Here we list the current open, running and finished master projects at the visualization cluster. Running and finished projects can inspire you on interesting directions for your master thesis. If you are interested in a listed project contact the corresponding supervisor. If you have another topic or are uncertain on what to take, contact Huub van de Wetering.
Modern AI and Deep Learning can detect specific patterns in complex structures,like 3D geometry and temporal or meta data. In a first feasibility study it was proventhat neural networks are able to fully automatically label relevant hard clashes (high,medium or low priority) from geometry …
NXP Semiconductors enables a smarter, safer, and more sustainable world through innovation. As the world leader in secure connectivity solutions for embedded applications, NXP is pushing boundaries in the automotive, industrial & IoT, mobile, and communication infrastructure markets. In the NXP manufacturing process, checking whether …
The field of 3D reconstruction from 2D imaging using deep learning is rapidly advancing. Neural Radiance Fields (NeRFs) [1] have shown great promise in this area for both natural and medical imaging. To address the slow training and inference of these models, Gaussian Splatting …
The typical definition of dimensionality reduction is that points are mapped to the visual space, preserving the original pairwise distance between all points (global techniques) or between points belonging to the same neighborhood (local techniques). In light of this definition, the precision of the …
Typical dynamic network layout technique assume the time axis to be discrete, in order to simplify the problem and adapt techniques and technologies from the static graph drawing literature. This however has several drawbacks. If the network presents natural timeslices this technique works remarkably well: …
UiPath is the market leader in Robotic Process Automation (RPA) and is an end to end business automation platform. An important component of automation is being able to understand the process using process mining. The following assignments are related to UiPath Process Mining (formerly …
Prematurely born babies who are admitted to the NICU (neonatal intensive care unit) in hospitals could develop sepsis. This is threatening for their health, therefore, researchers try to predict sepsis based on multidimensional event and time series data collected while monitoring these babies. This …
Coronary artery disease (CAD) involves the narrowing or blockage of coronary arteries due to plaque buildup or stenosis, reducing blood flow to the heart. To diagnose CAD, X-ray coronary angiograms (CAG) are acquired to display the coronary artery structure from a 2D perspective. Typically, …
Temporal datasets are notoriously hard to visualize. The use of the space-time cube, that is a three-dimensional visualization with the third dimension being time, is a solution that has been initially investigating in the context of cartography and later applied in a number of visualization systems. …
The use of adjacency matrices in network visualization is justified by a several reasons: they do not suffer from clutter (as in node-link diagrams for example), and allow to quickly identify groups and structures with practically no adverse effects when scaling to larger networks. …
Current approaches for facial reconstruction involve parametric modeling, where mathematical optimization is used to fit 3D morphable models to scanned point clouds of the face. In some cases, depth maps arecomputed and 3D morphable models are then fitted on top of this map using …
Background – With “Information Diffusion” we refer to the discipline of modelling how Information “spreads” over a network under the premises of a stochastic model, which approximates and encapsulates the properties of a real diffusion phenomenon [1,2]. The network on which the diffusion takes …
Existing process mining techniques on traditional event logs result in many problems. If an event is related to different cases, we get false behavior in the model (convergence), for a case there also may be multiple instances of the same activity within a case …
Heat transfer represents the transport of thermal energy along certain paths, much like fluid motion represents the transport of fluid parcels along fluid paths. Due to this similarity, heat transfer can be analyzed and visualized based on tools similar to those used for fluid …
Background: Mechanical ventilation (MV) is a life-saving intervention used to support patients with respiratory failure. However, the effectiveness of MV can be compromised due to patient-ventilator asynchrony (PVA), which occurs when the patient's breathing pattern does not align with the ventilator's settings. PVA can …
In high-dimensional spaces, one intriguing property is that some data instances are among the k nearest neighbors of most (or all) other instances. This effect is known as data hubness, and the general effect is connecting unrelated manifolds or neighborhoods. While hubness reduction is …
Within Metrology & Patterning Control we focus on delivering cost efficient metrology and control solutions that help customers optimize scanner performance to maximize yield. With ever shrinking overlay margins this requires increasingly detailed overlay measurements: more measurements per wafer and more wafers measured, resulting …
In Process Mining, the resource perspective focusses on the people, machines and other resourcesemployed in the end-to-end flow of the process. Cases and tasks are handed over betweenresources, resources have certain availabilities, and resources often govern when what can happen.In this project, we want …
<to be provided>
