Neueste Zugänge 

  1. COCPITT - the COmpaCt PIxel Tracking Telescope Commissioning, Performance Evaluation and Applications to Beam Test Studies 

    Reichmann, Michael (2015)
    The aim of this thesis is the commissioning of COCPITT - the COmpaCt PIxel Tracking Telescope, it is also meant to outline a performance evaluation and applications to beam test studies. In the first part an introduction is given that describes the theoretical background. It follows an explanation of the working principle of the telescope’s parts, especially the CMS pixel chip and of the telescope itself. Then, different set-ups are ...
    Master Thesis
  2. SpectralNet - Predicting the Time-Evolution of non-linear Partial Differential Equations using equation-supported LSTM-RNNs 

    Weber, Pascal (2018)
    In this work we present the SpectralNet, a novel approach to predict the time-evolution of non-linear partial differential equations. It is a combination of the Fourier-Galerkin pseu- dospectral method with Long Short Term Memory-Recurrent Neural Networks (LSTM- RNN). In contrast to purely data-driven approaches we do not approximate the time- evolution operator or the solution, but replace time-intensive steps in the solver. Based on ...
    Master Thesis
  3. Analysis of the Degree Programmes in the Field of Food Science and Technology Offered by Swiss Universities and Universities of Applied Sciences 

    Bieri, Philipp (2021)
    CES Studies
    This thesis systematically examines the degree programmes in the field of food science and technology offered by Swiss universities of applied sciences and the federal institutes of technology. Universities and universities of applied sciences educate qualified professionals for the economy, academia, and society. Due to the continuously changing needs of the labour market, those institutions have to develop their degree programmes in a ...
    Master Thesis
  4. Forest: Structural Code Editing with Multiple Cursors 

    Voinov, Philippe (2022)
    Software developers sometimes have to repeat an edit in multiple parts of their codebase in order to maintain or extend their software. To let the user perform a repetitive edit, text editors provide multi-cursor editing, which applies editing commands in multiple locations simultaneously. However, multi-cursor text editing is limited, since each executed command must make the desired change regardless of which cursor executes it. To ...
    Master Thesis
  5. Sparse Learning in System Identification: Debiasing and Infinite-Dimensional Algorithms 

    Akan, Mehmet Tolga (2021)
    In the traditional system identification techniques, a priori model structure is widely assumed to be available and the unknown parameters of the assumed model structure are estimated by maximizing the adherence of the assumed model structure to the experimental data. However, selecting the model structure can be problematic, sometimes leading to overfitting. Recent developments in the regularization based system identification methods, ...
    Master Thesis
  6. Experimental Verification of Energy Control in Buildings with Thermal and Visual Constraints 

    Decoussemaeker, Antoon (2021)
    About one-third of the total energy used in Switzerland can be attributed to space heating and cooling, which makes this area an attractive target for potential energy-saving solutions. Simply heating less would be an easy solution, but not a very attractive one. People expect a certain level of comfort when being inside a building, which is why it is crucial to develop methods that can achieve energy savings while preserving or even ...
    Master Thesis
  7. Scalability of Encointer - a Proof-Of-Personhood Cryptocurrency 

    Guicciardi, Piero (2022)
    Encointer is a cryptocurrency using a novel consensus mechanism called Proof- Of-Personhood which is based on people meeting physically at regular intervals in order to attest each other's personhood. After having a digital identity which is provably linked to a real human being, each user receives a universal basic income in one of Encointer's local community currencies. The protocol requires complex logic to be calculated on the ...
    Master Thesis
  8. Enabling Reproducible Randomness in ML Input Data Pipelines 

    Mohit, Kumar (2021)
    Master Thesis
  9. Semantically Controllable Human-Scene Interaction Synthesis 

    Zhao, Kaifeng (2021)
    Master Thesis
  10. Online Learning in Contouring Control Using Bayesian Linear Regression 

    Krishnadas, Raamadaas (2021)
    The contouring control problem aims to increase the tracking accuracy while traversing the trajectory as fast as possible. Model-based control algorithms such as Model Predictive Control have improved the tracking performance of contouring tools. They are nevertheless subject to the limitations of the simplified linear system models. The combination of control and machine learning has contributed to significant performance improvement. ...
    Master Thesis
  11. Real-Time Learning-Based Model Predictive Control: Online Algorithms and Applications in Energy Systems 

    Aoife, Henry (2021)
    The increased availability of sensing and computational capabilities in modern cyber-physical systems and networked systems has led to a growing interest in learning and data-driven control techniques. Learning-Based Model Predictive Control (LBMPC), i.e. the integration of learning methods in Model Predictive Control schemes, is one technique with potential applications for the control of dynamical systems under uncertain and stochastic ...
    Master Thesis
  12. Delayed deep learning for continuous-time dynamical systems 

    Schlaginhaufen, Andreas (2021)
    Bridging the gap between deep learning and dynamical systems, neural ODEs are a promising approach to model continuous-time dynamical systems. Motivated by state augmentation in discrete-time models, we propose to extend the neural ODE framework to neural delay di erential equations in order to naturally capture non-Markovian e ects such as time delays or hysteresis, which are often encountered in real world applications. We demonstrate ...
    Master Thesis
  13. Data-Driven Robust Congestion Pricing 

    Wang, Yize (2021)
    Self-interested routing is often inefficient in traffic networks. Economists and computer scientists have proven that imposing proper tolls on congested roads, i.e., congestion pricing, can effectively improve network efficiency by reducing the total travel time experienced by all users. However, most researches focus on deterministic demands, while uncertainties are rarely studied. As a result, the tolls designed for the deterministic ...
    Master Thesis
  14. Distributed identification and control for building thermal management 

    Mühlebach, Lorin (2021)
    Advanced control techniques have the potential to drastically improve the energy efficiency of buildings, with respect to thermal management. They can significantly reduce both the monetary cost and the environmental impact related to heating buildings. The application of advanced control schemes such as model based controllers in thermal management of buildings is often limited by (i) the expensive and time consuming process of obtaining ...
    Master Thesis
  15. Fraud Detection in Ethereum Using Web-scraping and Natural Language Processing Techniques 

    Benetti, Zeno (2021)
    The objective of this thesis is to discern Ethereum fraudulent smart contracts (defined as smart contracts related to Ponzi schemes) from non-fraudulent ones on the Ethereum blockchain. For this purpose, we employ web scraping techniques in order to retrieve data on the transactions of each smart contract. More importantly, we retrieve the opcodes sequence of each smart contract, which is to say the set of instructions that determine the ...
    Master Thesis
  16. A generative adversarial network-based framework for data-driven control problems with application to building energy management 

    Fonseca Lima, Doris (2021)
    Data-driven control methods have emerged in the last decades in response to increasingly complex energy systems and the integration of volatile renewable energy sources. They outperform simple rule-based and model predictive con- trollers in terms of cost and their response against uncertainties. The proposed methods are data-intensive, which is why there have been advances in the devel- opment of machine learning models producing synthetic ...
    Master Thesis

Mehr anzeigen