About
55
Publications
18,595
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
547
Citations
Citations since 2017
Introduction
CPO of Optioryx. Optioryx is on a mission to help companies transport less air by optimally stacking items into boxes, boxes on pallets and pallets in trucks. In addition, we optimise the assortment of boxes according to historical item and order profiles.
Publications
Publications (55)
Over the last few years, research in automatic sleep scoring has mainly focused on developing increasingly complex deep learning architectures. However, recently these approaches achieved only marginal improve-ments, often at the expense of requiring more data and more expensive training procedures. Despite all these efforts and their satisfactory...
Medicines based on messenger RNA (mRNA) hold immense potential, as evidenced by their rapid deployment as COVID-19 vaccines. However, worldwide distribution of mRNA molecules has been limited by their thermostability, which is fundamentally limited by the intrinsic instability of RNA molecules to a chemical degradation reaction called in-line hydro...
A paper of Alsinglawi et al was recently accepted and published in Scientific Reports. In this paper, the authors aim to predict length of stay (LOS), discretized into either long (> 7 days) or short stays (< 7 days), of lung cancer patients in an ICU department using various machine learning techniques. The authors claim to achieve perfect results...
Over the last few years, research in automatic sleep scoring has mainly focused on developing increasingly complex deep learning architectures. However, recently these approaches achieved only marginal improvements, often at the expense of requiring more data and more expensive training procedures. Despite all these efforts and their satisfactory p...
This paper introduces pyRDF2Vec, a Python software package that reimplements the well-known RDF2Vec algorithm along with several of its extensions. By making the algorithm available in the most popular data science language, and by bundling all extensions into a single place, the use of RDF2Vec is simplified for data scientists. The package is rele...
The inception of Relational Graph Convolutional Networks (R-GCNs) marked a milestone in the Semantic Web domain as it allows for end-to-end training of machine learning models that operate on Knowledge Graphs (KGs). R-GCNs generate a representation for a node of interest by repeatedly aggregating parametrised, relation-specific transformations of i...
Deep learning techniques are increasingly being applied to solve various machine learning tasks that use Knowledge Graphs as input data. However, these techniques typically learn a latent representation for the entities of interest internally, which is then used to make decisions. This latent representation is often not comprehensible to humans, wh...
PurposeIn this correspondence, we highlight general and domain-specific caveats in the development and validation of prediction models.
Methods
Development and use of the “QUiPP” application, a tool for preterm birth prediction which is supported by the United Kingdom National Health Service, is scrutinised and commented on.
ResultsWe highlight and...
Messenger RNA-based medicines hold immense potential, as evidenced by their rapid deployment as COVID-19 vaccines. However, worldwide distribution of mRNA molecules has been limited by their thermostability, which is fundamentally limited by the intrinsic instability of RNA molecules to a chemical degradation reaction called in-line hydrolysis. Pre...
Messenger RNA-based medicines hold immense potential, as evidenced by their rapid deployment as COVID-19 vaccines. However, worldwide distribution of mRNA molecules has been limited by their thermostability, which is fundamentally limited by the intrinsic instability of RNA molecules to a chemical degradation reaction called in-line hydrolysis. Pre...
As Knowledge Graphs are symbolic constructs, specialized techniques have to be applied in order to make them compatible with data mining techniques. RDF2Vec is an unsupervised technique that can create task-agnostic numerical representations of the nodes in a KG by extending successful language modeling techniques. The original work proposed the We...
A recently published study [1] proposed a machine learning classifier to detect preterm birth at an early stage of the pregnancy by making use of an envelope created from Fourier coefficients. The evaluation of this system within this study is, however, fundamentally flawed which resulted in overly optimistic near-perfect predictive performance mea...
In the time series classification domain, shapelets are subsequences that are discriminative of a certain class. It has been shown that classifiers are able to achieve state-of-the-art results by taking the distances from the input time series to different discriminative shapelets as the input. Additionally, these shapelets can be visualized and th...
Information extracted from electrohysterography recordings could potentially prove to be an interesting additional source of information to estimate the risk on preterm birth. Recently, a large number of studies have reported near-perfect results to distinguish between recordings of patients that will deliver term or preterm using a public resource...