The proposed project aims to develop novel methods for photorealistic rendering of diffusion MRI datasets by integrating advanced cinematic rendering technologies, path-tracing algorithms, and global illumination models. Diffusion MRI is an essential tool for studying neural connections and tissue architecture, but its traditional visualization …
Diffusion MRI allows us to make spectacular visualizations of the human brain. Depending on how you model the data coming out of the MRI scanner, you can obtain insights into different properties of the underlying tissue. Modeling fiber orientation distributions allows us to perform …
Since Google introduced knowledge graphs (KG) in 2012, the interest in the topic has increased continuously, and many companies applied this or comparable techniques. Nowadays, KGs are used in various fields, from product recommendations for online shops to finding connections between criminals in criminal …
Traditionally, assessing sleep, and sleep disorders, is performed using Polysomnography (PSG). PSG focuses on the measurement and analysis of brain activity, eye movements, and muscle activity to determine whether a subject is awake or asleep, and in which sleep phase someone is (light sleep, …
When simulating the dynamics of solid bodies in contact, one must compute the geometric overlap, determine where contact forces should be applied and in which direction. In addition, when the bodies are not entirely rigid or interpenetrate because of finite time steps, one introduces …
In software engineering Unified Modeling Language (UML) diagrams are used to visually represent a software system. UML diagrams communicate different aspects of the system (e.g., the main actors, roles, actions, and classes). The goal of the UML diagram is to document the architecture of …
Description: Tractography is a method that maps nerve tracts using orientation data from diffusion MRI scans. Despite advancements over recent decades, state-of-the-art algorithms still face significant inaccuracies, generating four times as many invalid bundles as valid ones, showing little predictive value on anatomical metrics, …
In the field of robotics and automation, determining the position and orientation of objects is essential for various applications. Traditionally, this has been accomplished using vision-based sensors. The information from these sensors can recover the local geometry of a target object, which is done …
Discrete multivariate event sequences are discrete records of a state with multiple attributes that form a chronologically ordered sequence. Discrete multivariate event sequences can be found in domains ranging from healthcare to transportation. Nevertheless, generating and analyzing such sequences from existing data is not …
Time series data, collected across various domains, holds valuable insights that can drive decision-making. Identifying specific patterns within this data is valuable but challenging. For example, a shop owner might want to know if their sales have ever dropped for seven consecutive days. In …
In recent years, graph pangenomes have become popular approaches to compare the DNA sequences of many organisms and discover differences that link to observable and measurable characteristics (or phenotypes) of interest, such as higher yield for crops or disease resistance in human genomics. These …
Background Prostate cancer is a major health burden. Both in Europe and the United States, it is the type of cancer with the highest incidence in men and the second cause of cancer-related death. One in seven men is diagnosed with prostate cancer in …
The focus of existing VA systems for explainable DL models has primarily been on classification, which does not exhibit the complexities of image-to-image translation problems. Image-to-image translation models involve transforming data from one form to another, i.e., the input and outputs are high dimensional …
A Comma Separated Values (CSV) file is a plain text file that contains rows of data values (see Figure). These files are typically used to load into visualization and machine learning tools. It often happens that the CSV file is not correctly structured. For …
Network analysis is often node-centric, e.g., ego-network analysis using a node-link diagram. Other times the analysis is more edge-centric such as the high-level communication overview provided by a hierarchical edge bundle view. A path-centric analysis and visualization is still an unexplored area. Paths are …
The construction of genealogy trees is typically done by patching pieces of information together found by browsing historic records with, for instance, birth, marriage, or burial registrations. Nowadays, many of these records have been digitized, allowing for obtaining results faster. However, finding, precise matches …
Any data analytical problem has multiple ways to be solved, involving different data mining, machine learning, or visualization solutions used in various combinations and orders. One example is the Kaggle competitions (https://www.kaggle.com/competitions), where a problem is posted, and the community contributes with different code-based …
In this fast digital content world, it is not uncommon for people to have thousands of images, texts, or songs in their possession that are usually not discarded but often not consumed. Some may create different strategies to organize content, but classifying and finding …
Most diffusion magnetic resonance imaging studies of disease rely on statistical comparisons between large groups of patients and healthy participants to infer altered tissue states in the brain; however, clinical heterogeneity can greatly challenge their discriminative power. There is currently an unmet need to …
A common task in the workflows of genomic biologists is to locate and inspect regions in genome-aligned data that show variation in many samples or genes. This can be a heavily repetitive task, going back and forth between manually extracting or querying the data …
