Sponsors

Itility

www.itility.nl.

Platinum Sponsor
Portfolio Item

cis.ieee.org

Technical Co-Sponsor
Portfolio Item

is.tm.tue.nl

Organization
Portfolio Item

www.nippur.nl

Silver Sponsor
Portfolio Item

www.eusflat.org

Technical Co-Sponsor
Portfolio Item

www.tue.nl

Organization
Portfolio Item

www.ortec-consulting.com

Silver Sponsor
Portfolio Item

Orangegames.com

Silver Sponsor
Portfolio Item

www.ieee.org

Technical Co-Sponsor
Portfolio Item

ewh.ieee.org/r8/benelux/cis/main.html

Technical Co-Sponsor
Portfolio Item

www.nwo.nl/en

Organization
Portfolio Item

www.siks.nl

Organization
iPhone Black iPhone White iPhone White

Proceedings

Committee

Program Committee

Uzay Kaymak

Uzay Kaymak
Eindhoven University of Technology
The Netherlands

General Chair
Anna Wilbik

Anna Wilbik
Eindhoven University of Technology
The Netherlands

Finance Chair
Susana Vieira

Susana Vieira
IDMEC, Instituto Superior Técnico, Universidade de Lisboa, Portugal

Publication Chair
Marie-Jeanne Lesot

Marie-Jeanne Lesot
Université Pierre et Marie Curie
France

Program Chair
Rui Jorge Almeida

Rui Jorge Almeida
Eindhoven University of Technology
The Netherlands

Publicity Chair
Bernadette Bouchon-Meunier

Bernadette Bouchon-Meunier
Université Pierre et Marie Curie
France

Executive Directors
Ronald R. Yager

Ronald R. Yager
Iona College
USA

Executive Directors
João Paulo Carvalho

João Paulo Carvalho
INESC-ID, Instituto Superior Técnico
Universidade de Lisboa, Portugal

Program Chair
João M. C. Sousa

João M. C. Sousa
IDMEC, Instituto Superior Técnico, Universidade de Lisboa, Portugal

Special Session Chair
Paul W.P.J. Grefen

Paul W.P.J. Grefen
Eindhoven University of Technology
The Netherlands

Sponsor Chair

Advisory Board

Giulianella Coletti (Italy)
Miguel Delgado (Spain)
Mario Fedrizzi (Italy)
Laurent Foulloy (France)
Salvatore Greco (Italy)
Julio Gutierrez-Rios (Spain)
Eyke Hüllermeier (Germany)

Anne Laurent (France)
Luis Magdalena (Spain)
Christophe Marsala (France)
Benedetto Matarazzo (Italy)
Manuel Ojeda-Aciego (Spain)
Maria Rifqi (France)
Lorenza Saitta (Italy)

Olivier Strauss (France)
Enric Trillas (Spain)
Llorenc ̧ Valverde (Spain)
José Luis Verdegay (Spain)
Maria-Amparo Vila (Spain)
Lotfi A. Zadeh (USA)

International Program Committee

Rui J. Almeida (Netherlands)
Michal Baczynski (Poland)
Nalan Bastürk (Netherlands)
Gleb Beliakov (Australia)
Radim Belohlavek (Czech Republic )
Salem Benferhat (France)
Jim Bezdek (USA)
Isabelle Bloch (France)
Ulrich Bodenhofer (Austria)
Piero Bonissone (USA)
Bernadette Bouchon-Meunier (France)
Humberto Bustince (Spain)
Guoqing Chen (China)
Esma Nur Cinicioglu (Turkey)
Carlos A. Coello Coello (Mexico)
Giulianella Coletti (Italy)
Oscar Cordon (Spain)
Ana Colubi (Spain)
Didier Coquin (France)
Inés Couso (Spain)
Keeley Crockett (UK)
Fabio Cuzzolin (UK)
Bernard De Baets (Belgium)
Guy De Tré (Belgium)
Sébastien Destercke (France)
Marcin Detyniecki (France)
Antonio Di Nola (Italy)
Remco Dijkman (Netherlands)
Didier Dubois (France)
Fabrizio Durante (Italy)
Francesc Esteva (Spain)
Mario Fedrizzi (Italy)
Janos Fodor (Hungary)
David Fogel (USA)
Sylvie Galichet (France)
Patrick Gallinari (France)
Maria Angeles Gil (Spain)
Lluis Godo (Spain)
Fernando Gomide (Brazil)
Gil González Rodríguez (Spain)
Michel Grabisch (France)
Steve Grossberg (USA)
Przemysław Grzegorzewski (Poland)
Lawrence Hall (USA)

