Data Science Week Spring 2025
What is the Data Science Week?
The goal of the data science week is to introduce interested students and staff to data science in a fun and cooperative way, and help create a community of data scientists at the University of Twente, the faculty of Behavioural and Management Sciences, and beyond. BDSi and DSI organize various events during the week, including a datathon, contextual speakers, expert lectures, hands-on workshops, and a networking drink.
During the lunch breaks expert data scientists will provide lectures on the most important tools in a data scientists’ toolbox; data wrangling, modelling, and communicating results. These lectures will be structured to support the datathon materials, but can be attended without participating in the datathon itself. The lectures are followed by a hands-on practical session in which the lunch lecturerer - supported by a team of motivated coaches - will guide participants in applying the lecture materials to their datathon submissions.
(Guest) speakers will be invited during the week to provide a deeper background in the topics and methods covered in the lectures and datathon, or to put these topics in a broader context. Throughout the week there will be ample time for socialization and networking, as well as a poster presentation session and networking drink on Thursday afternoon.
Lunch talks, data science workshops, and datathon
You can now sign up for the various lunch talks, the datathon, and the workshops. Places are limited, so sign up now!
Data Science Drinks & Poster Session
Come join us for a drink, updates on the latest BMS Data Science in research, and an excellent networking opportunity!
Datathon
A datathon is an event in which teams collaborate and compete to create a solution to a shared problem. By learning from experts and peers and immediately applying your skills on a relevant and engaging real-world dataset, the BDSi datathons provide a great environment for both students and staff, beginners and experts to further hone their skills. For the spring 2025, we will have a new and rewarding data challenge using physiological data gathered from and by participants.
Speakers
(Almost) every lunch break (12:45 - 13:30), expert speakers from across the University of Twente and beyond will give talks on various topics surrounding digital phenotyping. From a broad overview of the roots and likely future of the field, practical applications for social research, to legal and ethical implications - there is something here for everyone to enjoy. All the talks are meant to broaden and enrich the discussion around the data science week, and can be enjoyed with or without participating in the datathon or any of the workshops.
Lucas Noldus is professor in Behavior, Information Technology and Innovation at Radboud University in Nijmegen, and founder and CEO of Noldus Information Technology, a developer of software tools and integrated measurement systems for the study of human and animal behavior, headquartered in Wageningen. Noldus’ systems have found their way into thousands of academic and industrial research labs around the world.
sHe has (co)authored more than 140 papers and conference presentations about methods and techniques in behavioral research. In 2023 he was elected as Fellow of the Netherlands Academy of Engineering. Besides his corporate and academic work, Lucas serves on a range of boards and committees related to science, innovation and sustainability.
Matthijs Noordzij is Full Professor of Health Psychology and Persuasive Technology and directs the Health Dynamics & Self Management Lab at the University of Twente in The Netherlands.
His research and education focuses on exploring the scientific foundations and design principles for integrating sensor technology in (mental) healthcare and self-management.
His vision is to develop health technology that aligns with core human values such as compassion, while striving to create innovative solutions that enhance the way we interact with technology in healthcare settings.
Arlene John is an Assistant Professor at the Biomedical Signals and Systems (BSS) group at the University of Twente. She completed her PhD on data fusion frameworks for wearable health monitoring devices at University College Dublin, and has previously worked on Machine Learning Mathematics at Qualcomm and ASML.
Her current research interests include biomedical signal processing, machine learning and inference, explainable AI, and multisensor data fusion.
Ying Wang is an Assistant Professor at the Biomedical Signals and Systems (BSS) group at the University of Twente.
Her research is interdisciplinary, and applies and develops multi-modal model-based signal processing, sensing and physiological system modeling techniques in the healthcare field. Her main research interest is remote continuous monitoring of individual’s physiological signs (such as, heart activty) and body movement in daily life for personalized disease prevention and management.
She is especially enthusiastic in using her expertise to tackle challenges surrounding the daily monitoring of physiological (brain and body) responses to dynamic physical activities for different healthcare purposes, such as, helping people stay in healthy and tracking patients' disease symptoms for disease management.
Annemieke Witteveen is Associate Professor at the Biomedical Signals and Systems (BSS) group and the Personalized eHealth Technology (PeHT) research program.