Master project with Kay Roggenbuck.I am a PhD candidate at the visualization cluster, and my topic concerns visualizations for law enforcement and criminal investigations.Furthermore, this project is part of the AI4Intelligence project in cooperation with multiple PhD candidates from different universities across the Netherlands, …
When a researcher wants to study the genetics of a species, the use of a reference genome is a common approach. A reference genome is the genetic information of one idealized organism of a species. It is assembled by combining DNA from multiple organisms …
Master project with Kirsten Maas. The topic of my PhD is Visual Analytics for Percutaneous Coronary Interventions. I collaborate with Philips, Catharina Ziekenhuis Eindhoven and the Cardiovascular Biomechanics group of the Biomedical Engineering department.In short: I am interested in NeRF reconstruction methods and Visual Analytics …
Master project with Astrid van den Brandt. Studying genetic variation underlying phenotypes is an important topic in genomics. In plant genomic research, for example, scientists analyze the variation between cultivars and wild types to develop crops with improved resistance to diseases. This analysis is commonly …
Master project with Sanne van der Linden. I am a PhD candidate and my research topic is about event sequence data. Much of the collected data is multivariate sequential data from heterogeneous data sources, such as patient treatments and medication in healthcare or customer behavior …
Master project with Linhao Meng. My research focuses on empowering the machine learning pipeline with visual analytics (VA) for data scientists and engineers. Model development is a demanding process that involves various tasks about raw data, features, and models. We explore how to support data …
Background Major depressive disorder (MDD) is a prevalent neuropsychiatric disorder with at least one episode occurring in the lifetime of 15%-18% of people worldwide. MDD is a very heterogeneous disease with highly varying symptom profiles and inefficient treatment as only one-third remit after first-line …
During his short but prolific life and career, Vincent van Gogh produced more than 2,000 artworks, including close to 900 paintings and 1,100 drawings and sketches [1,2]. He was also a passionate letter writer and more than 900 written exchanges with his family, friends …
The main subject that will be investigated during this project is the explain-ability of black-box deep learning models using visual analytics techniques. The main goal will be to successfully build a framework in which model architects and developers can explore the inner workings of …
Social computing applications, such as online social networks, have experienced a significant momentum in the last decades. These applications enable users to collaboratively create, manage and share resources with other users in real time. Although they provide several benefits for users and organizations, these …
Among the existing visual representations for the analysis of multidimensional data, Dimensionality Reduction (DR) layouts are one of the most popular, allowing users to analyze similarity relationships. In general, DR techniques aim at reducing a high-dimensional space to 2 or 3 dimensions and are …
Dimensionality reduction is one of the leading visualization tools for analyzing multidimensional data, allowing for studying similarity/dissimilarity relationships in any dataset where a distance function can be defined. Despite its popularity, mapping many features to usually a pair of dimensions (in the visual space) …
Coronary artery disease is one of the most common heart diseases. The coronary arteries are the main heart vessels supplying oxygenated blood to the heart. When diseased, these arteries are clogged in certain locations, which we refer to as stenoses. To treat these stenoses, …
Target levelTUe Master’s student(s) - employed as intern at ASML working in the collaborative project with the Van Gogh Museum (VGM) in the scope of the ASMl-VGM partnershipProject goalInteractive visual analysis design and implementation to explore topographical features in Van Gogh’s paintings (with a …
Diffusion MRI tractography has revolutionized our understanding of the human brain's structural connectivity by enabling the reconstruction of white matter pathways. Along-tract profiling, known as tractometry, provides valuable insights into the microstructural properties of individual bundles. However, defining a reliable core streamline representation, such …
Building Information Modelling (BIM) or Building Information Management, is a highly collaborative process that allows architects, engineers, real estate developers, contractors, manufacturers, and other construction professionals to plan, design, and construct a structure or building within one 3D model.The most difficult part of BIM …
Various diffusion MRI (dMRI) measures have been proposed for characterising tissue microstructure over the last 15 years. Despite the growing number of experiments using different dMRI measures in assessments of white matter, there has been limited work on: 1) examining their covariance along specific …
This project aims to develop a web-based visualization tool for diffusion MRI tractography, enabling researchers and clinicians to interactively explore and analyze white matter pathways. Diffusion MRI tractography generates a vast amount of data in the form of streamlines, representing potential fiber pathways within …
The proposed master project aims to provide an overview of automated methods for the detection of the AC-PC line in medical imaging and segmentation approaches for the extraction of the dentato-rubro thalamic tract (DRTT) using diffusion MRI tractography. Both the AC-PC line and the …