Francisco Herrera (Spain)
Enrique Herrera-Viedma (Spain)
Ludmilla Himmelspach (Germany)
Kaoru Hirota (Japan, China)
Janusz Kacprzyk (Poland)
Uzay Kaymak (Netherlands)
Cengiz Kahraman (Turkey)
Abraham Kandel (USA)
James Keller (USA)
Frank Klawonn (Germany)
Erich Peter Klement (Austria)
Laszlo Koczy (Hungary)
Vladik Kreinovich (USA)
Tomas Kroupa (Italy)
Rudolf Kruse (Germany)
Christophe Labreuche (France)
Jérome Lang (France)
Henrik Larsen (Denmark)
Mark Last (Israel)
Weldon A. Lodwick (USA)
Edwin Lughofer (Austria)
Jean-Luc Marichal (Luxembourg)
Trevor Martin (UK)
Sebastian Massanet (Spain)
Mylène Masson (France)
Silvia Massruha (Brazil)
Gilles Mauris (France)
Gaspar Mayor (Spain)
Jerry Mendel (USA)
Radko Mesiar (Slovakia)
Ralf Mikut (Germany)
Enrique Miranda (Spain)
Javier Montero (Spain)
Jacky Montmain (France)
Serafín Moral (Spain)
Zbigniew Nahorski (Poland)
Yusuke Nojima (Japan)
Vilem Novak (Czech Republic )
Hannu Nurmi (Finland)
Nikhil Pal (India)
Endre Pap (Serbia)
Simon Parsons (UK)
Gabriella Pasi (Italy)

Witold Pedrycz (Canada)
Irina Perfilieva (Czech Republic )
Fred Petry (USA)
Vincenzo Piuri (Italy)
Olivier Pivert (France)
Henri Prade (France)
Anca Ralescu (USA)
Dan Ralescu (USA)
Mohammed Ramdani (Morocco)
Marek Reformat (Canada)
Adrien Revault d'Allonnes (France)
Beloslav Riecan (Slovakia)
Maria Dolores Ruiz (Spain) Thomas Runkler (Germany)
Enrique Ruspini (USA)
Daniel Sanchez (Spain)
Mika Sato-Ilic (Japan)
Glen Shafer (USA)
Roman Słowinski (Poland)
Gregory Smits (France)
João Sousa (Portugal)
Pilar Sobrevilla (Spain)
Martin Stepnicka (Czech Republic )
Umberto Straccia (Italy)
Michio Sugeno (Japan)
Eulalia Szmidt (Poland)
Kay-Chen Tan (Singapore)
Bruno Teheux (Luxembourg)
Settimo Termini (Italy)
Konstantin Todorov (France)
Vicenc Torra (Sweden/Spain)
I. Burhan Turksen (Canada)
Bülent Tütmez (Turkey)
Linda van der Gaag (Netherlands)
Herman K. van Dijk (Netherlands)
Barbara Vantaggi (Italy)
Michel Verleysen (Belgium)
Thomas Vetterlein (Austria)
Susana Vieira (Portugal)
Anna Wilbik (Netherlands)
Slawomir Zadrozny (Poland)
Hans-Jürgen Zimmermann (Germany)
Jacek Zurada (USA)

