document

A Step Towards Understanding Normalizing Flows and their Likelihood Behavior

de Bruin, Niels (author)

Normalizing flows have demonstrated their ability to learn complex and high-dimensional distributions. However, the behavior of normalizing flow likelihoods are not yet fully understood, particularly when exposed to outlier data, where it has been observed that large likelihoods are often assigned to inputs that are substantially different from...

master thesis 2024

document

Comparative Study of Loss Functions in Personal Identification for Smartwatch Data: Examining Accuracy of Loss Functions in Personal Identification using Outlier Detection with Auto-encoders on Data from Smartwatches

Yümlü, Ege (author)

Smartwatches are equipped with sensors that allow continuous monitoring of physiological and physical activities, making them ideal sources of data for data analysis. However, accurately identifying individuals based on smartwatch data can be challenging due to the presence of outliers. Hence, outlier detection techniques play a crucial part in...

bachelor thesis 2023

document

Performance of outlier detection on smartwatch data in single and multiple person environments: An analysis of the performance of different outlier detection methods on consumer-grade wearable data in environments with single and multiple subjects

Wubben, Luuk (author)

Outlier detection is an essential part of modern systems. It is used to detect anomalies in behaviour or performance of systems or subjects, such as fall detection in smartwatches or voltage irregularity detection in batteries. This provides early indications of something of potential problems.<br/><br/>A part of outlier detection that is not...

bachelor thesis 2023

document

A Comparative Analysis of Learning Curve Models and their Applicability in Different Scenarios: Finding datasets patterns which lead to certain parametric curve model

Kalandadze, Anna (author)

Learning curves display predictions of the chosen model’s performance for different training set sizes. They can help estimate the amount of data required to achieve a minimal error rate, thus aiding in reducing the cost of data collection. However, our understanding and knowledge of the various shapes of learning curves and their applicability...

bachelor thesis 2023

document

Advancements in Large-Scale Volumetric PIV and PTV

Saredi, E. (author)

Particle Image Velocimetry (PIV) is considered nowadays the state-of-the-art for non-intrusive and quantitative 3D velocity measurements. Its ability to measure the velocity field around complex geometries is a valuable tool that engineers can exploit for aerodynamic design optimization in various domains, such as aerospace, wind turbines and...

doctoral thesis 2023

document

Benchmarking Outlier Detection Methods for Detecting IEM Patients in Untargeted Metabolomics Data

Bongaerts, Michiel (author), Kulkarni, Purva (author), Zammit, Alan (author), Bonte, Ramon (author), Kluijtmans, Leo A. J. (author), Blom, Henk J. (author), Engelke, Udo F. H. (author), Tax, D.M.J. (author), Ruijter, George J.G. (author), Reinders, M.J.T. (author)

Untargeted metabolomics (UM) is increasingly being deployed as a strategy for screening patients that are suspected of having an inborn error of metabolism (IEM). In this study, we examined the potential of existing outlier detection methods to detect IEM patient profiles. We benchmarked 30 different outlier detection methods when applied to...

journal article 2023

document

Detecting outliers from pairwise proximities: Proximity isolation forests

Mensi, Antonella (author), Tax, D.M.J. (author), Bicego, Manuele (author)

Because outliers are very different from the rest of the data, it is natural to represent outliers by their distances to other objects. Furthermore, there are many scenarios in which only pairwise distances are known, and feature-based outlier detection methods cannot directly be applied. Considering these observations, and given the success...

journal article 2023

document

Outlier detection in time series: The Random Projection Outlier Ensemble

Freyer, Caroline (author)

Outlier detection in time series has important applications in a wide variety of fields, such as patient health, weather forecasting, and cyber security. Unfortunately, outlier detection in time series data poses many challenges, making it difficult to establish an accurate and efficient detection method. In this thesis, we propose the Random...

master thesis 2022

document

Machine learning based time-series postprocessing for the interferometric SAR remote sensing data

Kaźmierczak, Adrianna (author)

A satellite remote sensing technique, Interferometric Synthetic Aperture Radar (InSAR), is able to provide surface displacement information on a millimeter level. In this study, data from the TerraSAR-X satellite collected in the years 2009-2018 over the area of Amsterdam is used. Even though radar data is a subject to multi-step processing,...

master thesis 2021

document

Graph-aware anomalous network agent detection

Gerçekcioğlu, S.A. (author)

