document

Synthetic data generation for research – enabler for privacy-enhancing health data sharing?: A multidisciplinary research on synthetic data generation in healthcare

van der Wel, Iris (author)

Data-driven health research, specifically the development of AI models, is hampered by poor data availability and associated administrative burdens, caused complex and fragmented data protection regulation. To reap the benefits of using high quality health data, while safeguarding data protection of patients, the synthetic data generation is...

master thesis 2024

document

Optimizing strains in Metabolic Engineering: comparative analysis of β-Conditional Variational Auto-encoder and Probabilistic PCA for synthetic data generation

Kirbeyi, Doruk (author)

This research explores the landscape of dataset generation through the lens of Probabilistic Principal Component Analysis (PPCA) and β-Conditional Variational Auto-encoder (β-CVAE) models. We conduct a comparative analysis of their respective capabilities in reproducing datasets that mirror the distribution of the original data that comes from a...

bachelor thesis 2024

document

Evaluating 6D pose estimation accuracy with synthetic data: A comparative analysis of RGB based and RGB-Depth-based images in a chess piece picking task with a robotic arm

Waterhout, Max (author)

This study investigates the influence of synthetic data on the accuracy of 6D pose estimation in RGB images compared to RGB-Depth image-based methods. Additionally, it aims to examine how this performance varies across different types of small chess pieces during a picking task with a robotic arm. The methodology involves 3D scanning the chess...

master thesis 2024

document

Making it Clear: Using Vision Transformers in Multi-View Stereo on Specular and Transparent Materials

Tolsma, Pieter (author)

Transparency and specularity are challenging phenomena that modern depth perception systems have to deal with in order to be used in practice. A promising family of depth estimation methods is Multi-View Stereo (MVS), which combines multiple RGB images to predict depth, thus circumventing the need for costly specialized hardware. Although...

master thesis 2023

document

3D Kinematics Estimation with Biomechanics Model

Lin, Zhi-Yi (author)

Human 3D kinematics estimation involves measuring joint angles and body segment scales to quantify and analyze the mechanics of human movements. It has applications in areas such as injury prevention, disease identification, and sports science. Conventional marker-based motion capture methods are expensive both in terms of financial investment...

master thesis 2023

document

Enhancing Historical Dutch OCR Accuracy with Post-Correction & Synthetic Data

Eckhardt, Thomas (author)

This paper presents a novel approach to synthetic data generation for OCR post-correction, utilizing specific background and font variations tailored to specific timeperiods. The goal is to use synthetic data to enhance text accuracy in digitized historical documents. The proposed three-step process involves generating synthetic images that...

master thesis 2023

document

Anomaly Detection and Synthetic Data Generation for Power Systems Using Autoencoder Neural Networks

Wang, C. (author)

The scale of the power system has been significantly expanded in recent decades. To gain real-time insights into the power system, an increasing number of sensors have been deployed tomonitor grid states, resulting in a rapidly growing number of measurement points. Simultaneously, there has also been a rise in the penetration of renewable energy...

doctoral thesis 2023

document

NLICE: Synthetic Medical Record Generation for Effective Primary Healthcare Differential Diagnosis

Al-Ars, Z. (author), Agba, Obinna (author), Guo, Zhuoran (author), Boerkamp, C. (author), Jaber, Ziyaad (author), Jaber, Tareq (author)

This paper offers a systematic method for creating medical knowledge-grounded patient records for use in activities involving differential diagnosis. Additionally, an assessment of machine learning models that can differentiate between various conditions based on given symptoms is also provided. We use a public disease-symptom data source called...

conference paper 2023

document

Federated Synthetic Data Generation with Stronger Security Guarantees

Ghavamipour, Ali Reza (author), Turkmen, Fatih (author), Wang, Rui (author), Liang, K. (author)

Synthetic data generation plays a crucial role in many areas where data is scarce and privacy/confidentiality is a significant concern. Generative Adversarial Networks (GANs), arguably one of the most widely used data synthesis techniques, allow for the training of a model (i.e., generator) that can generate real-looking data by playing a min...

conference paper 2023

document

Enriching Diversity of Synthetic Images for Person Detection

POLYA RAMESH, CHINMAY (author)