The Neonatal Intensive Care Unit (NICU) is designed to treat high-risk infants, such as those who were born prematurely, and to monitor vital signs, prevent sickness, and give life support. The NICU is where infants that are critically ill are often treated. Premature infants …
Process discovery is often done automatically using process discovery algorithms, such as the Probabilistic Inductive Miner [2]. However, the quality of the discovered models depends heavily on the quality of the data and how the data is prepared and selected. This is hard to …
Background: Diffusion-weighted magnetic resonance imaging is a technique aimed at measuring the displacement of water molecules inside biological tissues. From those acquisitions, it is possible to reconstruct fiber orientation distribution functions (fODF) describing the apparent quantity of white matter fibers going through a voxel …
Discrete multivariate event sequences can be found in domains ranging from healthcare to transportation. Discrete multivariate event sequences are discrete records of a state with multiple attributes that form a chronologically ordered sequence. For example, consider the medication intake of a patient. In this …
When estimating the orientation of an object in an image, several factors such as rotational symmetries, occlusion, and self-occlusion can create a set of possible orientations, either continuous or discrete. Consider a smooth cylinder where its orientation around one axis cannot be visually derived …
Digitization of archives is an ongoing process in which the books in archives are handled in some order. The partial availability of the digitized records poses a problem for both volunteer, researcher and manager. All of them are left in a state in which …
The increasing use and adoption of machine learning prediction techniques by different societal sectors, from health to industry domains, have recently fomented the need to inspect prediction models for accountability. This trend is usually referred to as explainable AI (xAI), and Visual Analytics (VA) …
This project is conducted in collaboration with UiPath Process Mining, which focuses on discovering, monitoring, analyzing, and improving business processes. These processes are uncovered via process mining and visualized in process models. These models are useful for discovering unwanted behavior and places where the …
In the Netherlands, a frequently used mode of transport is the bicycle. A quarter of the daily trips made within the country are done by bike. The relatively short distances, little elevation changes, and special bike lanes give the country a biking culture. Unfortunately, …
View synthesis and 3D reconstruction are complex fundamental problems in computer vision. Although several traditional neural networks for 3D reconstruction have been proposed, they typically cannot represent the high frequency details existing in these signals. Neural Radiance Fields (NeRF) [1] is a new emerging …
Ensembles are compositions of standard classifiers taking advantage of classifiers' different characteristics by combining individual predictions into a single classification outcome. With the need to audit results produced by automated techniques, the demand to explain the results of ensemble models has emerged in recent …
Within the field of tractography incredible advancements have been made by being able to non-invasively measure and model nerve tracts within the human body. While this alone allows for a better understanding of the neural pathways, this has also opened the door for further …
Introduced in 2015 by Ronneberger et al. [1], The U-Net model is one of the most powerful neural networks for image translation. This process allows an input image to be translated into an (possibly very different) image efficiently and effectively. It has also been …
Data labeling, as a fundamental task in supervised machine learning, refers to the annotation of data with representative labels. In contrast to active learning (AL), interactive labeling relies on users’ knowledge and pattern identification ability to select meaningful instances to label [1]. Previous work …
Robotic manipulation has traditionally been focusing on the manipulation of rigid objects. However, as robotics is expanding in new application fields and is expected to physically interact with humans and a large variety of objects, the expectation is that robots will be able to …
This project aims to design a physics-based simulation environment that dynamically represents a robot capable of performing vision-guided manipulation of rigid objects. Object poses have to be estimated with the use of an RGB(D) camera. The process should be fully autonomous. In order to …
ASML and the Van Gogh Museum entered in a partnership aimed at supporting the preservation of Vincent van Gogh’s legacy. Understanding the objects, context and materials, how they have changed and will change in the future, and how that change can be monitored and …
The Random Forest model is an effective ensemble machine learning model that can be used to achieve high predictive accuracy. It consists of multiple decision tree models, each trained on a smaller part of the original data. However, its inherent complexity makes it difficult …
Main research question of project: To what extent can Spotify recommendations be explained to a satisfactory extent through narrative visualizations.Description: Artificial intelligence (AI) is becoming a more prominent part of our every day lives. However, a concern that comes with AI is that depending …
This project is about the integration of IBM Rhapsody models in 3-diminensional Unity environment while allowing interaction with the models, simulation of the models, and placement of the models meaningfully with respect to the 3d-elements that they describe.
