Keeping people with dementia and family members involved in the storytelling process

By Diana-Otilia Sutac

Evaluating Data Bias and User Enjoyment in the Full System

By Konstantin Teplykh

Designing a simple interface, suitable for People with Dementia

By Luminița Nițescu

Enhancing Collaborative Storytelling for People with Dementia through AI-Based Media Generation

By Rares Burghelea

Activity detection from in-mouth sensors

Supervisors: Przemysław Pawełczak, Vivian Dsouza

Detection of Bruxism Using Data From an In-Mouth Accelerometer

By Floris van de Voorn

Intraoral Microelectronics for Hydration Monitoring in Dental Hygiene

By Jenna Bonke

Using in-mouth sensor measurement data to estimate breathing rate

By Konstantinos Stergiou

Voice Activity Detection and Keyword Classification using Data from the Intraoral Densor Sensing Platform

By Nathan Klumpenaar

Algorithms and Applications for Optimal Decision Trees

Supervisors: Emir Demirović, Koos van der Linden

AnyDTree: An Anytime Algorithm for Perfect Decision Trees

By Iulia Hosu

Finding Robust Optimal Regression Trees Using Exhaustive Search

By Jesse Vleeschdraager

The Search for Optimal Robust Classification Trees

By Kutlu Şan Demirören

Algorithm Selection with Continuous Feature Optimal Decision Trees

By Saunaq Chakrabarty

Algorithms for dynamic scheduling in manufacturing, towards digital factories

Supervisors: Mathijs de Weerdt, Léon Planken, Kim van den Houten

Evaluating Proactive, Reactive, and Hybrid Strategies for the Stochastic Multi-Mode RCPSP with Hard Deadlines

By Andreas Shiamishis

Algorithms for dynamic scheduling in manufacturing, towards digital factories

By Bogdan Paramon

Algorithms for Dynamic Scheduling in Manufacturing Towards Digital Factories

By Ioan Hedea

Evaluating Dynamic Scheduling Strategies for a Multi-Mode RCPSP/max Problems with generalised time-lags/no-wait constraints

By Jeffrey Meerovici Goryn

Algorithms for Scheduling under Uncertainty

By Mayte Steeghs

Analyze the Impact of Development and Build Strategies on Performance Metrics in Different CI Open-Source Projects

Supervisors: Sebastian Proksch, Shujun Huang

Evaluating the Impact of Collaboration Modes on Software Delivery Efficiency in Open-Source Projects

By Atanas Buntov

Analyzing the Impact of Documentation on Performance Metrics in Different Continuous Integration Open-Source Projects

By Daniel Rachev

CI told you: Exploring the role of testing strategies as part of CI pipelines and their impact on DevOp metrics in Open Source projects.

By Kiril Panayotov

Evolution of CI Pipeline Complexity: Impact on Build Performance

By Kwangjin Lee

The impact of branching and merging strategies on KPIs in open-source software

By Serban Ungureanu

Analyzing bottlenecks and limitations in the efficiency and performance of Genetic Algorithms that solve the Global Geometry Optimization Problem

Supervisors: Peter A.N. Bosman, Anton Bouter, Vanessa Volz

Genetic Algorithms for Solving the Global Geometry Optimization Problem: Evaluating Initialization and Crossover Strategies for Lennard-Jones Cluster Optimization

By Emīls Dzintars

Dynamic Mutation Rate Control for the Genetic Algorithm for Global Geometry Optimization

By Jacek Kulik

Efficient Utilization of Local Optimization Methods and Strategies in Local Search Genetic Algorithms for Lennard Jones Clusters

By Kaloyan Yanchev

Analyzing The Impact of Mutations on Genetic Algorithms for Finding the Lowest Energy Structure of Atomic Clusters

By Stefan Bud

Annotation Practices in Societally Impactful Machine Learning Applications: What are these automated systems actually trained on?

Supervisors: Cynthia Liem, Andrew Demetriou

Benchmark Blindspots: A systematic audit of documentation decay in TPAMI’s∗datasets

By Alex Despan

Dataset quality within a societally impactful machine learning domain

By Alexandru Fazakas

Behind the Labels: Transparency Pitfalls in Annotation Practices for Societally Impactful ML

By Claudia Scorţia

Annotation Practices in Societally Impactful Machine Learning Applications

By Damjan Košutić

Annotation Practices in Societally Impactful Machine Learning Applications

By Simona Lupşa

Auditory Kernels for Representing Speech

Supervisors: Dimme de Groot, Jorge Martinez

Efficient Auditory Coding for Bat Vocalizations

By Aleksandra Savova

Auditory Kernels for Representing Degraded Speech

By Baturalp Karslioglu

Benchmarking Geo-distributed Databases

Supervisors: Oto Mráz, Asterios Katsifodimos

Benchmarking Geo-distributed Databases: Evaluation using the DeathStar hotel reservation benchmark

By Aidan Eickhoff

Benchmarking Geo-distributed Databases: Evaluating Performance using the Product-Parts-Supplier Workload

By Eduard-Alex Mihai

Benchmarking geo-distributed databases: Evaluation using the SmallBank benchmark

By Filip-Andrei Cirtog

DeathStar Movie for Geo-Distributed Databases

By Samuel van den Houten

MovR as a Benchmark for Geo-Distributed Databases

By Wilhelm Marcu

Causal Machine Learning

Supervisors: Jesse Krijthe, Rickard Karlsson

Robust Causal Inference with Multi-task Gaussian Processes

By Logan Ritter

Empirical Study on the Impact of Network Architecture on Causal Effect Estimation with TARNet

By Monika Witczak

When causal forests mislead

By Rares Iordan

Analyzing the Impact of Depth and Leaf Size on CATE Estimation in Honest Causal Trees

By Rheea-Maria Prodan

Evaluating the Robustness of Interventional Normalizing Flows under Nuisance Misspecification