Her research line focusses on building dynamic patient-level models for personalized prediction, monitoring and optimization to support clinical decision making in oncology.
As PI, Annemieke coordinates several large projects on self-management and decision support for oncology, such as the KWF PARTNR project for optimal cancer-related fatigue treatment and the €6.32M 4TU research program RECENTRE on lifestyle and risk-based monitoring.
Jorge Piano Simões is an Assistant Professor in the Psychology, Health, and Technology (PHT) section.
His research sits at the intersection of psychology, eHealth, and machine learning, focusing on the development and evaluation of app-based Just-in-Time Adaptive Interventions (JITAIs) to personalize mental health care for individuals with mood disorders.
To enhance digital interventions, he integrates tools such as ecological momentary assessment, biosignal monitoring via smartwatches, and smartphone-based digital phenotyping to capture behavioral patterns and inform adaptive treatment strategies.
Peter Slijkhuis is a psychologist who focuses on human behavior and technology, with a special interest in how people use and interact with technology (Usability Testing and UX Research). He is the educational coordinator at BMS Lab, responsible for creating course materials explaining and using the equipment that BMS Lab provides.
He has extensive experience with eye-tracking, virtual and augmented reality, facial and body motion tracking, wearables and more.
Stay tuned for updates!
We’re coordinating with speakers inside and outside the UT, and will update the website once more details are known.
Lectures & Practicals
In the afternoon (13:45 - 15:30, Tuesday - Friday) expert data scientists from BDSi and our partners will provide a lecture on the most important tools in a data scientists’ toolbox; data wrangling, feature engineering, modelling, and communicating results. These lectures will be structured to support the datathon materials, but can be attended without participating in the datathon itself.
After a short coffee break, the lecture will be followed by a hands-on practical session (~14:45 - 15:30). During these this time, the lecturer - supported by a team of motivated coaches - will support participants in applying the lecture materials to their datathon submissions. While these sessions are meant to accompany the days’ lecture, they can be attended by any datathon participants. Coaches will be on hand to answer any questions about the days’ lecture, the datathon, or data science in general.
Posters & Drinks
On thursday afternoon, we invite all data science week participants as well as anyone interested in data science at the University of Twente to join us for a poster presentation and drinks. This is a great opportunity to mingle with the other teams, and create lasting connections with peers and data science experts!
Certificates & TGS credits
All participants in the Datathon will get a signed certicifate of participation, listing the lectures and workshops they attended. PhD candidates (and of course PdEng, etc.) who attend the lectures and workshops and participated in the datathon receive a Twente Graduate School (TGS) certificate for 0.5 ECTS.
Competition
The team with the best solution will receive the coveted BDSi Data Science trophy. All teams will also be asked to share their solutions, problems, and learning experience during the final presentations.
Who can join?
Staff, students, family, and friends
Everyone related to the University of Twente and their friends and family can join any of the events during the Data Science Week. The lunch talks in particular are meant to be open to everyone who has an interest in the topic.
The datathon is open to both novices and experts, and everyone in between. You can join as a team, alone, or skip it altogether and only participate in the workshops. As long as one person in the team is affiliated with the University of Twente, you’re free (in fact, encouraged!) to invite friends, (external) colleagues, and/or family to join your team. If you do join alone, you can choose to be assigned to a team with other data science enthusiasts, or go at it alone.
What is required to compete in the datathon?
Some experience with R or Python
Some programming knowledge is required!
You'll need to have a basic idea of either R or Python in order to follow along with the lectures and practicals. Materials will always be prepared for R, and when possible for Python as well.
While we will do our best to introduce data science topics in the various workshops without relying on code, a basic understanding of R and/or Python will make it much easier to follow along.
If you have some experience with other programming languages, you should be able to follow along with a little preparation. More information on installing and using R can be found in the What can I do to prepare for the datathon? section.
If you're new to programming in general or would like a deeper understanding of R, and would rather learn from one of our colleagues, the Cognition, Data and Education (CoDE) section provides courses and materials aimed at teaching staff and Johannes Steinrücke teaches half-day introduction to R and data visualization in R workshops for PhD's (and EngD's).