Additional Reviewers

Cristina Alcalde
Alessandro Antonussi
Louis Aslett
Edurne Barrenechea
Maciej Bartoszuk
Fernando Batista
Benjamin Bedregal
Libor Behounek
Gleb Beliakov
Sarra Ben Hariz
Chiheb-Eddine Ben N’Cir
Magdalena Bendova
Mara José Benítez Caballero
Hanen Borchani
Felix Bou
Reda Boukezzoula
Denis Bouyssou
Yamine Bouzembrak
Christian Braune
Alberto Bugarìn
Ana Burusco
Inma Cabrera
Marta Cardin
Anna Cena
Alireza Chakeri
Mouna Chebbah

Petr Cintula
Maria Eugenia Cornejo Piñero
Miguel Couceiro
Maria Jose Del Jesus
Cyril De Runz
Denisa Diaconescu
Graaliz Dimuro
Alexander Dockhorn
Christoph Doell
Paweł Drygaś
Zied Elouedi
Javier Fernandez
Tommaso Flaminio
María Angeles Galán García
Marek Gagolewski
Juan Gomez Romero
Petra Hodakova
Aoi Honda
Petr Hurtik
Johan Jacquemin
Simon James
Balasubramaniam Jayaram
Ilyes Jenhani
Chee Kau Lim
Frank Klawonn

David Lobo
Nicolas Madrid
Enrico Marchioni
Nicolas Marin
Arnaud Martin
Maria J. Martin-Bautista
Brice Mayag
Jesús Medina
Thuraya Mellah
Jos M. Merigó
Pedro Miranda
Gildas Morvan
Mirko Navara
Tatiane Nogueira Rios
Michael Oberguggenberger
Pere Pardo
Barbara Pȩkala
Davide Petturiti
Marc Pirlot
Badran Raddaoui
Eloisa Ramírez Poussa
Alejandro Ramos
Jordi Recasens
Ricardo Ribeiro
Juan Vicente Riera

Ricardo Oscar Rodriguez
Jonas Rogger
Christoph Roschger
Daniel Ruiz-Aguilera
Lorenza Saitta
Ahmed Samet
Laura Schnüriger
Karima Sedki
Jose-Maria Serrano
Prakash Shenoy
Andrzej Skowron
Alexander Sostak
Jana Spirkova
Eiichiro Takahagi
Joan Torrens
Gracian Trivino
Esko Turunen
Lev Utkin
Lionel Valet
Llorenc Valverde
Francisco J. Valverde Albacete
Jan Van den Berg
Amanda Vidal Wandelmer
Zdenek Wagner
Gero Walter

Local Organizing Committee

Uzay Kaymak

Uzay Kaymak
Eindhoven University of Technology
The Netherlands

Local Organizer
Annemarie van der Aa

Annemarie van der Aa
Eindhoven University of Technology
The Netherlands

Local Organizer
Rui Jorge Almeida

Rui Jorge Almeida
Eindhoven University of Technology
The Netherlands

Local Organizer
Caro Fuchs

Caro Fuchs
Eindhoven University of Technology
The Netherlands

Local Organizer
Anna Wilbik

Anna Wilbik
Eindhoven University of Technology
The Netherlands

Local Organizer

Program

Proceedings

Download proceedings vol. I
(until July 18, 2016)

Download proceedings vol. II
(until July 18, 2016)

Program Overview

Download program overview (PDF)
(last update June 6, 2016)

Download session content (PDF)
(last update June 6, 2016)

Download book of abstracts (PDF)
(last update June 13, 2016)

Plenary Speakers

Joseph Y. Halpern

Joseph Y. Halpern, Cornell University, USA, Actual Causality: A Survey

Abstract: What does it mean that an event C “actually caused” event E? The problem of defining actual causation goes beyond mere philo- so- phical speculation. For example, in many legal arguments, it is pre- cisely what needs to be established in order to determine responsibi- lity. (What exactly was the actual cause of the car accident or the medical problem?) The philosophy literature has been struggling with the prob- lem of defining causality since the days of Hume, in the 1700s. Many of the definitions have been couched in terms of counter- factuals. (C is a cause of E if, had C not happened, then E would not have happened.) In 2001, Judea Pearl and I introduced a new defini- tion of actual cause, using Pearl’s notion of structural equations to model counterfactuals. The definition has been revised twice since then, extended to deal with notions like ”responsibility” and ”blame”, and applied in databases and program verification. I survey the last 15 years of work here, including joint work with Judea Pearl, Hana Chockler, and Chris Hitchcock. The talk will be completely self-con- tained.