By Ruthvik Allu

Classification of Alzheimer’s disease by linking single-cell and spatial data

Supervisors: Marcel Reinders, Timo Verlaan, Roy Lardenoije, Gerard Bouland

Researching the cell – amyloid plaque relationship in Alzheimer’s disease

By Dimitar Smenovski

Predicting Proximity to Pathology for Single-Cell Data in Alzheimer’s Disease

By Galya Vergieva

Exploring the latent space learned by scRNA-seq foundation models to identify AD subtypes

By Ísak Jónsson

Incorporating multi-omics for Alzheimer’s Disease predictions

By James Lee

A Multi Task Learning approach to classifying the severity of Alzheimer’s disease using single-cell gene expression data

By Willem Dieleman

Create your own blockchain

Supervisors: Johan Pouwelse, Bulat Nasrulin

TrustChain for Smartphones: Measuring reconnection latency when the network is interrupted

By Alexandra Nicola

Scaling TrustChain to One Million Blocks on Mobile Devices

By Michiel Bakker

Communication Protocol Impact on Energy Efficiency of Blockchain Application

By Tomasz Puczel

Throughput Analysis of a Trustchain Protocol Implementation

By Tudor Chirilă

Trustchain Mobile: A Low-Latency Smartphone Peer-to-Peer Transaction System

By Vlad-George Iftode

Data hound: analyzing smells in large code datasets

Supervisors: Arie van Deursen, Maliheh Izadi, Jonathan Katzy, Razvan Mihai Popescu

Data hound: Analysing non-English data smells in large code datasets

By Bogdan-Mihai Buzatu

Data Hound: Linking Educational Value to LLM Code Completion Performance During Inference

By Boris Annink

Analyzing the Impact of Self-Admitted Technical Debt on the Code Completion Performance of Large Language Models

By Lucas Witte

Data Hound: Analyzing Boilerplate Code Data Smell on Large Code Datasets

By Stefan Minkov

Deciphering Cancer Heterogeneity with Machine Learning

Supervisors: Joana de Pinho Gonçalves, Sara Costa, Ivan Stresec

Learning Signature Exposures from Gene Expression at Single-Cell Resolution: Regular vs. Multitask Learning of Individual Regression Models

By Ariel Potolski Eilat

Comparing De Novo and COSMIC Mutational Signatures in Single-Cell Sequencing Data

By Fedde de Haas

Deciphering Cancer Heterogeneity with Machine Learning - Signature fitting analysis on single cells in relation to pseudo-bulk data

By Raul Rotar

Robustness of Fitted Mutational Signature Exposures in Single-Cell Data

By Rebecca Nys

Multivariate Correlation of Mutational Signature Exposures and Gene Expression in Single-cell Breast Cancer

By Traian Dobrin

Deep Learning Methods for Denoising Microscopy Images in Voltage Imaging Videos

Supervisors: Alejandro Castañeda Garcia, Nergis Tömen

Benchmarking Self-supervised Learning for Denoising Voltage Imaging Data

By Ioan Leolea

Comparing deep learning and traditional denoising methods for voltage imaging

By Jan Willem Eriks

Evaluating established denoising methods for voltage imaging: Comparison of SUPPORT, DeepCAD-RT, and PMD when applied to voltage imaging data

By Jiayi Wang

Denoising Microscopy Images in Voltage Imaging Videos

By Radoslaw Majer

Ensemble techniques for (P)DFA learning

Supervisors: Sicco Verwer, Simon Dieck

Diversity-Driven Ensemble Learning with the Alergia Algorithm

By Błażej Łytkowski

DFA Ensembles without suitablity metrics

By Georgios Tsampikos Kontos

Adapting the EDSM Algorithm for Ensemble Learning: A Machine Learning Approach to DFA Inference

By Radu-Cosmin Dumitru

Effect of changing the sequence orders on DFA ensembles learned via EDSM

By Wiktor Cupiał

Evaluating and Improving Robustness in Sequential/Temporal Domains

Supervisors: Mustafa Celikok, Frans Oliehoek

Evaluating the Robustness of DQN and QR-DQN in Traffic Simulation

By Cristian Toadere

Evaluating the Robustness of SAC under Distributional Shifts in Driving Domain

By Lazar Polovina

Evaluating and Enhancing the Robustness of Proximal Policy Optimization to Test-Time Corruptions in Sequential Domains

By Mate Rodić

Detecting Environment Changes via Quantile Spread in Quantile Regression Deep-Q Networks

By Paul-Gabriel Stan

Evaluating the robustness of DQN and QR-DQN under domain randomization

By Youri Zwetsloot

Explainable Fact-Checking with LLMs

Supervisors: Shubhalaxmi Mukherjee, Pradeep Murukannaiah

Evaluating Faithfulness of LLM Generated Explanations for Claims: Are Current Metrics Effective?

By Borislav Marinov

Explainable Fact-Checking with Large Language Models

By Marina Serafeimidi

Explainable Fact-Checking with LLMs

By Matei Bordea

Explaining Cricket Shot Techniques Using Pose Estimation with Explainable AI

Supervisors: Ujwal Gadiraju, Danning Zhan

Generating Expertise-Specific Explanations in Cricket Pose Estimation

By Ansh Kumar

Adapting Explainable AI methods for multi-target tasks

By Atanas Semov

Explaining Cricket Shot Techniques with Explainable AI

By Bruno Martinović

What pose estimation methods are most effective for analyzing cricket shots?