If you’re confident you can participate in the datathon in another programming language, you’re more than welcome to do so (we challenge you to try in C, Fortran, Brainf***, or JavaScript). Just be aware that we probably can’t offer support if or when you get stuck.
What can I do to prepare for the datathon?
Get a team
First off, get a team together. The datathon is meant to be a collaborative experience where you work alongside a variety of expertises. While you can compete on your own, we strongly suggest working together.
Set up your coding environment
If you’re new to data science, you’ll want to set up a working environment. We recommend working in R or Python, depending on your experience.
Install R and RStudio, and prepare a working environment - Our colleague Johannes Steinrücke has written a good guide on how to set up R and RStudio for your projects, including some practical advice not covered in many other sources. The guide was written for students starting with coursework with R, but is equally applicable for other data science projects.
Install Python - The Women in Data Science team maintains a set of tutorials on installing Python (using Anaconda to manage packages and environments), Jupyter notebooks and the basics of Python data structures: https://github.com/keikokamei/WiDS_Datathon_Tutorials.
Further reading
If you’re looking for more information, a competitive edge, or just a good way to spend some time, we can recommend some more reading materials:
An Introduction to Statistical Learning is a free to download book providing an excellent introduction to practical machine learning using both R and Python.
R for Data Science is a free online book compiled by Hadley Wickham and a long list of community contributors, covering the whole gamut of modern data science in R. It is well worth a look, and a good reference even for experienced data scientists.
Kaggle.com provides resources to get started with Kaggle, as well as a long list of competitions that are approachable for beginners - with code and discussions available from hundreds of other participants. Trying your hand at a competition or two is a good way to spend a rainy weekend.
Sharada Kalanidhi has written an excellent deep dive into the 2023 WiDS datathon, including links to further resources for both R and Python: https://www.widsworldwide.org/get-inspired/blog/a-data-scientists-deep-dive-into-the-wids-datathon/.
Lunch talks, data science workshops, and datathon
You can now sign up for the various lunch talks, the datathon, and the workshops. Places are limited, so sign up now!
Data Science Drinks & Poster Session
Come join us for a drink, updates on the latest BMS Data Science in research, and an excellent networking opportunity!
Schedule
The spring 2025 Data Science Week takes place from March 3rd to March 10th. There will be an opening lecture and talk introducing the topic, the schedule for the week, and the technicalities of competing in the datathon.
The rest of the week, there will be lunch talks on topics surrounding digital phenotyping, followed by lectures on core data science skills and practicals applying those skills to the problem in the datathon. The data science week closes on Monday the 10th with presentations from the competing datathon teams, and a final keynote.
Further details will be made available in the coming weeks and months.
Monday
March 3
Digital phenotyping: of mice and men, babies and business
12:45 - 13:30, Location: Citadel T300
Lucas Noldus is professor in Behavior, Information Technology and Innovation at Radboud University in Nijmegen, and founder and CEO of Noldus Information Technology, a developer of software tools and integrated measurement systems for the study of human and animal behavior, headquartered in Wageningen. Noldus’ systems have found their way into thousands of academic and industrial research labs around the world.
sHe has (co)authored more than 140 papers and conference presentations about methods and techniques in behavioral research. In 2023 he was elected as Fellow of the Netherlands Academy of Engineering. Besides his corporate and academic work, Lucas serves on a range of boards and committees related to science, innovation and sustainability.
The desire of humans to observe and describe the behavior of other organisms – their behavioral phenotype – is thousands years old, as we know from the writings of Aristotle (4th century BC). More recently, halfway the 20th century, Nobel laureates Tinbergen, Lorenz and Von Frisch taught us the importance of systematic observation and registration as a way to understand the mechanism and development of behavior, and founded the scientific discipline of ethology. Since then, generations of behavioral biologists and psychologists have collected behavioral data through observation and manual annotation. With the advent digital image processing in the 1980s, it became possible to automate this labor-intensive and error-prone process, and digital phenotyping was born.