Background
Leveraging graphs for machine learning tasks can result in more expressive power as extra information is added to the data by explicitly encoding relations between entities. Knowledge graphs are multi-relational, directed graph representations of domain knowledge. Recently, deep learning-based techniques have been gaining a lot of popula...
At the end of 2019, Chinese authorities alerted the World Health Organization (WHO) of the outbreak of a new strain of the coronavirus, called SARS-CoV-2, which struck humanity by an unprecedented disaster a few months later. In response to this pandemic, a publicly available dataset was released on Kaggle which contained information of over 63,000...
As KGs are symbolic constructs, specialized techniques have to be applied in order to make them compatible with data mining techniques. RDF2Vec is an unsupervised technique that can create task-agnostic numerical representations of the nodes in a KG by extending successful language modelling techniques. The original work proposed the Weisfeiler-Leh...
This paper contributes to the pursuit of leveraging unstructured medical notes to structured clinical decision making. In particular, we present a pipeline for clinical information extraction from medical notes related to preterm birth, and discuss the main challenges as well as its potential for clinical practice. A large collection of medical not...
Information extracted from electrohysterography recordings could potentially prove to be an interesting additional source of information to estimate the risk on preterm birth. Recently, a large number of studies have reported near-perfect results to distinguish between recordings of patients that will deliver term or preterm using a public resource...
tslearn is a general-purpose Python machine learning library for time series that offers tools for pre-processing and feature extraction as well as dedicated models for clustering, classification and regression. It follows scikit-learn’s Application Programming Interface for transformers and estimators, allowing the use of standard pipelines and mo...
A large portion of structured data does not yet reap the benefits of the Semantic Web, or Web 2.0, as it is not semantically annotated. In this paper, we propose a system to generates semantic knowledge, available on DBPedia, from common CSV files. The "Tabular Data to Knowledge Graph Matching" competition, consisting of three different subchalleng...
Deep-learning based techniques are increasingly being used for different machine learning tasks on knowledge graphs. While it has been shown empirically that these techniques often achieve better pre-dictive performances than their classical counterparts, where features are extracted from the graph, they lack interpretability. Interpretability is a...
In the time series classification domain, shapelets are small time series that are discriminative for a certain class. It has been shown that classifiers are able to achieve state-of-the-art results on a plethora of datasets by taking as input distances from the input time series to different discriminative shapelets. Additionally, these shapelets...
Vermeire, KM, Vandewiele, G, Caen, K, Lievens, M, Bourgois, JG, and Boone, J. Training progression in recreational cyclists: no linear dose-response relationship with training load. J Strength Cond Res XX(X): 000-000, 2019-The purpose of the study was to assess the relationship between training load (TL) and performance improvement in a homogeneous...
Background:
Mobile apps generate vast amounts of user data. In the mobile health (mHealth) domain, researchers are increasingly discovering the opportunities of log data to assess the usage of their mobile apps. To date, however, the analysis of these data are often limited to descriptive statistics. Using data mining techniques, log data can offe...
Preterm birth is the leading cause of death among young children and has a large prevalence globally. Machine learning models, based on features extracted from clinical sources such as electronic patient files, yield promising results. In this study, we review similar studies that constructed predictive models based on a publicly available dataset,...
Preterm birth is the leading cause of death among children under five years old. The pathophysiology and etiology of preterm labor are not yet fully understood. This causes a large number of unnecessary hospitalizations due to high–sensitivity clinical policies, which has a significant psychological and economic impact. In this study, we present a...
Purpose:
This study aimed to predict the session Rate of Perceived Exertion (sRPE) in soccer and determine the main predictive indicators of the sRPE.
Methods:
A total of 70 External Load Indicators (ELIs), Internal Load Indicators (ILIs), Individual Characteristics (ICs) and Supplementary Variables (SVs) were used to build a predictive model.
Re...
Background
Headache disorders are an important health burden, having a large health-economic impact worldwide. Current treatment & follow-up processes are often archaic, creating opportunities for computer-aided and decision support systems to increase their efficiency. Existing systems are mostly completely data-driven, and the underlying models a...
BACKGROUND
Background: Mobile applications generate vast amounts of user data. In the mHealth domain, researchers are increasingly discovering the opportunities of these data to assess the engagement levels of their developed mobile applications. To date however, the analysis of these data is often limited to descriptive statistics. Using the right...