By Daniel Plevier

Presenting XAI-generated Explanations Of Cricket Shots

By Gido Vitner

Exploring the Vulnerability of Deep Regression Models to Backdoor Attacks

Supervisors: Lingyu Du, Guohao Lan

Backdoor attacks on deep regresion models: BadNet attacks on Headpose estimation models

By Bart Coster

Backdoor Attacks on 3D Gaze Estimation Models: When BadNets Meet Your Eyes: Data Poisoning in Deep Regression

By E LS

Full Image Backdoor Attacks on Gaze Estimation Networks: A Study on Regression Vulnerabilities

By Mateusz Surdykowski

Manipulating Head Pose Estimation Models: Exploring Deep Regression Models’ Vulnerability to Full Image Backdoor Attacks

By Petra Gulyás

Extending WaNet Attacks to Regression models, a case study on head pose estimation models

By Saïd-Ahmed Koudjeti

Extending Measures of Rank Similarity

Supervisors: Julián Urbano

Extending rank correlation coefficients to relevance profiles

By Andrea Vezzuto

Quantifying Uncertainty in Rank Correlation Coefficients

By Andreas Tsatsanis

A Probabilistic Account of the Uncertainty Due to Ties in Rank-Biased Overlap

By Lukáš Chladek

The Definition of a New Correlation Variant for Rankings With Ties

By Mikołaj Gazeel

Extending Rank-Biased Overlap (RBO) to Relevance Profiles

By Thijs Houben

Fairness and Bias in Recommender Systems

Supervisors: Masoud Mansoury

Fairness and Bias in Recommender Systems: To what extent do content-based recommendation models suffer from unfairness, and how does this differ from collaborative filtering?

By Filip Angheluta

The Effects of Debiasing Methods on the Fairness and Accuracy of Recommender Systems

By Filip Čajági

Fairness in Collaborative Filtering Recommender Systems: A Comparative Analysis of Trade-offs Across Model Architectures

By Jeeyoon Kang

How effective are current fairness intervention methods in addressing unfairness in recommendation systems, and what trade-offs do they introduce in terms of accuracy?

By Jiaqing Huang

Alleviating the unfairness issue with knowledge-aware recommendation models

By Yoan Popov

Graph Learning on Tabular Data

Supervisors: Kubilay Atasu, Cagri Bilgi

Graph Learning on Tabular Data: Think Global And Local

By Andrei Stefan

Relational Deep Learning with Graph Transformers: Exploring Local and Global Message Passing

By Ignacio Cuñado Barral

Hybrid Graph Representation Learning for Money Laundering Detection

By Marius Frija

Exploring the benefits of Graph Transformers in Relational Deep Learning

By Rafael Alani

Graph Learning on Financial Tabular Data: Cascade and Interleaved architectures using GNNs and Transformers

By Sorin Enachioiu

High-Dimensional Data Visualization via Sampling-Based Approaches

Supervisors: Martin Skrodzki, Klaus Hildebrandt

Exploring the computational feasibility limits of perplexity in t-SNE for scenarios of limited working memory

By Dimitar Netzov

Sample-Based t-SNE Embeddings: How different Sampling Strategies influence the Quality of Low-Dimensional Embeddings

By Em Ketterer

Improving Sampling-Based t-SNE Performance Using Dijkstra's Algorithm for Approximate Distance Computation

By Filip Markov

High-Dimensional Data Visualisation via Sample-Based approaches: the effect of perplexity at different levels of sample-based approach

By Muhammad Arslan Bhatti

Measurement of structural similarity between different embeddings as a way of predicting a suitable perplexity

By Radu-Marius Chiriac

How Much Data is Enough? Modelling Learning Curves by Neural Networks

Supervisors: Tom Viering, Cheng Yan, Sayak Mukherjee

Extrapolating Learning Curves: When Do Neural Networks Outperform Parametric Models?

By Adelina Cazacu

The Impact of Imbalanced Training Data on Learning Curve Prior-Fitted Networks

By Bozhidar Kostov

The Effect of Domain Shift on Learning Curve Extrapolation

By Max Soeters

How Noisy Is Too Noisy? Robust Extrapolation of Learning Curves with LC-PFN

By Razvan Marian Gherasa

Effectiveness of Machine Learning Models in Classifying Learners Based on Learning Curves

By Sinan Başaran Karaarslan

How to compute on encrypted data

Supervisors: Lilika Markatou

Computing with Fully Homomorphic Encryption

By Alexandru-Eugen Bulboacă

An analysis of Structured Encryption compared to other secure computation technologies

By Dorian Herbiet

Secure Multi-party Computation: A Survey

By Pedro Gomes Moreira

A Comparative Study of Privacy-Preserving Computation Techniques

By Sergiu-Nicolae Stancu

Computation Capabilities of Server-Side Trusted Execution Environments

By Vlad-Ștefan Popescu

Implementation and Verification of Algorithms

Supervisors: Benedikt Ahrens, Kobe Wullaert

Assessing Formal Verification in SPARK

By Dinu Blanovschi

Exploring the program verifier Dafny that can compile to other languages

By Jeroen Koelewijn

Why3 and Proving A* Automatically

By Kajetan Neumann

Exploring the Capabilities and Limitations of Algorithm Verification in Vampire

By Mohammed Balfakeih

Locking Bugs Out with KeY

By Tejas Kochar

Improving the Flexibility of Energy System Optimization Models

Supervisors: Germán Morales España, Maaike Elgersma

Effect of Minimum Up and Down Time Constraints with Fully Flexible Temporal Resolutions

By Gabriel Tertelici

Start-Up and Shut-Down Capabilities in Unit Commitment Model with Fully Flexible Temporal Resolution

By Karol Sperczyński

Start-up and Shut-down Capabilities in an Energy System Optimization Model with Flexible Temporal Resolution

By Rūta Giedrytė

Start-Up and Shut-Down Costs in an Energy System Optimisation Model with Fully Flexible Temporal Resolutions

By Uroš Gluščević

Start-up and Shut-down Trajectory Constraints in an Energy System Optimisation Model with Fully-Flexible Temporal Resolution

By Yurian Lagrand

Interpretable reinforcement learning policies using decision trees

Supervisors: Anna Lukina, Daniël Vos

SPLIT-PO: Sparse Piecewise-Linear Interpretable Tree Policy Optimization

By Ernesto Hellouin de Menibus

Discretising Continuous Action Spaces for Optimal Decision Trees

By Mart van der Kuil

Interpretable Reinforcement Learning for Continuous Action Environments

By Misha Kaptein

Decision Trees vs. Ensembles in Regression-Based Offline RL

By Rareş Polenciuc

Imitation learning from neural networks with continuous action spaces using regression trees

By Tymon Cichocki

Looking deeper into the dependency management practices of developers

Supervisors: Sebastian Proksch, Cathrine Paulsen

Motivating Version Range Adoption in Maven Through Quantified Trust

By Gijs Hoedemaker

A Study into the Use of Version Locking in Gradle Projects

By Joppe Boerop

An Empirical Study of Version Conflicts in Maven-Based Java Projects

By Valentin Mihăilă

Dependency Families in the Maven Ecosystem: An Analysis of Software Dependency Graphs

By Wojciech Graj

Machine Learning and Statistical Analysis of Biological Data to Understand Mechanisms of Aging

Supervisors: Marcel Reinders, Bram Pronk, Inez den Hond, Gerard Bouland

Improving and Interpreting Epigenetic Age Predictors

By Elena Langens

Improving Single-Cell Transcriptomic Aging Clocks

By Klara Hirmanová

Can We Use Physical Characteristics of Genes to Predict Age-Related Changes in Expression?

