Data Science Summit 2019
The Annual Data Science Summit Eindhoven, organized by DSCE, takes place in the Frits Philips Muziekgebouw in Eindhoven on Tuesday November 12, 2019. The goal of the summit is to show our interesting scientific research that is done in close cooperation with and inspired by industry.
We are very pleased to unveil all speakers for this year’s edition. Prof. Tijl De Bie (Ghent University) will give the keynote this year. In the further plenary program, Prof. Volkher Scharnhorst (Catharina Hospital) will kick off the ‘Data Science for Health’ session, followed by Prof. Panos Markopoulos (TU/e - Industrial Design). Prof. Jan Post (Philips Drachten), Prof. Geert-Jan van Houtum and Dr. Alessandro Di Bucchianico (TU/e - Statistics) will do the same for the ‘Data Science for Industry’ part. This year we will end the program with an interactive panel discussion on Responsible Data Science, with interesting and inspiring panel members. This will certainly lead to exciting follow-up discussions during the network drinks after the formal program.
Read the detailed program below.
Like last years, there will be sufficient time for discussion and hands-on idea sharing during the poster sessions, where you can learn and discuss interesting examples of Data Science methods and applications with practitioners. The day is aimed at a broad audience: from (research) specialists in the field to applicants and practitioners. We want to inspire and give directions for solving your specific challenges.
|Day chair: Wouter Duivesteijn (TU/e - DSCE)|
|09:00||Registration & coffee|
|10:00||Opening||Robert-Jan Smits (TU/e - President of the Executive Board)|
|10:10||Keynote||Tijl De Bie (University of Ghent)||Methods and principles for data exploration|
|10:55||Poster pitches||PhD's / PDs|
|11:15||Posters, coffee & snacks|
|11:45||Data Science for Health||Volkher Scharnhorst (TU/e, Catharina Hospital)||With a little AI from your friends….data turns into information|
|Panos Markopoulos (TU/e - Industrial Design)||What can we learn from play?|
|12:50||Lunch & posters|
|14:20||Data Science for Industry||Jan Post (Philips Drachten, RuG)||Towards digital twins: Predictive maintenance and model based control in zero defect manufacturing|
Geert-Jan van Houtum (TU/e - Maintenance and Reliability) &
Alessandro Di Bucchianico (TU/e - Statistics)
|Insights and challenges from collaboration with industrial partners|
|15:25||Responsible Data Science|
TU/e - Healthy & active ageing
TU/e - Ethics
TU/e - Data Mining
Tilburg University - Law, Technology & Society
Jack van Wijk
TU/e - Visualization
|Interactive panel discussion|
|16:30||Networking drinks & posters|
Tijl De Bie (University of Ghent)
Methods and principles for data exploration
Data science is a fast growing research field, which has already made a vast impact on industry and society. The methods that have contributed most to this success so far tend to be supervised learning methods in various guises. Such methods are easy to build a business case around: one can quantify how much money will be gained, how many lives will be saved, etc. Methods for data exploration, on the other hand, have a more open-ended goal of providing new insights or making discoveries in data. While such methods have also been widely deployed in practice, their uptake is challenged by the fact that business cases for them tend to be less clear and less quantifiable. Moreover, and crucially, it is conceptually unclear to formally quantify how 'good' an insight or a discovery found in data is. This latter problem has been the focus of much research in the past years. This talk will provide a survey of this line of research, with a particular focus on research done funded by my ERC grant FORSIED, and present an overview of current and future challenges.
Biography Tijl De Bie
Tijl De Bie is currently Full Professor at the University of Ghent. Before moving to Ghent, he was a Reader at the University of Bristol, where he was appointed Lecturer (Assistant Professor) in January 2007. Before that, he was a postdoctoral researcher at the KU Leuven (Belgium) and the University of Southampton. He completed his PhD on machine learning and advanced optimization techniques in 2005 at the KU Leuven. During his PhD he also spent a combined total of about 1 year as a visiting research scholar in U.C. Berkeley and U.C. Davis.
He is currently most actively interested in the formalization of subjective interestingness in exploratory data mining, and in the use of machine learning and data mining for music informatics as well as for web and social media mining. He currently holds a grant portfolio of around EUR 4M, including a prestigious ERC Consolidator Grant titled "Formalizing Subjective Interestingness in Exploratory Data Mining" (FORSIED), as well as an FWO Odysseus grant titled "Exploring Data: Theoretical Foundations and Applications to Web, multimedia, and Omics Data".