Background:
Mobile apps generate vast amounts of user data. In the mobile health (mHealth) domain, researchers are increasingly discovering the opportunities of log data to assess the usage of their mobile apps. To date, however, the analysis of these data are often limited to descriptive statistics. Using data mining techniques, log data can offe...
Purpose Mhealth apps generate vast amounts of user data. Increasingly, researchers are discovering the opportunities of these data to assess the engagement levels of their applications. To date however, the analysis of these data is often limited to descriptive analysis. Using the right data mining techniques, application log data can offer signifi...
The advent of Internet-of-Things (IoT) applications, such as environmental monitoring, smart cities, and home automation , has taken the IoT concept from hype to reality at a massive scale. However, more mission-critical application areas such as energy, security and health care do not only demand low-power connectivity, but also highly reliable an...
Models obtained by decision tree induction techniques excel in being interpretable. However, they can be prone to overfitting, which results in a low predictive performance. Ensemble techniques provide a solution to this problem, and are hence able to achieve higher accuracies. However, this comes at a cost of losing the excellent interpretability...
In order to achieve optimal gains from training while reducing the risk of negative effects, athletes must perceive an ideal Internal Training Load. This load is invoked by the training content and individual characteristics. Training sessions are often team-based, although each athlete has his/her own characteristics, making it hard for coaching s...
Conceptual ideas to incorporate prior knowledge into the different phases of a white-box ML process.
Currently, most of white-box machine learning techniques are purely data-driven and ignore prior background and expert knowledge. A lot of this knowledge has already been captured in domain models, i.e. ontologies, using Semantic Web technologies. The goal of this research proposal is to enhance the predictive performance and required training time...
On dense railway networks "such as in Belgium" train travelers are frequently confronted with overly occupied trains, especially during peak hours. Crowdedness on trains leads to a deterioration in the quality of service and has a negative impact on the well-being of the passenger. In order to stimulate travelers to consider less crowded trains, th...
Poster about GENESIM, a technique to convert an ensemble into a single, interpretable model
Models obtained by decision tree induction techniques excel in being interpretable.However, they can be prone to overfitting, which results in a low predictive performance. Ensemble techniques are able to achieve a higher accuracy. However, this comes at a cost of losing interpretability of the resulting model. This makes ensemble techniques imprac...
Projects
Projects (3)
Investigating the use of AI for infection management in the ICU.
Transforming cycling into a social experience
The topic of athlete data in cycling is especially relevant in Flanders, the birthplace of many cycling innovations. Real-time data doesn’t just enable cyclists to get an instant overview of their performance for improved training and strategic decision-making; it also makes cycling a social experience, opening up areas of a market in which novelty and added value are key differentiators.
Addressing new technical challenges in real-time data transmission and analysis
By introducing new technologies in the areas of long-range networks and data analysis, CONAMO will address several innovation goals, including:
- reliable long-range sensor connectivity in high-density networks;
- a semantic reasoning platform that analyses cyclist data to implement individualized and adaptive training models;
- increased user experience during training and collective cycling events and the identification of business opportunities for cyclists, fans and media professionals.
In determining what factors spark increased user experience during actual cycling events, the project intends to extend the data-driven cycling experience from ‘post event’ into ‘during event’.
Taking personal training and collective cycling to the next level
CONAMO will collaborate with diverse partners specializing in the areas of athletic training methods, public engagement, the Internet of Things, networking and big data. Two use cases form the core of the project:
- preparation for the event in the form of training;
- group experience during mass cycling events with a trial planned at a mass cycling event such as the 2018 Tour of Flanders for amateurs.
The project’s living lab will explore how social interaction, storytelling, gamification and smart connections to professional cycling experiences can enhance user experience in both use cases and motivate a wide group of cyclists to train in a healthy way.
Promoting an active lifestyle to a wider group
Fields of investigation and innovation for CONAMO don’t just include the technical and social; the project also seeks to support the creation of a healthier, more responsible and social cycling experience. Cycling continues to grow in popularity around the world, and promoting exercise to a wider group of people is an explicit goal of CONAMO and its collaborators.