Joseph Halpern received a B.Sc. in mathematics from the University of Toronto in 1975 and a Ph.D. in mathematics from Harvard in 1981. In between, he spent two years as the head of the Mathematics Department at Bawku Secondary School, in Ghana. After a year as a visiting scientist at MIT, he joined the IBM Almaden Research Center in 1982, where he remained until 1996, also serving as a consulting professor at Stanford. In 1996, he joined the CS Department at Cornell, and was department chair 2010-14.
Halpern's major research interests are in reasoning about knowledge and uncertainty, security, distributed computation, decision theory, and game theory. He is a Fellow of AAAI, AAAS (American Association for the Advancement of Science), the American Academy of Arts and Sciences, ACM, IEEE, and SEAT (Society for the Advancement of Economic Theory). Among other awards, he received the ACM SIGART Autonomous Agents Research Award in 2011, the Dijkstra Prize in 2009, the ACM/AAAI Newell Award in 2008, the Godel Prize in 1997, was a Guggenheim Fellow in 2001-02, and a Fulbright Fellow in 2001-02 and 2009-10. Two of his papers have won best-paper prizes at IJCAI (1985 and 1991), and another two received best-paper awards at the Knowledge Representation and Reasoning Conference (2006 and 2012). He was editor-in-chief of the Journal of the ACM (1997-2003) and has been program chair of a number of conferences.

Tuesday, 21 June
Chris Dyer

Chris Dyer, Carnegie Mellon University, USA, Learning Representations of Complex Structures in Natural Language with Neural Networks

Abstract: Effective processing of natural language requires integrating information from a variety of sources: an individual words meaning de- pends on the context it is used in; the proper interpretation of a sentence depends on understanding the discursive context it occurs in; and, rea- soning about the truth of a linguistically encoded proposition requires drawing on world knowledge. However, if we take stock of what progress has been made in language processing applications to date, it is precisely those that depend on a narrow view of contextrather than those that re- quire significant integration of contextual informationwhere we find the most success. In this talk I argue that the challenge of developing next-generation models that are sensitive to broader contextual information can be helpfully cast as a representation learning problem. Given a basic representation of the input signal and relevant contextual information, a unified repre- sentation suitable for making predictions needs to be computed. I discuss work from my group on using neural networks to integrate basic represen- tations of component linguistic elements and combining them recursively to obtain composite representations of complex objects. Our work has demonstrated that taking inspiration from the linguistic structures when designing architectures is more effective than task-agnostic architectures. Applications ranging from text categorization, to language modeling, to machine translation will be discussed.

Chris Dyer is an assistant professor at Carnegie Mellon University. Dyer graduated from the Duke University in 2000, where he studied computer science. He went on to obtain a Ph.D. in linguistics in 2010 from University of Maryland under the supervision of Prof. Philip Resnik. Chris Dyer's reasearch interests line in the intersection of statistical machine translation, unsupervised learning, computational morphology and phonology, large-scale data processing, probabilistic models of natural language processing, Bayesian techniques and machine learning. He is currently supported by grants from The National Science Foundation (Lexical Borrowing), DARPA (LORELEI), Google (A Hybrid Neural–Phrase-Based Model for Machine Translation) and The Army Research Office (MT/NLP for Low-Resource Languages). Source: Dyer homepage

