document

Dynamic Target Time Management with Reinforcement Learning: A case study on Zurich short-haul regulated arrivals

Caranti, Leonardo (author)

This Master Thesis investigates the possible improvements to the Target Time Management concept to optimize the arrival flows for SWISS International Airlines. The aim is to improve operational performance based on the current model used, as well as prove that Target Time Management constitutes a valuable system to improve operations in a...

master thesis 2024

document

Data-driven optimal control for safe quadrotor navigation in windy environments

Probst, Johanna (author)

Creating autonomous Micro Aerial Vehicles for executing complex missions poses various challenges, including safe navigation in the presence of external wind disturbances. Most current navigation methods handle external wind disturbances through real-time estimation and rejection algorithms in the control stage, but lack safety guarantees in...

master thesis 2023

document

All-at-once optimization for kernel machines with canonical polyadic decompositions: Enabling large scale learning for kernel machines

van Mourik, Ewoud (author)

This thesis studies the Canonical Polyadic Decomposition (CPD) constrained kernel machine for large scale learning, i.e. learning with a large number of samples. The kernel machine optimization problem is solved in the primal space, such that the complexity of the problem scales linearly in the number of samples as opposed to scaling cubically...

master thesis 2022

document

Online Surrogate Models for the Constrained Optimization of Interplanetary Low-Thrust Trajectories

Andrade Castanheira, Francisco (author)

The optimization of interplanetary, low-­thrust trajectories is a computationally expensive aspect of preliminary mission design. To reduce the computational burden associated with it, surrogate models can be used as cheap approximations of the original fitness function. Training the surrogate models in a fully online manner can be done to...

master thesis 2022

document

Topology Optimization and Physics-Informed Neural Networks for Metamaterial Optics Design

Everingham, Dylan (author)

The development of optical metamaterials in recent years has enabled the design of novel optical devices with exciting properties and applications ranging across many fields, including in scientific instrumentation for space missions. This in<br/>turn has led to demand for computational methods which can produce efficient device designs....

master thesis 2022

document

Reduce model unfairness with maximal-correlation-based fairness optimization

Huang, Wenxuan (author)

Supervised machine learning is a growing assistive framework for professional decision-making. Yet bias that causes unfair discrimination has already been presented in the datasets. This research proposes a method to reduce model unfairness during the machine learning training process without altering the sample value or the prediction value....

master thesis 2022

document

Integrating Predictive and Optimization Model for Intelligent Schedule Management based on Real Time ETA Information: A Concept of Machine Learning and Exact Solution in Petrochemical Loading Facility

Emanuel Febrianto Prakoso, Emanuel (author)

This study addresses the truck rescheduling problem as the consequence of uncertain arrival time. It proposes an integrated system of predictive model powered by machine learning algorithm and exact optimization model such that it is distinct from most existing literatures in this domain. The uncertainty of truck arrival time is captured as...

master thesis 2021

document

Principal Component hierarchy for sparse quadratic programs

Vreugdenhil, Robbie (author)

We propose a novel approximation hierarchy for cardinality-constrained, convex quadraticprograms that exploits the rank-dominating eigenvectors of the quadratic matrix. Each levelof approximation admits a min-max characterization whose objective function can be op-timized over the binary variables analytically, while preserving convexity in the...

master thesis 2021

document

Vortex-model-based Multi-objective Optimization of Winglets for Wind Turbines using Machine Learning

Leenders, Nick (author)

In order to reduce the levelised cost of energy, the rotors of wind turbines are increasing in size. To increase the energy yield, wind turbine rotors need to have an innovative tip design; such as winglets. Winglets are used widely in aircraft design; however, they remain mostly absent in state-of-the-art wind turbine design. The low-fidelity...

master thesis 2021

document

Machine learning to support cutting plane selection in two-stage robust optimization problems using a column-and-constraint-generation algorithm

van der Vlugt, Boaz (author)

The field of robust optimization deals with problems where uncertainty influences the optimal decision. Some of these problems can be formulated in a ‘two-stage’ formulation, such as the location transportation problem. To solve such a problem, a column-and-constraint-generation algorithm has been introduced in which constraints are iteratively...