By Lovre Mlikotić

Performing Gene-Gene Correlation Analysis Across Three Human Age Groups to Improve Biological Age Prediction Models

By Tycho Grapendaal

Improving Single-Cell Transcriptomic Aging Clocks: Enhancing Accuracy and Biological Interpretability

By Vlad Alexan

Machine Learning for humanitarian forecasting: a survey

Supervisors: Marijn Roelvink, Cynthia Liem

Assessing the trustworthiness and real-world feasibility of machine learning models for conflict forecasting

By Alexia-Iustina Gavrilă

Performance and Feasibility of Machine Learning for Multi-hazard Humanitarian Forecasting: A literature survey

By Ewa Smura

Impact-based humanitarian forecasting using machine learning for floods

By Leonardo Marcuzzi

How well can machine learning tools for humanitarian forecasting be used in predicting the consequences of forced displacement?

By Lia Petrova

What are the areas of improvement for data available for the development of disease outbreak forecasting ML models?

By Matej Bavec

Maintaining Plasticity for Deep Continual Learning

Supervisors: Wendelin Böhmer, Laurens Engwegen

Analyzing Plasticity Through Utility Scores

By Aldas Lenkšas

Layerwise Perspective into Continual Backpropagation: Replacing the First Layer is All You Need

By Augustinas Jučas

Evaluating Catastrophic Forgetting in Neural Networks Trained with Continual Backpropagation

By Justinas Jučas

Exploring Alternatives to Full Neuron Reset for Maintaining Plasticity in Continual Backpropagation

By Urte Urbonavičiūtė

Activation Function-Adapted Parameter Resetting Approaches

By Victor Purice

Making sense of emotions: how to gain and visualize mental health insights from self-report data?

Supervisors: Esra de Groot, Willem-Paul Brinkman

Deriving and Presenting Insights from Experience Sampling Method (ESM) Data Through Network Visualization

By Adam Gajdoš

Visualizing Experience Sampling Data to Enhance Clinical Insights into Mental Resilience

By Antreas Economides

Visualizing ESM Data to Support Mental Health Symptom Identification and Intervention Planning

By Cristiana Cotoi

Visualizing Self-Report Data for Clinical Insight: Practitioner Perspectives on ESM Feedback for Assessing Therapy Effectiveness

By Jules Savelkoul

Gaining and Visualizing Mental Health Insights from Self-Report Data: Presentation of Insights from ESM Data into Client Conditions for Practitioners

By Kasper van Maasdam

Methods for the acceleration of realistic rendering

Supervisors: Elmar Eisemann, Michael Weinmann, Christoph Peters

Perception-based Optimization of Wavelength Sampling Distributions for Spectral Rendering

By Camil-Cristian Dobos

Subpixel level Pathtracing

By Jan de Munck

A Better Light Candidate Generation Algorithm for ReSTIR Ray Tracing Using an Acceleration Structure to Identify Relevant Lights

By Rafayel Gardishyan

Global Illumination using ReSTIR DI and Photon-Mapped Virtual Point Lights: An improvement on Instant Radiosity

By Samuel Bruin

Worldspace ReSTIR for direct illumination

By Vlad Ştefănescu

Modeling decision making in cognitive architectures (literature survey)

Supervisors: Bernd Dudzik, Chenxu Hao

Modeling decision making in cognitive architectures

By Bora Goral

Modeling Episodic Memory in Cognitive Architectures: A Comparative Study of Soar and Xapagy

By Hai Xie

ACT-R in the military: a systematic review

By Veerle Loykens

An Analysis of ACT-R and CLARION Representing Heuristic Strategies for Consumer Decision-Making

By Willem van de Sanden

How suited are cognitive architectures for implementing moral reasoning? – a Systematic Literature Review

By Wojciech Hajdas

Modelling cyclic structures in Agda

Supervisors: Jesper Cockx, Bohdan Liesnikov

Modelling cyclic structures in Agda

By Călin-Marian Diacicov

Stuck in a (While) Loop

By Claire Stokka

Modelling cyclic structures in Agda

By Faizel Mangroe

Encoding Finite State Automata in Agda using coinduction

By Noky Soekarman

Productively recursing infinitely

By Sarah van de Noort

Multi-Layered Telemetry Assessing Global Performance of LEO Internet Providers (e.g. Starlink)

Supervisors: Nitinder Mohan, Tanya Shreedhar

The Influence of Ground Infrastructure Proximity on Starlinks Performance: A Novel Method to Unravel Starlinks Network Routing

By Christiaan Baraya

Capturing the Spatiotemporal Dynamics of LEO ISP Performance

By Cristian Benghe

Multi-Layered Telemetry Assessing Global Performance of LEO Internet Providers: Enhancing LEO Internet Providers Telemetry with User-Initiated Active Measurements

By Janusz Urbański

Towards a Global Telemetry System for Evaluating LEO ISP Performance

By Vlad-Ștefan Graure

Multimodal Machine Learning Techniques for Analyzing Laughter and Drinking in Spontaneous Social Encounters

Supervisors: Hayley Hung, Litian Li, Stephanie Tan

The Data Barrier to Lightweight Drinking Detection

By Joelle Tijssens

Laughter Accelerometer-Based Detection in Natural Social Interactions

By Luka Orbovic

Detecting Drinking Behavior in Social Settings Using Chest-Mounted Accelerometer Data

