Suche
Ergebnisse
-
Computing the Poisson-Binomial Distribution for Soccer Match Outcomes
(2024)In soccer analytics, the Poisson-Binomial distribution is used to obtain the probabilities of the possible match scores of a team. This is an important distribution for analysts, because it allows for construction of new descriptive metrics and further meta-analysis. This work outlines the theoretical background of the Poisson-Binomial distribution, hoists it into the context of soccer analytics, while also providing content on the ...Bachelor Thesis -
-
BIM-Based Circularity Assessment for Swiss Architecture Competitions
(2024)This thesis aimed to provide quantitative methods to assess circular construction strategies in Swiss architecture competitions. Its methodology consisted of three steps: Firstly, current practices in architecture competitions were identified. Secondly, current assessment methods were revised and, thirdly, integrated into a BIM-based competition delivery process. Very few Swiss architecture competitions that explicitly targeted circularity ...Master Thesis -
Solving the Elastic Wave Equation with Physics-Informed Neural Networks: A Robust and Critical Assessment
(2024)Physics-Informed Neural Networks (PINNs) have recently emerged as a promising approach for solving Partial Differential Equations (PDEs), offering a meshfree alternative that integrates physical principles into the learning process. This presents a new paradigm compared to traditional discretization methods and purely data-driven machine learning techniques. While promising, PINNs are not a panacea; they inherit challenges such as spectral ...Master Thesis -
Exploring the use of WebAssembly for isolating Functions in Dandelion
(2024)Untrusted code execution is the process of running software that cannot be assumed to execute correctly (bug-freedom) or with good intentions (malware-freedom). Today, untrusted code execution is found in various places, from a web-browser safely running websites on a mobile phone, to a large cloud computing provider running customer workloads on managed hardware and infrastructure. From an operating system perspective, we talk about ...Bachelor Thesis -
Experimental Optimization of a Peristaltic Pump Prototype for Pit-Emptying
(2024)The development of efficient, affordable, and mobile pit-emptying techniques is crucial for providing safe sanitation to people in densely populated areas of urban and peri-urban settlements with no access to sewer systems. A functional test stand for a low-cost, manually built peristaltic pump prototype was constructed and used to evaluate the flow rate performance of the prototype and variations thereof. Different tube sizes, tube ...Bachelor Thesis -
Statistical Analysis of Orbit Prediction Quality for ARIS SAGE CubeSat Satellite
(2024)Bachelor Thesis -
Design of an HDPE bottle collection and pre-cleaning system for recycling in Blantyre, Malawi
(2024)Until today, around 3 billion people lack access to municipal solid waste collection. Espe- cially low-income countries struggle with mismanagement of plastic waste. Openly disposed plas- tic materials form a severe risk to humans, animals, and the environment. To mitigate the growing issue of improperly discarded plastic waste in Blantyre, Malawi, a pilot program is being estab- lished by the Chair of Global Health Engineering at ETH ...Master Thesis -
Detection of Contamination in Biowaste
(2024)In the pursuit of a circular economy and the optimization of recycling rates for municipal waste, biowaste, constituting over 34% of Europe’s total municipal waste, emerges as a signifi- cantly overlooked resource. The potential of converting this biowaste into biogas and compost is substantial, offering valuable sources of green energy and fertilization, respectively. How- ever, a central challenge obstructing this potential lies in ...Master Thesis -
Causality in Unsupervised Learning: Methods and Applications in Cancer Genomics
(2024)Unsupervised learning deciphers the beautifully complex patterns embedded within vast amounts of data. As one of the main branches of machine learning, it seeks to discover hidden patterns in unlabelled data. One of the prevalent techniques within unsupervised learning is clustering, which groups data into distinct subsets of shared characteristics. In cancer research, clustering offers promising avenues to stratify patients based on their ...Doctoral Thesis