Volkher Scharnhorst (Catharina Hospital, tu/e)
With a little AI from your friends… data turns into information
TU/e, Catharina Hospital and Máxima Medical Center formally collaborate in the Expert Center Clinical Chemistry Eindhoven (ECKCE). The ECKCE aims to improve health care through development, clinical validation and implementation of novel analytical tests and by integrating data to enhance effective clinical decision making. During the presentation several examples will be given of how algorithms - by turning data into clinically actionable data - have improved patient care. Large data sets are needed to build robust algorithms. It often is hard to obtain the required data. Reasons for that and possible solutions are discussed during the talk.
Biography Volkher Scharnhorst
Volkher Scharnhorst studied medical biology in Cologne and Leiden and received his PhD from the University of Leiden on molecular determinants of Wilms’ tumor. After his residency as a clinical chemist In Máxima Medisch Centrum, he worked in Atrium Medisch Centrum en since 2006 in Catharina Ziekenhuis. Since 2014, he is part-time professor of Clinical Chemistry with the research group Chemical Biology at the department of Biomedical Engineering of Eindhoven University of Technology. His research focuses on the use of biomarkers in diagnosing and monitoring disease, with an emphasis on the improvement of analytical techniques and interpretation of test results. In his profession as a clinical chemist Scharnhorst is committed to translating the analysis results from the laboratory into information that is of relevance to doctors in their treatment of patients. His areas of focus here are diagnostics of malignant diseases and research into biomarkers of cardiovascular diseases.
Panos Markopoulos (TU/e, Industrial Design)
What can we learn from play?
This talk shall review the design of a number of games designed with the purpose of supporting motor learning, social skills, and encouraging physical activity and social interaction for various user groups emphasizing on the role of embodiment in interaction. It will also demonstrate how games can be valuable media for learning about people and I discuss the potential and limits of player modelling. The talk shall conclude with some general lessons and challenges for future work in this area.
Biography Panos Markopoulos
Panos Markopoulos is a professor in the department of Industrial Design on the topic of Design for Behaviour Change. Previously, he has held research positions at Queen Mary, University of London, and at Philips Research. He has co-founded the Interaction Design and Children series of conferences and International Journal of Child Computer Interaction by and is currently serving as chief editor in Behaviour and Information Technology (Taylor and Francis). His work spans sevearl topics of nteraction design and human computer interactionsuch as awareness systems, technologies for learning, rehabilitation technologies, and wearable technologies for healthcare.
Jan Post (Philips Drachten, RuG)
Towards Digital Twins: Predictive Maintenance and Model Based Control in Zero Defect Manufacturing
Big data and knowledge based design becomes more and more popular in industry as a part of Industry 4.0. On the one hand, in the development area, knowledge based design of process and product become mature and more easy to use in Computer Aided Engineering. On the other hand sensors, data analytics and predictive maintenance are introduced in -new- production platforms. The question is how to combine and fuse data based on model-based systems engineering and data based on real-time measurements to make it useful for future process control to create more autonomy. Philips Drachten is working in this subject in the area of high precision parts made from stainless steel. This presentation will give an overview about what Public Private partnership can do on these subjects, how they contribute to the domains of process development, predictive maintenance and process control and will envision this will lead to future digital twins for model based process control, predictive maintenance and zero defect manufacturing.
Biography Jan Post
Over a period of more than 35 years Jan Post was involved in the co-operation of Philips and academic research initiating research on Advanced manufacturing and the guidance of students and the valorization of that research at Philips Personal Care. Most of the research is/was in the domain of Computational Mechanics, Material development and digitalization of Industry. In his current position he is responsible for the Public Private Partnerships of Philips Drachten, Professor Digital Fabrication at the university Groningen, project lead of the Smart Industry Field lab “Region of Smart Factory”, responsible for the HTSM roadmap Smart Industry and figurehead of the NWA-Smart Industry.
Allesandro di bucchianico (tu/e - statistics)
geert-jan van Houtum (tu/e - Maintenance and Reliability)
Insights and Challenges from Collaboration with Industrial Partners
We present an overview of several projects that members of the Research Programme on smart manufacturing and maintenance carry out in collaboration with industrial partners. The goal of this overview is to highlight insights and lessons learned from past projects. Looking at the future, we identify major trends and challenges in smart manufacturing and maintenance. We will show how we intend to address these challenges in current and upcoming projects. In particular, we will present the upcoming PrimaVera (Predictive maintenance for Very effective asset management) project, one of the 17 projects of the Dutch National Science Agenda projects.
