Search
Results
-
Data-driven analysis of the "Ranking quality" network formation model
(2020)Recent years have witnessed a dramatic growth in online social media, such as YouTube, Instagram, and Twitch, which are based on User-Generated Content (UGC). A huge amount of UGCs are generated by social influencers every day and spread over the world, having a huge impact on, e.g., social media marketing, and information spreading. Therefore, it becomes important to investigate (i) how such influencers emerge and (ii) what are the ...Master Thesis -
Visualizing BGP RIB Changes into Forwarding Plane by Leveraging BMP and IPFIX
(2020)At its core, the Internet and modern large-scale data centers use BGP as its main control-plane protocol to exchange routing and reachability information among its peers. BGP has been around for decades and has seen countless updates and extensions to support the growing number of use cases and ever increasing demands. The desire to gain deeper insights into the internal states of BGP prompted the introduction of the BGP Monitoring Protocol ...Master Thesis -
Compositional Computational Systems
(2020)We propose a collection of formal definitions for problems and solutions, and study the relationships between the two. Problems and solutions can be represented as morphisms in two categories, and the structure of problem reduction and problem-solving has the properties of a heteromorphic twisted arrow category (a generalization of the twisted arrow category) defined on them. Lagado, a compositional computational system built on a ...Master Thesis -
Exploring the Utility of Fine-Tuned Transformer Embeddings in Machine Learning Guided Directed Evolution
(2020)Directed Evolution is one of the most powerful tools for protein engineering, which functions through repeated mutagenesis in the sequence space and screening for desired properties such as increased reactivity, higher thermal stability, and stricter stereoselectivity. However, by increasing the number of sites for mutagenesis, the combinatorial sequence space grows exponentially, which means with even a few mutating sites, exploring the ...Master Thesis -
Development and evaluation of modulated arc technique for total body irradiation radiotherapy
(2020)Total Body Irradiation (TBI) is a type of Radiation Therapy (RT) technique, used for irradiation of the whole patient body. The standard way of TBI is based on static photon beams with more than 3 m long distance between the radiation source and the patient. But it is often not possible in smaller size radiation therapy rooms in many RT centers. Modulated Arc (mARC) technique for TBI, is one of the techniques to perform TBI with a ...Master Thesis -
Evaluation and Deployment of Resource-Constrained Machine Learning on Embedded Devices
(2020)Deep neural networks (DNNs) are a vital tool in pattern recognition and Machine Learning (ML) – solving a wide variety of problems in domains such as image classification, object detection, and speech processing. With the surge in the availability of cheap computation and memory resources, DNNs have grown both in architectural and computational complexity. Porting DNNs to resource-constrained devices – such as commercial home appliances ...Master Thesis -
Real-time projected gradient based NMPC with an application to anesthesia control
(2020)Master Thesis -
Modellierung von Hangmuren in bewaldetem Gebiet mit dem Simulationsprogramm RAMMS
(2020)Master Thesis -
Applying Machine Learning to Detect and Enhance Fractures from GPR-reflection data
(2020)The recent demand for renewable energies has sparked interest in geothermal energy in Switzerland. In order to have the most efficient energy transition possible, knowledge of the environment where this type of energy can be extracted is needed. The Bedretto Underground Laboratory for Geo-Energies (BULG) provides such an environment, consisting of crystalline rock masses with fractures and faults. These fractures and faults are the primary ...Master Thesis