The earliest applications of this novel technique were limited to movement tracking of small animals in controlled laboratory assays, such as insects and rodents. Since then, developments have accelerated: recording with two cameras allowed the 3D tracking of flying insects or swimming fish, ultrawideband technology enabled accurate tracking of animals or humans in large spaces, and inertial sensing with 3D accelerometers and gyroscopes opened the door to posture estimation and behavior recognition. A recent example is the design of a Smart Baby Suit for monitoring the neurodevelopment of babies at risk of a genetic disorder. With increasingly powerful CPUs, GPUs and AI models, we can perform pattern recognition on just about any image stream, audio signal or motion data. These developments have brought countless opportunities to advance biomedical research, healthcare and affective computing, which has led to a thriving business of digital phenotyping tools.
However, these technologies can theoretically also be used for purposes that could harm people, which is why the European Commission has enacted the AI Act, which prohibits AI-based certain types of digital phenotyping. As a research community, we should keep a dialog with policymakers to make sure that society can reap the benefits of promising technologies while risks are mitigated.
Datathon: kick-off
13:45 - 14:30, Location: Citadel T300
Introduction to the datathon, finding and matching teams.
Datathon: Gathering data
14:45 - 16:30, Location: Citadel T300
Digital phenotyping often relies on highly personalized data. What could be more personalized than working on data gathered by and from you and the other participants? We will use real physiological measurements in a simple and fun experimental design to gather data from participants, for participants.
Tuesday
March 4
From Signals to Insights: Validity and Applications of Ambulatory Physiological Monitoring
12:45 - 13:30, Location: Citadel T300
Matthijs Noordzij is Full Professor of Health Psychology and Persuasive Technology and directs the Health Dynamics & Self Management Lab at the University of Twente in The Netherlands.
His research and education focuses on exploring the scientific foundations and design principles for integrating sensor technology in (mental) healthcare and self-management.
His vision is to develop health technology that aligns with core human values such as compassion, while striving to create innovative solutions that enhance the way we interact with technology in healthcare settings.
Advances in wearable technology have made it possible to continuously track physiological signals such as heart rate variability, skin conductance, and respiration in everyday life. This form of passive sensing provides valuable insights into stress, emotion regulation, and mental health, moving beyond the limitations of laboratory studies. In this talk, I will introduce the principles of ambulatory physiological monitoring, discuss the validity of current measurement techniques, and explore their potential applications in research and clinical practice. While these methods offer exciting opportunities, challenges remain in ensuring data quality, interpreting physiological signals in context, and addressing ethical concerns. By critically examining both the promise and limitations of these tools, we can better understand how to integrate them into studies and applications in a meaningful and responsible way.
Workshop: Data Wrangling
13:45 - 15:30, Location: Citadel T300
Cleaning and combining datasets, (visually) exploring data and patterns, preparing raw data for further analysis.
Wednesday
March 5
Advancing Digital Phenotyping: From Physiological Time Series Data to Real-Life Multimodal Health Monitoring.
12:45 - 13:30, Location: Citadel T300
Arlene John is an Assistant Professor at the Biomedical Signals and Systems (BSS) group at the University of Twente. She completed her PhD on data fusion frameworks for wearable health monitoring devices at University College Dublin, and has previously worked on Machine Learning Mathematics at Qualcomm and ASML.
Her current research interests include biomedical signal processing, machine learning and inference, explainable AI, and multisensor data fusion.
Ying Wang is an Assistant Professor at the Biomedical Signals and Systems (BSS) group at the University of Twente.
Her research is interdisciplinary, and applies and develops multi-modal model-based signal processing, sensing and physiological system modeling techniques in the healthcare field. Her main research interest is remote continuous monitoring of individual’s physiological signs (such as, heart activty) and body movement in daily life for personalized disease prevention and management.
She is especially enthusiastic in using her expertise to tackle challenges surrounding the daily monitoring of physiological (brain and body) responses to dynamic physical activities for different healthcare purposes, such as, helping people stay in healthy and tracking patients' disease symptoms for disease management.
This talk explores the journey from physiological time-series data to multimodal data analysis for digital phenotyping, emphasizing the transition from controlled semi-lab environments to real-life health monitoring. The challenges and some innovations in daily-life health monitoring required to sense information unobtrusively to enable the development of personalized phenotypes for continuous health tracking is discussed. Key topics include both wireless and wearable sensing techniques, multimodal feature extraction, identifying interrelationships amongst features, and connecting these insights to individual phenotypes.