Process discovery is often done automatically using process discovery algorithms, such as the Probabilistic Inductive Miner [2]. However, the quality of the discovered models depends heavily on the quality of the data and how the data is prepared and selected. This is hard to …
One objective of the Sailing+ application is to help newcomers engage with, and learn about, the sport of sailing. Part of achieving this goal is to summarize interesting events when and where they occur. In this thesis, we ask ourselves the question how to …
Existing process mining techniques on traditional event logs result in many problems. If an event is related to different cases, we get false behaviour in the model (convergence), for a case there also may be multiple instances of the same activity within a case …
When a machine learning classification has been made and the user disagrees with the prediction, he or she wants to know what needs to be changed to get a (better) different outcome. Calculating this is a part of machine learning called counterfactuals and recourse. …
The U-Net model, introduced in 2015 by Ronneberger et al. [1], is one of the most successful deep learning models. It allows to efficiently and effectively process an input image into an output which can be drastically different. It has been used for image …
Discrete multivariate event sequences can be found in domains ranging from healthcare to transportation. Discrete multivariate event sequences are discrete records of a state with multiple attributes that form a chronologically ordered sequence. For example, consider the medication intake of a patient. In this …
Problem In a previous project, Baker Tilly created an autoencoder to detect fraudulent transactions in a list of transactions. The autoencoder shows good results for the anomaly detection problem. However, it is difficult to show why the model made certain decisions and why it …
This is a project with ING Bank (Amsterdam*). ING wants to better understand their micro-service architecture. They reconstruct this based on execution traces. This leads to very large graphs (see example). The project may involve one or more of the following:o Analysis & Visualisation …
The recent COVID-19 pandemic introduced new challenges for mental healthcare, such as the detrimental effects it has on peoples mental well-being, but also the limited access that people have to mental healthcare systems. PROSIT (Predicting Risk and Outcomes of Social Interactions) is a project …
A surrogate model is an interpretable model trained to approximate the predictions of a black box model for model explainability[1]. Thus it should be able to approximate the predictions of the underlying model as accurately as possible and be interpretable at the same time. …
Computing medial axes for 2D shapes is a well understood topic, with efficient, robust, and easy-to-use methods (see e.g., Ogniewicz and Kubler, 1995; Telea and van Wijk, 2002; Falcao et al., 2004; Siddiqi and Pizer, 2009). The 2D medial axis transform (MAT) fully encodes …
Modern Graphics Processing Units (GPUs) have been shown to provide a viable means to accelerating compute-intensive applications. The main goal of any of the following projects is to develop GPU data structures and algorithms to accelerate certain graphics-related applications, through NVidia's CUDA GPU programming …
VinciTech is a robot company that is developing a lightweight robotic platform for collaborative tasks. This robotic platform is intended to work alongside people, as a COllaborative roBOT (COBOT). The robot arm itself is made of Igus Robolink W components. In a previous MSc …
The turnaround process is a series of tasks that need to be executed to prepare a parked aircraft for a new flight (e.g. fueling or loading baggage). The efficient execution of such tasks is necessary to guarantee that most flights will depart on time. …
Social media posts from politicians are biased, i.e. strongly in favor of one group or argument, and framed, i.e. selected, emphasised and presented. Although bias and framing do not imply falsehood, they do shape the receiver’s understanding of information, as politicians typically choose the …
Pose estimation is a core component in many modern computer vision pipelines. In applications like robotic grasping, augmented reality, and scene understanding, the ability to accurately and robustly predict the position and orientation of objects from RGB images is essential. Though the performance of …
Vlisco releases 250 - 300 new dessins every year, and every new dessin is manually judged on feasibility and producibility. A risk profile is generated based on likelihood of typical errors related to the product drawing.This process is called Product Release and relies heavily …
A Neonatal Intensive Care Unit (NICU) is a hospital department for neonates who need intensive care after birth. These neonates are monitored closely to check their vital signs (like ECG, blood pressure, oxygen saturation levels in the blood), as life-threatening complications can occur. These …
This research will focus on exploring and analyzing the ways in which progressive aggregate query results can be visualized and presented to the user in the most informative, actionable way. Furthermore, ways to utilize the visualization as an interface by the user to further …
Digital twins have been applied in the field of aerospace engineering, manufacturing and smart products and asset lifestyle management. In all cases, the digital twin has been proven useful in ensuring infor- mation continuity, decision support and system behavior predictions. In recent years, research …
Deep learning networks are the state of the art in machine learning for various classification and regression tasks in many domains, e.g., machine vision, speech recognition, and, natural language processing. Deep learning models often outperform traditional machine learning models in terms of classification/regression accuracy. …