bachelor thesis 2021

document

Devising Multivariate Splits for Optimal Decision Trees

Mălan, Abel (author)

Decision trees are often desirable for classification/regression tasks thanks to their human-friendly models. Unfortunately, the construction of decision trees is a hard problem which usually implies having to rely on imperfect heuristic methods. Advancements in algorithmics and hardware processing power have rendered globally optimal trees...

bachelor thesis 2021

document

Spatial configurations and learning rules impact on the evolution of cooperative behaviour in the n-person iterative prisoner’s dilemma

Gismondi, Roberta (author)

Decision-making dynamics and their impact of human behaviour have raised a large number of questions throughout the years. Traits like competition and collaboration amongst agents are often studied, in the context of Game Theory, by the medium of games such as the Iterative Prisoners’ Dilemma.Furthermore, many realistic scenarios and possible...

bachelor thesis 2021

document

Building Random Forests with Optimal Decision Trees

Molhoek, Jord (author)

Decision trees are most often made using the heuristic that a series of locally optimal decisions yields a good final decision tree. Optimal decision trees omit this heuristic and exhaustively search - with many optimization techniques - for the best possible tree. In addition, training an ensemble of decision trees with some randomness has...

bachelor thesis 2021

document

Learning based hardware-centric quantum circuit generation

Schalkers, Merel (author)

Large fault­tolerant universal gate quantum computers will provide a major speed­up to a variety of common computational problems. While such computers are years away, we currently have noisy intermediate­scale quantum (NISQ) computers at our disposal. In this project we present two quantum machine learning approaches that can be used to find...

master thesis 2021

document

Low-Thrust Interplanetary Trajectory Optimization Using Pre-Trained Artificial Neural Network Surrogates

Saz Ulibarrena, Veronica (author)

The use of low-thrust propulsion for interplanetary missions requires the implementation of new methods for the preliminary design of their trajectories. This thesis proposes a method using the Monotonic Basin Hopping global optimization algorithm to find feasible trajectories with optimum use of the mass of fuel for the case in which the...

master thesis 2021

document

Design of a reconfigurable metamaterial with the use of Bayesian optimization and machine learning

Kasprzyk, Szymon (author)

Metamaterials are a relatively new group of materials whose behaviour strongly depends on the design of their internal structure. They can be employed in a wide range of applications, one of which is presented in this thesis. As cardiovascular diseases account for around 30% of deaths worldwide the research done in the field of Materials Science...

master thesis 2020

document

An Investigation Into Predict-and-Optimize Machine Learning

Puppels, Thomas (author)

Predict-and-Optimize (PnO) is a relatively new machine learning paradigm that has attracted recent interest: it concerns the prediction of parameters that determine the value of solutions to an optimization problem, such that the optimizer ends up picking a good solution. Training estimators with standard loss functions like mean squared error...

master thesis 2020

document

MultiTune: Dynamic budget allocation for hyperparameter tuning

Dev, Shikhar (author)

Hyperparameter optimization(HPO) forms a critical aspect for machine learning applications to attain superior performance. BOHB (Bayesian Optimization and HyperBand) is a state of the art HPO algorithm that approaches HPO in a multi-armed bandit strategy, augmented with Bayesian optimization to drive configuration sampling. However, BOHB...

master thesis 2020

document

Deepification: Learning Variable Ordering Heuristics in Constraint Optimization Problems

Doolaard, F.P. (author)

Constraint programming is a paradigm for solving combinatorial problems by checking whether constraints are satisfied in a constraint satisfaction problem or by optimizing an objective in a constraint optimization problem. To find solutions, the solver needs to find a variable and value ordering. Numerous heuristics designed by human experts...

master thesis 2020

document

Humble Giants: Computational Intelligence for Designing More Sustainable High-rise Buildings using Surrogate Models

Fortich Mora, Fredy (author)

As urbanization increases around the world, high-rise buildings will continue to become a more prevailing typology, nonetheless, due in part to cumbersome computational simulations, rarely do designers have enough information during the early stages of design, which is the time when their choices affect the most the efficiency of their building....

master thesis 2020