Additionally, we examine methods for monitoring health trends over extended periods. Practical applications discussed will include energy expenditure monitoring during daily physical activity for people with risk of obesity, cardiac function monitoring for people with long term diabetes, psychophysiological condition monitoring for people with knee osteoarthritis, recovery tracking post-colorectal surgery using patch sensors, and smartphone-based digital phenotyping for breast cancer survivors.
Workshop: Feature Engineering
13:45 - 15:30, Location: Citadel T300
How to go from ‘raw’ sensor data to usable signals or ‘features’. We will provide some background and context for the choices you will have to make (or that are made for you with commercial products), and implement a basic pipeline for extracting features from raw signals data in R.
Thursday
March 6
Hands-on workshop digital phenotyping: fitting a framework and opportunities and challenges
12:45 - 13:30, Location: Citadel T300
Annemieke Witteveen is Associate Professor at the Biomedical Signals and Systems (BSS) group and the Personalized eHealth Technology (PeHT) research program.
Her research line focusses on building dynamic patient-level models for personalized prediction, monitoring and optimization to support clinical decision making in oncology.
As PI, Annemieke coordinates several large projects on self-management and decision support for oncology, such as the KWF PARTNR project for optimal cancer-related fatigue treatment and the €6.32M 4TU research program RECENTRE on lifestyle and risk-based monitoring.
Jorge Piano Simões is an Assistant Professor in the Psychology, Health, and Technology (PHT) section.
His research sits at the intersection of psychology, eHealth, and machine learning, focusing on the development and evaluation of app-based Just-in-Time Adaptive Interventions (JITAIs) to personalize mental health care for individuals with mood disorders.
To enhance digital interventions, he integrates tools such as ecological momentary assessment, biosignal monitoring via smartwatches, and smartphone-based digital phenotyping to capture behavioral patterns and inform adaptive treatment strategies.
In this workshop, participants will be introduced to key concepts related to digital phenotyping, including definitions, existing frameworks linking behavior, emotions, and physical states and digital traces, as well as clinical opportunities and barriers for implementing this tool. During the workshop, participants will also have the opportunity to critically evaluate how digital traces can be translated into clinical applications with a hands-on assignment. Lastly, participants will be presented to the state-of-the-art overview of how machine learning methods are being leveraged with digital phenotyping to improve and personalize care.
Workshop: Modelling
13:45 - 15:30, Location: Citadel T300
Introduction to modelling and machine learning in R.
Posters & Drinks
16:00 - 18:00, Location: TBA
(Social) networking with other participants, and other University of Twente students and staff interested in data science.
Friday
March 7
(to be announced...)
12:45 - 13:30, Location: Citadel T300
Workshop: Modelling II
13:45 - 15:30, Location: Citadel T300
More in-depth continuation of modelling, implications of different modeling choices and ‘fairness’ in AI models. [Note: exact contents may still change]
Sunday
March 9
Datathon: Submission deadline
23:59 - , Location:
Deadline for datathon submissions on the leaderboard.
Monday
March 10
Practical wearables: overview and demonstration of equipment available at BMS Lab
12:45 - 13:30, Location: Citadel T300
Peter Slijkhuis is a psychologist who focuses on human behavior and technology, with a special interest in how people use and interact with technology (Usability Testing and UX Research). He is the educational coordinator at BMS Lab, responsible for creating course materials explaining and using the equipment that BMS Lab provides.
He has extensive experience with eye-tracking, virtual and augmented reality, facial and body motion tracking, wearables and more.
Peter Slijkhuis will give an overview of equipment available at BMS Lab, and how it can be useful for social science. [Note: exact contents may still change]
Datathon: Team presentations
13:45 - 14:30, Location: Citadel T300
Presentations by the datathon participants. Solutions, challenges, and lessons learned.
Datathon: Prize ceremony
14:45 - 15:00, Location: Citadel T300
Prizes for the best and most innovative teams.
Final keynote
15:00 - 15:30, Location: Citadel T300
Final keynote speech and official closing of the Data Science Week.
Lunch talks, data science workshops, and datathon
You can now sign up for the various lunch talks, the datathon, and the workshops. Places are limited, so sign up now!
Data Science Drinks & Poster Session
Come join us for a drink, updates on the latest BMS Data Science in research, and an excellent networking opportunity!