We want to use moving least squares interpolation for reconstruction of an environment which is used in control of a collaborative robot (Cobot). A cobot is a robot designed to collaborate in a shared space with humans to assist in certain tasks. In order …
UiPath is the market leader in Robotic Process Automation (RPA) and focuses on hyper automation. An important component of hyper automation is being able to understand the process using process mining. The following assignments are related to UiPath Process Mining (formerly ProcessGold), which is based in …
Photon mapping is a physically-based light transport algorithm. It consists of two stages: in the first stage, energy packets called photons are emitted from light sources and traced through the scene. When the photons intersect with scene geometry, their position and energy are recorded …
Deep Learning models can currently achieve state of the art performances in several medical image analysis benchmarks. However, modern Deep Learning architectures have been shown to be susceptible to generating overconfident predictions even in cases when the model generates wrong the wrong prediction. The …
This study will provide more insight in sleep and the relation between sleep and air traffic using interactive web-based visualizations. Sleep data will be retrieved from a graphical sleep diary application and air traffic data from an open-source platform.Every two years, the Gemeentelijke Gezondheidsdienst …
ASML collects and analyzes event log data from thousands of machines in the field. This data is used to diagnose equipment failures in near real-time: often ASML’s diagnostic software can recommend which repair action to take. In addition, a database with all these machine …
Diffusion tensor imaging (DTI) is a magnetic resonance (MR) image technique that is being used to track fibers of white matter in the brain. This fiber tracking, also called tractography, can for example help surgeons with the preparation for brain surgery. During several steps, …
Polysomnography (PSG) remains the current gold standard for assessing sleep. PSG focuses on the measurement and analysis of brain activity, eye movements and muscle activity to determine whether a subject is awake or asleep, and in which sleep phase someone is. From PSG, the …
For musicians and music analysis, discovering, and explaining structural patterns is still done mostly by hand. And due to the limitation of having to listen to the music multiple times for its entire duration it is also very time consuming. For some songs, musical notation …
Given NBA data for two full competitions on player position, ball position, match events like scores, try to analyze and compare players, teams, and competitions on a level suitable for an amateur basketball coach.
International draughts is a two-player board game played on a 10 by 10 board. To analyze matches or research tactics for this game several datasets are available. Among others, a historic database of matches and a database that gives, for positions with a limited …
The electronic health record was designed to assist doctors, but in hospitals in the US, a kidney patient has on average 338 notes. The medical narratives in these notes play a major role in providing contextual richness of a patient and clinicians rely heavily …
Tractography, frequently also referred to as fiber tracking, is the most commonly used technique for reconstructing and visualizing nerve tracts in the human brain. The processing pipeline to visualize this data, from image acquisition to the final rendering, is rather complex and along the …
The Brabant Historical Information Center (BHIC) collects various types of genealogy data in the province of Noord Brabant. The datasets they collect contain the records of different events in one’s life, including birth, marriage, military, prison, residence register and death. And for each kind …
Cooperative robotics is a growing interest in industrial settings. This report focuses on the prediction of unstructured dynamic environments, which can be expected when a workspace is shared between a robotic system and a human. Accurate predictions of positions and velocities of objects in …
In any given company or organization, growing and escalating their business is one of the major goals. The decisions and strategies undertaken to achieve these goals are thus crucial. Generally, the measures against which companies measure and evaluate their performance or success are known …
Collaborative robots (Cobots) are used in, for instance, the assembly and packaging industry to help workers complete difficult or impossible repetitive tasks. To improve cobots they should be able to complete their tasks without colliding into dynamic objects. To avoid collision the cobot needs …
Narcolepsy is a chronic neurological condition that results from the dysregulation of the sleep-wake cycle occurring in an early stage, specifically in adolescence. Patients with narcolepsy experience excessive daytime sleepiness, cataplexy, hypnagogic hallucinations, sleep paralysis and disturbed nocturnal sleep and these symptoms together form …
Genealogy, the establishment of a pedigree, is the investigation and research of the family, family history, and past footprints. In the past, genealogy often used oral interviews, genetic analyses, historical records, and other queryable information to collect information about the family, and to prove …
Process mining tools help businesses gain insight into their processes by, among other things, providing automated visualizations of their process event logs. Process graphs play an important role in process analysis by providing an interactive graph layout in which nodes represent activities, and directed …