Biography Alessandro Di Bucchianico
Alessandro Di Bucchianico is Associate Professor of Statistics at TU/e. From 2007 to 2011 he was Deputy Head of LIME (Laboratory for Industrial Mathematics Eindhoven). He was quarter master of the Data Science Center Eindhoven. At a national level, he is one of the two coordinators of the Studygroups Mathematics with Industry (http://www.swi-wiskunde.nl), which is a core activity of Innovation Committee of the Dutch Mathematics Platform. Moreover, he is a member of the Big Data team of the Applied Mathematics Institute of the 4 technical universities in the Netherlands. His areas of expertise are statistical process control and reliability theory (both hardware reliability and software reliability). He carries out research on monitoring and lifetime predictions in the context of industrial processes. In particular, his focus is on predictive maintenance. Much of this research is carried out in cooperation with the industry through national and international projects.
Biography Geert-Jan van Houtum
Geert-Jan van Houtum is Full Professor and chair of Maintenance and Reliability at TU/e since 2008. Since September 2017, he is also vice-dean IE of the Department IE &IS. His areas of expertise include maintenance optimization, spare parts inventory control, inventory theory in general, and operations research. Geert-Jan carries out research on the maintenance and reliability of capital goods. In particular, his focus is on design and control of spare parts networks, predictive maintenance concepts, and product design choices that have a strong effect on system availability and TCO. In this research, also the value of remote monitoring data and other degradation data is investigated. Much of this research is carried out in cooperation with the industry, working with companies such as ASML, Dutch Railways, Philips, Océ, Marel, the Royal Dutch Airforce and Navy, and Vanderlande.
yuan lu (tu/e - Healthy & active ageing)
Yuan Lu is Associate Professor of Design for Healthy and Active Ageing at TU/e ID. She also holds a position as Guest Professor at the School of Software Technology at Zhejiang University in China. She has a background in mathematics, industrial engineering and innovation sciences. She carries out research to explore the use of technology probes to create personalised motivational strategies to promote healthy and active ageing. Together with the related multi-stakeholders including technological companies, care organisations, hospitals, communities, other knowledge institutions and etc, she follows an ecological approach to create sustainable values for all parties involved. Lu has been leading and participating in a number of national and EU research projects in the area of design for healthy and active ageing, including the CRISP Grey but Mobile project in the Netherlands and the Horizon 2020 REACH project in Europe. She has been a member of the advice board to the Province Brabant in the area of Healthcare since 2017.
VINCENT Müller (tu/e - ETHICS)
Vincent C. Müller studied philosophy with cognitive science, linguistics and history at the universities of Marburg, Hamburg, London and Oxford. He was Stanley J. Seeger Fellow at Princeton University and James Martin Research Fellow at the University of Oxford. He is now Professor of philosophy at Technical University of Eindhoven (TU/e), University Fellow at the University of Leeds and Turing Fellow at the Alan Turing Institute, London - as well as President of the European Society for Cognitive Systems and Chair of the euRobotics topics group on 'ethical, legal and socio-economic issues’. Müller's research focuses on theory and ethics of disruptive technologies, particularly artificial intelligence. Müller organizes a conference series on the Theory and Philosophy of AI and is principal investigator of a EU-funded project on "Inclusive Robotics for a Better Society" (INBOTS) and on the large platform project AI4EU. He has generated ca. 3.9 mil.€ research income for his institutions.
mykola pechenizkiy (tu/e - data mining)
Mykola Pechenizkiy is Professor of Data Mining at the Department of Mathematics and Computer Science. His core expertise and research interests are in predictive analytics and its application to real-world problems in industry, medicine and education. At DCSE he leads the Customer Journey and Responsible Data Science interdisciplinary research programs aiming at developing techniques for informed, accountable and transparent analytics. As principal investigator of several applications-inspired research projects he aims at developing foundations for next generation predictive analytics and demonstrating their ecological validity in practice. Over the past decade he has co-authored more than 100 peer-reviewed publications and served on the program committees of the leading data mining and AI conferences.
linnet taylor (tilburg university - tilt)
Linnet Taylor is Associate Professor at the Tilburg Institute for Law, Technology, and Society (TILT). Her research focuses on digital data, representation and democracy, with particular attention to transnational governance issues. She leads the ERC Global Data Justice project, which aims to develop a a conceptual framework for the ethical and beneficial governance of data technologies on the global level. The research is based on insights from technology users, providers and activists around the world.
jack van wijk (tu/e - visualization)
Jack van Wijk is full professor in Visualization at TU Eindhoven, and scientific director of the Data Science Center Eindhoven and of the PDEng program Data Science. His main research interests are information visualization and visual analytics, aiming to provide insight using a combination of clear visual representations, smooth interaction, and integration of methods from statistics, machine learning and data mining. He currently focuses on providing insight in predictive analytics: given an outcome, how can we understand the reasoning followed by complex models?