Networks with a large number of participants and a highly dynamic data exchange are better off using a distributed networking system due to network failures in centralized networks. However, with the increase in distributed networking, security problems arise in distributed processes. Injection of malicious data, for example, must be dealt with...

master thesis 2021

document

Local Explanation Methods for Isolation Forest: Explainable Outlier Detection in Anti-Money Laundering

Bergþórsdóttir, Kristin (author)

Machine learning methods like outlier detection are becoming increasingly more popular as tools in the fight against money laundering. In this thesis, we analyse the Isolation Forest outlier detection algorithm in detail and introduce a new local explanation method for Isolation Forest, the MI-Local-DIFFI (Multiple Indicator Local-DIFFI) method....

master thesis 2020

document

Subject-specific identification of three dimensional foot shape deviations using statistical shape analysis

Stanković, Kristina (author), Huysmans, T. (author), Danckaers, Femke (author), Sijbers, Jan (author), Booth, Brian G. (author)

The high prevalence of foot pain, and its relation to foot shape, indicates the need for an expert system to identify foot shape abnormalities. Yet, to date, no such expert system exists that examines the full 3D foot shape and produces an intuitive explanation of why a foot is abnormal. In this work, we present the first such expert system that...

journal article 2020

document

Robust and automatic data cleansing method for short-term load forecasting of distribution feeders

Huyghues-Beaufond, Nathalie (author), Tindemans, Simon H. (author), Falugi, Paola (author), Sun, Mingyang (author), Strbac, Goran (author)

Distribution networks are undergoing fundamental changes at medium voltage level. To support growing planning and control decision-making, the need for large numbers of short-term load forecasts has emerged. Data-driven modelling of medium voltage feeders can be affected by (1) data quality issues, namely, large gross errors and missing...

journal article 2020

document

Advanced Set Bounding Methods for Fault Detection

Ritsma, Folkert (author)

Performance of set based fault detection is highly dependent on the complexity of the set bounding methods used to bound the healthy residual set. Existing methods achieve robust performance with complex set bounding that narrowly define healthy system behavior, yet at the cost of higher computation times. In this thesis a major improvement is...

master thesis 2019

document

Outlier detection in non-Gaussian distributions

Maas, Youri (author)

In this thesis we are going to study outlier detection methods and propose a new method. Classical outlier detection is typically based on the assumption that the data is from a Gaussian/normal distribution. When the underlying distribution of a random sample is heavy tailed, so not normal , it is likely to have some extreme observations which...

bachelor thesis 2019

document

Vibration-based Monitoring of the Zwartewaterbrug: a Machine Learning Approach

de Bruijn, Janno (author)

In the Netherlands there are many bridges that crosses waterways, which are key nodes in the transportation system. The safety and integrity of these bridges is nowadays assessed by (visual) inspections at regular intervals. This approach cannot provide information about damage development in between inspections, leading to potential failure or...

master thesis 2019

document

Exploring normalizing flow for anomaly detection

Pathak, Chinmay (author)

Anomaly detection is a task of interest in many domains. Typical way of tackling this problem is using an unsupervised way. Recently, deep neural network based density estimators such as Normalizing flows have seen a huge interest. The ability of these models to do the exact latent-variable inference and exact log-likelihood calculation with...

master thesis 2019

document

Cross Domain Image Matching in Presence of Outliers

Liu, X. (author), Khademi, S. (author), van Gemert, J.C. (author)

Cross domain image matching between image collections from different source and target domains is challenging in times of deep learning due to i) limited variation of image conditions in a training set, ii) lack of paired-image labels during training, iii) the existing of outliers that makes image matching domains not fully overlap. To this end,...

conference paper 2019

document

A voxel-based methodology to detect (clustered) outliers in aerial lidar point clouds

Griffioen, Simon (author)

To obtain 3D information of the Earth’s surface, airborne LiDAR technology<br/>is used to quickly capture high-precision measurements of the terrain.<br/>Unfortunately, laser scanning techniques are prone to producing outliers<br/>and noise (i.e. wrong measurements). Therefore, a pre-process of the point<br/>cloud is required to detect and...

master thesis 2018

document

Unsupervised Cross Domain Image Matching with Outlier Detection

Liu, Xin (author)

This work proposes a method for matching images from different domains in an unsupervised manner, and detecting outlier samples in the target domain at the same time. This matching problem is made difficult by i) the different domain images that are related but under different conditions (e.g. photos of the same location captured in different...

master thesis 2018