ASML is one of the largest manufacturers of machines that are used in the process of creating silicon based micro-chips used in modern electronic devices. These machines are cutting edge photolithography scanners, used in the process of manufacturing micro-chips. The performance of these machines …
This graduation project aims to visualize behavioral change of people who use the mobile health application GameBus. GameBus is an application which promotes healthy behaviors (e.g. physical, social and cognitive activities) according to the age and interests of the user. Currently, analyzing the data …
The identification of a creator of a piece of art has both cultural and economical values. Cultural in a sense that it helps in shaping human history and economical in a sense that it gives an art buyer the confidence in purchasing an authentic …
Object detection has been the most important task in the field of computer vision. As researchers have proposed many efficient object detection methods, the deployment and application of these methods in an engineering perspective has become a problem. We propose to implement an efficient …
In industrial context, there is an increasing request to share the workspace between humans and robots. In this shared workspace, close collaboration between robots and humans takes place, such as robots helping humans with repetitive tasks. Collaboration can be made more flexible by enabling …
Companies often integrate their data by extracting information from different sources and applying various transformations to receive their desired output (also referred to as ETL). Maintenance on the transformation graphs applying these transformations is performed by a small number of domain experts that often …
In this thesis we propose a method for crowd simulation in building evacuation. The simulationenvironment is a building with optionally multiple floors in which fire and smoke can be present.The simulation should run in real-time with up to thousands of agents. People in the …
Machine Learning models get better and better at various tasks. However, along with these improvements, the complexity of these models also rapidly increases. This negatively affects the comprehensibility of these models. In this thesis, we defend the case for comprehensibility of a specific predictive …
Epidemiologists need to monitor complex resistance patterns of multi-drug resistant bacteria, and especially since bacteria are increasingly resistant to antibiotics. Their analysis, however, is limited to individual antibiotics. Hence, epidemiologists want to gain more insight in multi drug resistance patterns and their relations with …
Process mining is a technique to extract a process model from an event log. An event log represents a process and consists of traces describing a sequence of activities. Applying process mining techniques to a complex process can lead to a model that is …
The concepts of consonance and dissonance correspond roughly to the combinations of musical notes that are perceived by most to be pleasant and unpleasant, respectively. These concepts are some of the main cogs and gears available to composers for the purpose of introducing emotionaltension …
The main goal of this research is improving the performance of geodesic fiber tracking for HARDI data by utilizing the parallel computing capabilities of a Graphical Processing Unit (GPU) through the CUDA language. Instead of sequentially tracking single fibers in one CPU thread, the …
The Center for Infectious Disease Control, RIVM, is the national knowledge center and coordinator in the infectious disease domain. One way of reducing health problems related to infectious diseases is by vaccination. For some infectious diseases, such as the Human papilloma virus ( HPV) …
With the development of sensor and camera tracking systems, it becomes easier to track player events in a football match. With these match events, post-match analysis on players can be conducted to compare the performance of players.Comparing football players is not an easy task, …
Multi-agent systems generate large amounts of logging data that, when properly understood, could be used to understand and subsequently improve their behaviour. A multi-agent system is a computerized system that consists of multiple interacting intelligent agents in an environment. Typically, the agents in the …
In radiotherapy, the goal is to deliver high radiation doses to destroy the cancer cells,while sparing the adjacent healthy tissues. To ensure that disease is treated and normal structures are spared, a dose planning is required. Nowadays, through the use of image guidance techniques …
In this thesis, we develop two new methods for simulating large, dense crowds. We consider crowds ofseveral thousand agents. Each of these agents has to navigate the scene to reach its goal, while avoiding collisions with obstacles and other agents. Thus, our simulation methods …
Kempenhaeghe is an expertise centre for epileptology, sleep medicine, and neurocognition. Doctors gather information about epilepsy patients in order to respond with adequate surgery and/or medication. Per patient, all data on symptoms, treatments, events and notes are stored in an information system in the …
Nowadays, the usage of medical imaging data is widely present in both diagnostic procedures and treatment planning. Using Magnetic Resonance Imaging (MRI) or Computer Tomography (CT) scans, sets of two-dimensional slices are obtained, from which three-dimensional models can be constructed using segmentation algorithms. These …
Nowadays, it is possible to obtain brain networks from data measured by a Magnetic Resonance Imaging (MRI) scanner. This opens up new ways of understanding the human brain. One new possibility is comparing two brain networks, which may aid in understanding brain diseases like …