By Thomas Baeten

Laughter in Motion: Pose-Based Detection Across Annotation Modalities in Natural Social Interactions

By Vassil Guenov

Music Recommender Systems and Children

Supervisors: Sole Pera, Robin Ungruh

Analyzing the Impact of Acoustic Features on Music Recommendation for Children Across Age Groups

By Erkin Basol

Young Minds and Popular Charts : An empirical study on the mainstream music consumption of children

By Francisco Deque de Morais Amaro

From Beats to Being: Using adolescents’ listening data to identify developmental trajectories

By Max Lauf

From Hook to Chorus: Analyzing the relation between song structure and music listening behavior of children

By Sander Bakker

How demographic features impact the accuracy of recommendations

By Teun Bosch

Network anonymization for science

Supervisors: Anna Latour

A Constraint Programming Approach to Optimal Network Anonymization

By Andrei Ionita

Network Anonymization for Science: A Simulated Annealing Approach

By Elena-Denisa Arsene

A Pseudo-Boolean Approach to Full Graph Anonymisation

By Emke de Groot

Network Anonymisation for Science: Improving (n,m)-greedy Edge deletion anonymisation using global heuristic

By Jakub Matyja

Comparative analysis of two network anonymization settings using Integer Linear Programming

By Mike Erkemeij

Noisy Byzantine Agreement in a Small Quantum Network

Supervisors: Tim Coopmans

Noisy Byzantine Agreement in Quantum Networks: Impact of Gate Errors on a Weak Broadcast Protocol

By Alexandru-Andrei Cirjaliu-Davidescu

Noisy Byzantine Agreement Protocol in a Small Quantum Network: The Failure Probability of the Protocol Under Leakage Errors

By Ayse Idil Evci

Evaluating the Impact of Gate Errors on a Quantum-Aided Byzantine Agreement Protocol

By Jerzy Ksawery Wierzbicki

Effect of measurement errors on the failure probability of quantum-aided Byzantine agreement

By Kimon Kyparos

Quantum Byzantine Agreement Protocol Under Noisy Conditions: Evaluating the Impact of Qubit Decoherence on the Protocol’s Success Rate

By Prisha Meswani

Online Search and Children

Supervisors: Sole Pera, Hrishita Chakrabarti, Catholijn Jonker

The Quest to Improve Online Search

By Alexandra Darie

QuickFix: A Multi-step Query Reformulation Method For Children’s Online Search Queries

By Atilla Colak

Persona-Based Prompting: Enhancing Readability and Understanding in AI Responses for children

By Jordano de Castro

Enhancing Children’s Web Searches through Age-Specific Vocabulary Reformulation

By Rembrandt Hazeleger

Pixel Art 2.0

Supervisors: Elmar Eisemann, Petr Kellnhofer, Mathijs Molenaar

Procedural texturing for pixel art: Making pixel art resemble real materials

By Francisco Cunha

Pixel Art Vectorization with Gradients

By Kaldis Berzins

Automating Color Ramp Detection and Modification to Enhance Pixel Art

By Lenka Hake

Pixel Fixer: Semi-Automated Techniques for Correcting Pixel Art

By Rares Bites

How Can We convert 2D Pixel Art into a 3D Voxel Representation: Exploring different 3D reconstruction algorithms on 2D pixel input

By Tihana Krajtmajer

Privacy-Preserving Data Analytics

Supervisors: Roland Kromes, Zeki Erkin

Privacy-Preserving Data Analytics: What are the financial costs associated with the use of Homomorphic Encryption for privacy-preserving data analytics?

By Ivan Moreno Sarries

Quantum SMPC: Rich in theory, limited in practice: A systematic review of quantum secure multi-party computation

By Nicoleta Dobrică

Google DP vs. OpenDP: Empirical Comparison of Differential Privacy Libraries

By Stilyan Penchev

FATE vs. SecretFlow: A Practical Comparison for Privacy-Preserving Machine Learning

By Vlad Ionita

Comparing Differential Privacy in Practice: A Cross-Domain Analysis of Differentially Private-Offsite Prompt Tuning and Google's Differential Privacy Library

By Yurui Zheng

Programming Language Tooling for Hylo

Supervisors: Andreea Costea, Jaro Reinders

High-Fidelity C Interoperability in Hylo: A Principled Design for Safe and Idiomatic C Bindings

By Ambrus Tóth

Programming Language Tooling for Hylo: Incremental Compilation and Analysis

By Dobrin Bashev

Debugging Hylo: Providing Debugging Support to a Modern, Natively-Compiled Programming Language

By Tudor-Stefan Magirescu

Error-Tolerant Parsing and Compilation for Hylo: Enabling Interactive Development

By Viktor Sersik

Propagators for Constraint Programming

Supervisors: Emir Demirović, Imko Marijnissen

Propagators for Constraint Programming Energetic Reasoning

By Konstantin Kamenov

Explaining detectable precedences for the disjunctive constraint

By Matthias van Vliet

Evaluating the Impact of Explanations on the Performance of an Edge-Finding Propagator

By Radu Andrei Vasile

More general explanations for the Not-First/Not-Last propagators

By Yousef El Bakri

Property-Based Testing in the Wild!