Camera-based patient monitoring is undergoing rapid adoption in the healthcare sector with the recent COVID-19 pandemic acting as a catalyst. It offers round-the-clock monitoring of patients in clinical units (e.g. ICUs, ORs), or at their homes through installed cameras, enabling timely, pre-emptive care. These are powered by Computer Vision...

master thesis 2022

document

A Novel Concept for Home Healthcare Operations Using Electric Home Delivery Vehicles

Dann Ruiz, Nicolas (author)

Healthcare systems worldwide rely heavily on the efficient allocation of caregivers in home- based care. Despite this, to this day, the majority of home healthcare (HHC) organisations plan their operations manually, an extremely time-consuming and labour-intensive task yielding sub-optimal solutions. Research efforts in the operations research ...

master thesis 2022

document

BladeSynth: Damage Detection and Assessment in Aircraft Engines with Synthetic Data

Feng, Chengming (author)

Deep learning has been widely implemented in industrial inspection, such as damage detection from images. However, training deep networks requires massive data, which is hard to collect and laborious to annotate, especially in the aviation scenario of aircraft engines. To alleviate the demand for annotated data, we create BladeSynth - a large...

master thesis 2022

document

Automated Semantic Segmentation of Aerial Imagery using Synthetic Data

Caceres Tocora, Camilo (author)

Semantic segmentation of aerial images is the ability to assign labels to all pixels of an image. It proves to be essential for various applications such as urban planning, agriculture and real-estate analysis. Deep Learning techniques have shown satisfactory results in performing semantic segmentation tasks. Training a deep learning model is an...

master thesis 2022

document

Personalised prediction of skill development and retention using XGBoost and SHAP

van Leeuwen, Barry (author)

Predicting individual skill retention, the extent to which human operators retain learned skills over time is limited by lengthy experiments and identifying patterns in the highly dimensional data. Using machine learning to process this data and find patterns could provide a regression prediction of this data. This paper investigates the use of...

master thesis 2022

document

Generating Contextual Load Profiles Using a Conditional Variational Autoencoder

Wang, C. (author), Tindemans, Simon H. (author), Palensky, P. (author)

Generating power system states that have similar distribution and dependency to the historical ones is essential for the tasks of system planning and security assessment, especially when the historical data is insufficient. In this paper, we described a generative model for load profiles of industrial and commercial customers, based on the...

conference paper 2022

document

When Machine Learning Models Leak: An Exploration of Synthetic Training Data

Slokom, M. (author), de Wolf, Peter Paul (author), Larson, M.A. (author)

We investigate an attack on a machine learning classifier that predicts the propensity of a person or household to move (i.e., relocate) in the next two years. The attack assumes that the classifier has been made publically available and that the attacker has access to information about a certain number of target individuals. That attacker...

conference paper 2022

document

One Step Ahead: A weakly-supervised approach to training robust machine learning models for transaction monitoring

van der Werf, Daan (author)

In recent years financial fraud has seen substantial growth due to the advent of electronic financial services opening many doors for fraudsters. Consequently, the industry of fraud detection has seen a significant growth in scale, but moves slowly in comparison to the ever-changing nature of fraudulent behavior. As the monetary losses...

master thesis 2021

document

Handling the unknown: Towards on-the-job object recognition

ter Kuile, David (author)

As robots are becoming a more integral part in our daily lives, it is important to ensure they work in a safe and efficient manner. A large part of perceiving the environment is done through robot vision. Research in computer vision and machine learning lead to great improvements in the past decades and robots are able to outperform humans on...

master thesis 2021

document

FeTGAN: Federated Time-Series Generative Adversarial Network

Plesner, M.K. (author)

The key to producing high-fidelity time-series data is to preserve temporal dynamics. This means that generated sequences respect the relationship between variables across time as in the original data. While new types of GANs have been used to generate time-series data, they, like previous GAN<br/>implementations, are time consuming to train. A...

bachelor thesis 2021

document

Time Series Synthesis using Generative Adversarial Networks

Dannenberg, Jan-Mark (author)

Generative Adversarial Networks are widely used as a tool to generate synthetic data and have previously been applied directly to time-series data. However, relying solely on the binary adversarial loss is not sufficient to ensure the model learns the temporal dynamics of the data. TimeGAN [14] introduces an additional reconstruction and...

bachelor thesis 2021