In this thesis we present a software prototype to explore football data containing spatiotemporal data. In contrast to most of the current analyses, we show that football visualization is not restricted to statistical information by visualizing playing styles and strategies. We define possession chains …
The work in this thesis has been carried out under the auspices of Infostrada Sports, and its purpose is to visualize the core of a soccer match using spatio-temporal data. Matches consist of large, dense data sets of events, which are difficult to elucidate …
Sooner or later every modern city faces the challenges to cope with increased traffic and street congestions. Increased e-commerce means an increase in the number of delivery trucks driving around. Understanding how a city works can be used by researchers and governments to enforce …
ASML's wafer scanners play a crucial part in the process of making computer chips. They pattern an optical mask of hundreds of chips onto a silicon disc, a so-called wafer. There is no one that knows everything there is to know about a wafer …
In this thesis we visualize event logs, or also often called process data. We start with the idea of visualizing the data as a flow. We use data from a high school to implement and test our system. The data analyst we obtained the …
Electronic patient data and medical prescription histories are a valuable source of information. Doctors want to use this data to get more insight into their prescription behavior and that of their colleagues. Up till now, there is no suitable system that shows information about …
Demographic experts at CBS are interested in migration. Currently, analysis of migration data is a time-consuming process. The migration data set contains both information about the regions between which people migrate, and the migrants themselves. A combination of existing, easy to interpret visualizations is …
In this thesis we present a layout algorithm for Workflow nets, which are a specific type of Petri net. While much research has been performed on layout algorithms for graphs, there is little known research on layout algorithms for WF-nets. Our layout algorithm is …
The screen of a radar system is complicated and subject to many artifacts. Many physical aspects of the world need to be simulated in order to faithfully reproduce it. In this thesis we introduce an algorithm that can output a realistic image of a …
Business Intelligence tools are used by professionals to obtain knowledge about the organization they work in which in turn is used to make good management decisions. One type of BI tools use visualizations to make the data in the organizations’ databases more understandable and …
In UNIX-like operating systems such as Linux, the software is split into thousands of packages which are tracked by package management software. Interdependency is an important term in this context because in a Linux system, the working of an application may depend on the …
In this thesis, an approach to visualizing dense temporal events is investigated. When events are densely packed together, the resulting issues are highlighted and techniques to alleviate them are presented. The visualization developed enables uncovering interesting patterns hidden in such dense temporal data. The …
Traceability is considered to be important in many scientific and industrial fields for verification purposes, accountability and quality control. Currently existing methods for gaining insight in traceability information cannot provide a complete overview and lack the ability to quickly gain insight in the relations …
Clustering is a technique for grouping similar data. It is not evident what similar data is; this depends on a domain or even on a specific situation. Therefore, a user might be engaged in the clustering process, so he1 can transfer his domain knowledge. …
In this thesis the results of the ĕnal master project performed at the Eindhoven University of Technology, Department of Mathematics and Computer Science, Visualization group under the guidance of prof.dr.ir Jarke J. van Wijk are presented. The realized research has led to three products; …
The display of a large number of points, distributed over the plane, is a classic visualization problem. Available space is usually limited, which means a simple plot of the points (known as a scatter plot) quickly becomes cluttered and also suffers from problems such …
The goal of this project is to research the possibilities of “Augmented Reality for Landscape Development on Mobile Devices”. It aims to create a prototype that is able to derive the user’s context and, based on this context information, can display a new landscape …
The ability to connect computers to one another, by means of a network, has led to computers being more vulnerable for malicious behavior. Network operators have the task to prevent attackers from performing malicious activities on their networks. In this thesis we present an …
Moving object data visualization and analysis is a growing field of research. In this thesis we present a continuation of previous work where paths of moving vessels are convolved with a kernel onto a density map to aid operators of coastal surveillance systems and …
In this thesis the Lipschitz approach and interval arithmetic approach to ray tracing implicit surfaces are compared. This comparison has been described as future work by Andrew et al. in [Guy98]. The methods are compared on the following:• The pruning of space. This is …
We investigate a novel visualization method by which to render white matter fiber bundles, based on illustrative rendering. Illustrative rendering specializes in producing stylized images which allow for a great deal of abstraction. We aim to use guidelines and techniques from the traditional fields …