Supervisors: Sára Juhošová, Andreea Costea

Property-Based Testing in Open-Source Rust Projects: A Case Study of the proptest Crate

By Antonios Barotsis

Property-Based Testing in Practice using Hypothesis: In-depth study on how developers use Property-Based Testing in Python using Hypothesis

By David de Koning

Exploring Property-Based Testing in Java: An Analysis of jqwik Usage in Open-Source Repositories

By Harald Toth

Property-Based Testing in Rust, How is it Used?: A case study of the 'quickcheck' crate used in open source repositories

By Max Derbenwick

Property-Based Testing in Haskell: An Analysis of QuickCheck usage in Open-Source Haskell Projects

By Ye Zhao

Real World Evaluation of Optical Flow

Supervisors: Sander Gielisse, Jan van Gemert

Performance of Optical Flow Models on Real-World Occluded Regions

By Iris Petre

Real-world evaluation of Optical Flow on repetitive patterns

By Jesse Klijnsma

Bridging the Gap: A Real-World Dataset and Evaluation of Optical Flow Models in Large Displacement Scenarios

By Marijn Timmerije

Going Against the Flow

By Sachhyam Dahal

Real-World Evaluation of Optical Flow with Varying Lighting Conditions

By Zhuoyue Ge

Recommender Systems via Covariance Neural Networks

Supervisors: Elvin Isufi, Andrea Cavallo, Chengen Liu

Beyond-Accuracy (Sparsed-) coVaraince Neural Network Recommender Systems

By Ivan Bozhanin

Evaluating the performance of sparsified precision VNNs as a graph collaborative filter

By Jort Boon

How does sparsification affect the performance of covariance VNNs as graph collaborative filters?

By Martin Angelov

Performance of Covariance Neural Networks on Rating Prediction

By Timothy Axel

Recommender systems via Covariance Neural Networks: Using precision matrices as Graph Collaborative Filter

By Vic Vansteelant

Robust Decentralized Learning

Supervisors: Jérémie Decouchant, Bart Cox

Dynamic Topology Optimization for Non-IID Data in Decentralized Learning

By Antreas Ioannou

Byzantine Attacks and Defenses in Decentralized Learning Systems that Exchange Chunked Models

By Atanas Donev

Privacy Attacks on Decentralized Learning Systems that Exchange Chunked Models

By Halil Betmezoğlu

Persistence of Member Contribution Under Churn

By Luka Roginić

Client-Level Unlearning in Decentralized Learning

By Razvan Dinu

Robust Planning as Probabilistic Inference

Supervisors: Issa Hanou, Reuben Gardos Reid, Sebastijan Dumančić

Robust Planning for Sokoban with Probabilistic Inference

By Daniël 't Mannetje

Creating Robust Train Unit Shunting Plans using Probabilistic Programming

By Job van Zwienen

Finding Robust Schedules in the Stochastic Resource Constrained Project

By Kasper van Duijne

Robust Plan Inference in the Keys and Doors Problem

By Koen van der Knaap

Creating robust plans for the Minecraft planner of the PDDL Gym library using Probablistisitic Inference

By Matthijs Bonke

Scalable Structural Code Diffs

Supervisors: Quentin Le Dilavrec, Carolin Brandt

Efficiently Optimizing Hyperparameters for the Gumtree Hybrid Code Differencing Algorithm within HyperAST

By Alexander Nitters

Evaluating Stable Tree Differencing with Gumtree and HyperDiff

By Elias Hoste

Accelerating AST-Based Code Differencing - Optimizing ChangeDistiller’s Bottom-Up Matching Strategy with HyperAST

By Leo Mangold

Analyzing Iterative Improvements to Structural Code Diffs

By Maciej Mejer

Comparing Gumtree Greedy and Gumtree Simple adapted for scaling

By Ruben van Seventer

Self-supervised feature learning for diagnosing hip osteoarthritis in X-ray images

Supervisors: Gijs van Tulder, Jesse Krijthe

Evaluating the Value of Longitudinal Hip Radiographs in Self-Supervised Pretraining for Osteoarthritis Classification

By Dimana Stoyanova

Anatomy-Aware Masked Autoencoders for Hip Osteoarthritis Classification in X-ray Images

By Jasper van Beusekom

How effectively can a VAE's latent space reflect osteoarthritis severity and enable diagnostic accuracy under label scarcity and label noise?

By Poli Dimieva

Adversarial generative models applied to diagnosing Osteoarthritis

By Teun den Boer

Anatomy-aware data augmentation techniques in contrastive self-supervised learning for diagnosing hip osteoarthritis in X-ray images

By Zhenya Yancheva

Simulating and Analyzing the Performance of TCP Under Extreme Conditions

Supervisors: Fernando Kuipers, Adrian Zapletal

Impact of SDN-induced routing changes on TCP BBR

By Alexandru Șologon

Evaluating the Impact of L4S on TCP Performance

By Alexandru Tăbăcaru

Investigating the Impact of ACK Aggregation on TCP Performance using ns-3

By Hanna Heinczinger

Testing the impact of in-transmission bandwidth and delay variation on selected TCP variants

By Konrad Gniaz

An experimental evaluation of TCP startup algorithms

By Matei Grigore

Sparse Sequential Learning

Supervisors: Julia Olkhovskaia

Adaptive Feature Selection For Sparse Linear Bandits

By Martin Damyanov

Sparse Sequential Learning: Exploring Stochastic Contextual Linear Bandit and Feature Selection Combinations for Fixed Reduced Dimensions

By Vivek Kasyap Pasumarthi

Subspace Learning with Gaussian Processes for Sparse Contextual Bandits

By Yair Chizi

Surrogate Reloaded: Fast Testing for Deep Reinforcement Learning

Supervisors: Annibale Panichella, Antony Bartlett

XGBoost as a Surrogate Model for Testing Deep Reinforcement Learning Agents

By Aadesh Ramai

Surrogate Reloaded: Fast Testing for Deep Reinforcement Learning

By Leon Braszczyński

Surrogate Reloaded: Fast Testing for Deep Reinforcement Learning with Bayesian Neural Networks

By Rodrigo Montero González

Surrogate Reloaded: LSTM-Based Failure Prediction for Testing DRL Agents

By Steven van den Wildenberg

Surveying Usage of Cognitive-Affective Information in Adaptation for Intelligent Systems

Supervisors: Bernd Dudzik, Vandana Agarval

Towards Cognitively Aware Intelligent Systems: A Survey of Human Memory’s Role in Shaping Adaptation Mechanisms

By Daria Bucur

Surveying the Usage of Learning-Related Information in Adaptation for Intelligent Systems

By Mara Mih

Usage of Attention in Adaptation of Intelligent Systems

By Marie Louise Grundfør

Towards Emotionally and Motivationally Aware Intelligent Systems: A Systematic Literature Review

