CPUs and custom-built ASICs. With the introduction of HBM memory into modern ...
    Bachelor Thesis
  13. Practical data-centric optimization of C/C++ applications 

    Lepori, Andrea (2022)
    C is a programming language used everywhere and in a big part of scientific codes. With the increase of highly parallel computing machines the code needs to be adapted to be able to use the full power available. In my thesis I will expand a compiler frontend to be able to transform C code into a data centric representation that will intern be able to identify data dependencies automatically and hence produce highly parallel code. ...
    Bachelor Thesis
  14. Lagrange and Markov Spectra 

    Giudici, Luca (2022)
    Bachelor Thesis
  15. Graph algorithms for the spatial computer model 

    Baumann, Yves (2022)
    Bachelor Thesis
  16. Live Aircraft Destination Prediction using Machine Learning & Adversarial Attacks 

    Lindner, Mathis Kurt (2022)
    As a continuation of uncovering threats posed in aviation that are due to ADS-B not being secure, we looked into how a non-commercial aircraft user's privacy can be compromised in real-time with publicly available data. Since there are many ways to predict the destination of an airplane whilst in the air we investigated this matter using a long short-term memory and a gradient booster model. With the gradient booster model, depending on ...
    Bachelor Thesis

View more