By Miruna Cosmina Negoițescu

Usage of Decision-Making and Reasoning Information in Adaptation for Intelligent Systems

By Pjotr Schram

Talking About Mental Health: Information Disclosure in User Interactions With Chatbots or mHealth Applications

Supervisors: Ujwal Gadiraju, Esra de Groot

The Impact of Empathetic Language on Willingness to Disclose Mental Health Related Information to a Chatbot

By Lina Sadoukri

Do Privacy Policies Matter? Investigating Self-Disclosure in Mental Health Chatbots

By Manu Gautam

Talking Like a Human: How Conversational Anthropomorphism Affects Self-Disclosure to Mental Health Chatbots

By Sagar Chethan Kumar

Designing Mental Health Chatbots: The Impact of Self-Disclosure Techniques on the User Disclosure

By Yushan Shan

The Guardians of the Ledger, Vol. 2

Supervisors: Dr. Burcu Kulahcioglu Ozkan, Dr. Mitchell Olsthoorn, Dr. Annibale Panichella

Hyperparameter-Tuned Randomized Testing for Byzantine Fault-Tolerance of the XRP Ledger Consensus Protocol

By Aiste Macijauskaite

Survival of the Fittest: Evaluating Fitness Functions for Concurrency Testing on the XRPL Consensus Protocol

By Atour Mousavi Gourabi

Groot: Impact of Evolutionary Operators in XRPL Testing using Priority-Based Event Representation

By Bryan Wassenaar

EvoPriority: Evaluating Fitness Functions in Priority-Based Evolutionary Testing for the XRP Ledger Consensus Protocol

By Călin Ciocănea

May the Delays Be Ever in Your Favor: Genetic Operators in Delay-Based Testing of the XRPL Consensus Algorithm

By Wishaal Kanhai

The Stability Gap in Continual Learning with Deep Neural Networks

Supervisors: Tom Viering, Gido van de Ven

Reaching for Resilience: Understanding How Optimizers Affect the Stability Gap in Continual Learning

By Chris Obis

I Fought the Low: Decreasing Stability Gap with Neuronal Decay

By Kirill Zhankov

Sharpness-Aware Optimization for Stability Gap Reduction

By Ksenia Sycheva

Mind the Gap: Layerwise Proximal Replay for Stable Continual Learning

By Oskar Hage

Stability Gap in Continual Learning: The Role of Learning Rate

By Paulina Sobocińska

The use of Reinforcement Learning in Algorithmic Trading

Supervisors: Amin Sharifi Kolarijani, Antonis Papapantoleon, Neil Yorke-Smith, Julia Olkhovskaya

Feature Engineering in Reinforcement Learning for Algorithmic Trading: Investigating the Effects of State Representation on Trading Agent Performance in the Forex Market

By Finn van Oosterhout

The use of Reinforcement Learning in Algorithmic Trading: What are the impacts of different possible reward functions on the ability of the RL model to learn, and the performance of the RL Model?

By Justas Bertasius

Effects of exploration-exploitation strategies in dynamic Forex markets: The use of Reinforcement Learning in Algorithmic Trading

By Radu Serban

The use of Reinforcement Learning in Algorithmic Trading: The Impact of Function Approximation Methods on Model Performance

By Robert Mertens

Transferable Reinforcement Learning in Forex Trading: Cross-Currency Adaptation Techniques for EUR/USD and GBP/USD

By Yavuz Hancer

Thematic Analysis of Online User Studies

Supervisors: Willem-Paul Brinkman, Reginald Lagendijk

How Ethical Perspectives Influence Smokers' Preferences for Time Allocation in Online Smoking Cessation Interventions

By Andreea Ţebrean

Understanding the Experiences of Smokers and Vapers with Preparatory Activities Suggested in a Digital Smoking Cessation Intervention

By Antonio Lupu

Interaction with Artificial Social Agents

By Celal Karakoç

Preparing to Quit: A Thematic Analysis of Smokers' engagement with Conversational Agent-Guided Activities in Online Cessation Interventions

By Jason Miao

Human Insight vs. Artificial Intelligence: A Thematic Analysis

By Keshav Nair

Tiny Machine Learning for Embedded Systems

Supervisors: Qing Wang, Ran Zhu

TinyML-Empowered Line Following for a Car Robot

By Adrien Carton

TinyML-Based Adaptive Speed Control for Car Robot: A Comparative Approach

By Alexandru Petriceanu

Real-Time Traffic Sign Recognition on Microcontrollers

By Aykut Emre Celen

TinyML-Empowered Indoor Positioning with Light: A Study on the Impact of LED Aging and Failure

By Joey Wenyi Li

TinyML-Empowered Indoor Positioning with Light: Model Optimization using Neural Architecture Search

By Neel Lodha

Tiny but Mighty: Distilling Large Models for Testing

Supervisors: Mitchell Olsthoorn, Annibale Panichella

Distilling CodeT5 for Efficient On-Device Test-Assertion Generation

By Andrei Nicula

Efficient Local Test Assertion Generation: Distilling CodeT5+ for Reduced Model Size and High Accuracy

By Di Wu

Creating Local LLMs for Test Assertion Generation: A Comparative Study of Knowledge Distillation from CodeT5

By Georgi Dimitrov

Closing the Gap: Java Test Assertion Generation via Knowledge Distillation with Trident Loss

By Jeroen Chu

Distilling Knowledge for Assertion Generation: Alpha-Temperature Tuning in Smaller Language Models

By Kristian Hristov

To deceit or self-deceit, that is the question!

Supervisors: Catholijn M. Jonker, J.D. Top

Detecting Patient Deception and Adherence in Diabetes Support Using AI-Generated Conversation Summaries

By Hugo Koot

Detecting Patient Information Conflicts through Conflict Reasoning in Knowledge Graphs

By Jochem van Paridon

To Deceive or Self-Deceive?

By Marina Mădăraș

Enhancing Diabetes Care through AI-Driven Lie Detection in a Diabetes Support System

By Renee van Westerlaak

Entropy-Based Modeling For Detecting Behavioral Anomalies in Users of a Diabetes Lifestyle Management Support System

By Sorin - Andrei Ciuntu

Towards Benchmarking the Robustness of Neuro-Symbolic Learning against Backdoor Attacks

Supervisors: Kaitai Liang, Andrea Agiollo

How Robust Is Neural-Symbolic Model Logic Tensor Networks Against Clean-Label Data Poisoning Backdoor Attacks?

By Andrei Chiru

Towards Benchmarking the Robustness of Neuro-Symbolic Learning against Backdoor Attacks

By Diego Becerra Merodio

Evaluating the Robustness of Neuro-Symbolic Networks Against Backdoor Threats with WaNet

By Francesco Hamar

Towards Benchmarking the Robustness of Neuro-Symbolic Learning against Backdoor Attacks

By Myriam Cristiana Guranda

The Effect of Adversarial Attacks on Neuro-Symbolic Reasoning Shortcuts

By Sophie (Schaaf) Langeveld

Traffic analysis and forecasting for adaptive network resource management in 5G/6G networks

Supervisors: Marco Colocrese, Nitinder Mohan

Adaptability and Latency in Network Reconfigurations of Virtualized Network Functions in 5G Networks

By Calin Georgescu

Synthetic 5G Traffic Generation - A Machine Learning Approach

By Karsten van der Deijl

Measuring resource consumption and latency in virtual environment

By Kevin Ji Shan

Comparison of machine learning models for predicting near-future traffic demands

By Oliwier Jurek

Characterizing traffic destinations and temporal trends for adaptive network resource management in 5G/6G networks

By Vlad Dragutoiu

Trustworthy Financial Crime Analytics

Supervisors: Zeki Erkin, Kubilay Atasu

Secure computation of fan-in and fan-out degree of nodes using additive homomorphic encryption

By Darius Eduard Floroiu

Collaborative Detection of Malicious Clients for Financial Institutions using Multi-Party Computation

By Lauren de Hoop

How money flow statistics can be used to detect money laundering activity in graph-based financial crime detection

By Luca-Serban Ionescu

The Impact of Realistic Laundering Subgraph Perturbations on Graph Neural Network Based Anti-Money Laundering Systems

By Tom Joshua Clark

Understanding Z3 Solver

Supervisors: Soham Chakraborty, Dennis Sprokholt

Evaluating Z3’s Performance on Real Number Constraints

By Dimitar Delov

Is solver guidance redundant for strong SMT implementations?

By Odysseas Machairas

Solving the Frobenius Problem in Z3: Exploring Quantifier Elimination

By Paul Anton

Understanding SMT Solvers: Exploring Parallelization in Floating-Point Problems

By Tristan Schmidt

Understanding Bit-vector Arithmetic in Z3

By Veselin Mitev

Unheard and Misunderstood: Addressing Injustice in LLMs

Supervisors: Jie Yang, Anne Arzberger

Incorporating User Feedback into Post-Training LLM Improvement to Promote Hermeneutical Justice: An Interface to Amplify Marginalized Voices

By Ada Turgut

Unheard and Misunderstood: Reinforcing Hermeneutical Justice in Annotation Design for ADHD Voices

By Aleksandar Yotkov

Unheard and Misunderstood: How are hermeneutical injustices encoded in Reinforcement Learning from Human Feedback (RLHF) in the context of LLMs?

By Ieva Mockaitytė

Unheard and Misunderstood: Tracing Hermeneutical Injustice in ADHD Narratives Generated by Large Language Models

By Miia Zhang

Prompt Engineering for Hermeneutical Justice in LLMs: An Empirical Study on ADHD-Related Causal Reasoning

By Sanjit Sankara Subramanian Lakshmi

Using optimal methods for subroutines in DFA learning

Supervisors: Sicco Verwer, Simon Dieck

A theoretical analysis of optimal and heuristic methods for DFA learning

By Horia Radu

DFA Learning: Minimal Models from Subsamples vs. Heuristic Models from Full Data

By Matei Hristodorescu

Testing The Performance Of Minimal Models Trained On Sparse Data

By Max Pieters

Chaining Heuristic and Exact Methods for DFA Identification

By Vasil Chirov

We need to learn how to teach Machine Learning

Supervisors: Gosia Migut, Ilinca Rențea, Yuri Noviello

Analogies for Machine Learning Loss Functions: An Empirical Study on Understanding and Motivation

By Ahmet Arif Özmen

Conceptual Bridges in Machine Learning

By Maria Cristescu

Domain Specificity in Supervised Machine Learning Analogies

By Mateo Nasse

Teaching Gradient Descent Through Analogies, Step by Step

By Thomas Koppelaar

How to Teach Unsupervised Machine Learning with Analogies

By Vincent Ruijgrok

What can we learn from incident reports?

Supervisors: Diomidis Spinellis, Eileen Kapel

What Secondary Issues Contribute to Operational Problems?

By Alexandru Muresan

Linking Software Changes to Incident Reports

By Danny Bunschoten

Understanding Software Failures Through Incident Report Analysis

By Iulia-Maria Aldea

Understanding IT System Failures: Primary Fault Types, Severity Patterns, and Evolution in Modern Operations

By Jakub Rutkowski

Anatomy of a fix: Analyzing Solution Patterns in Public IT Incident Reports

By Martin Georgiev

WiFi as a Sensor: Capabilities, Challenges, and Defenses

Supervisors: Arash Asadi, Fabian Portner

Voltage Supply for Liquid Crystal Reconfigurable Intelligent Surface Biasing

By Alexandru - Cristian Dumitrache

Voltage Control System for Liquid-Crystal Based Reconfigurable Intelligent Surfaces

By Nazar Vasyliev

Investigation of Learning Robustness Techniques in WiFi Sensing Deep Learning Models

By Oleh Grypas

Wi-Fi as a Sensor: Capabilities, Challenges, and Defenses

By Sofia Dimieva

Radar-Inspired Defenses for Wi-Fi Sensing Privacy

By Stanisław Ostyk-Narbutt