Wednesday, 22 June
Chris Dyer

Peter P. Wakker, Erasmus University Rotterdam, Netherlands, The Present State of the Art of Modeling Uncertainty in Decision Theory, Resulting from an Iteraction between Mathematical Economists and Empirical Psychologists

Abstract: In decision theory, more than in other fields of IPMU, the modeling of uncertainty is driven by empirical findings about human behavior. Decision theorists are strict in the requirement that for every mathematical detail the empirical meaning must be exactly specified. For example, taking the lower bound of possible probabilities of an event, while accepted uncritically in most information management theories, is meaningless to a decision theorist until it has been specified whether the event in question yields good or bad outcomes.
This lecture describes how the current state of the art in uncertainty- decision theory could only come about from interactions between empiri- cally oriented psychologists and mathematically oriented economists. At several stages in history, the next step forward could be made only by empirical intuitions from psychologists. Following up on that, the next step forward could be made only by theoretical inputs from economists with advanced technical skills. Modern views on the proper modeling of uncertainty attitudes could only arise from the merger of ideas from all the fields mentioned. It, for instance, led to a measure of information- insensitivity that is more refined than just taking supremums or infimums of uncertainty measures.

Peter Wakker is a professor of decisions under uncertainty at the Department of Econometrics of the Erasmus School of Economics (ESE). He works in behavioral economics, primarily on the differences between normative and descriptive decisions, and on decisions under risk and uncertainty. Wakker has published in leading journals in economics, business, medicine, psychology, statistics, and mathematics. He was nominated the best-publishing Dutch economist in the years 1994, 1998, 2003, and 2007, and was ranked 90th in the world in the ISI's most cited scientists in economics and business in 2003. He received a Frank P. Ramsey Medal in 2013 and Medical Decision Making Career Achievement Award in 2007. Wakker regularly gives advices on insurance in the media. Wakker is director, jointly with Professor Han Bleichrodt, of the research group Behavioral Economics.
Source: ERIM, Peter Wakker homepage and EADM interview

Tuesday, 21 June
Chris Dyer

Katharina Morik, Technische Universität Dortmund, Germany, Resource-constrained Data Analysis and Exploration

Abstract: Computer science has always taken into account some resources needed for the execution of algorithms, namely runtime and memory space. Since the triumph of very large data centers, energy has become a resource of importance, additionally. In 2008, Google had its millionth server. Google’s estimated yearly energy consumption is about 2024 watt hours (Wh). A search request consumes 0.3 Wh, asking and reading the result at a home computer consumes about the same, so that each query costs about 0.6 Wh.
Where data centers challenge resources at a global scale, the energy of cyber-physical systems and smartphones is restricted at the local device. The battery of a smartphone has a capacity of about 8 Wh. The user wants a long battery duration together with a high quality of service. Regarding machine learning, there are two ways, in which energy may be saved. On the one hand, a learning algorithm may learn from compiler logs or from user behavior how to enhance the heuristics of the system’s software. On the other hand, the learning algorithm itself has to become energy-efficient. This can be achieved through approximations which reduce the operations that cost the most energy. Cyber-physical systems populate diverse parts of our everyday life, they are the nodes of the Internet of Things and they produce big data. If we focus again on smartphones, each user generates about 60 GB of data per year. Learning a personal model of app usage could allow early warnings when to recharge the battery.
However, the analysis of such data is not easy: data may be missing, their incompleteness is not easy to recognize, and they may be wrong due to several reasons. Labels, which are needed for classifier training, are missing. Data exploration is an important, though often under- estimated first part of data analysis. In the talk, several probabilistic graphical models will be presented to- gether with their applications.

Katharina Morik is a professor at Technische Universität Dortmund. She received her PhD at the university of Hamburg 1981 and worked in the well-known natural language project HAM-ANS at Hamburg from 1982 to 1984. Then, she moved to the technical university Berlin and became the project leader of the first German machine learning project, KIT-Lerner. From 1989 to 1991 she was leading a research group for machine learning at the German National Research Center for Computer Science at Bonn. This team developed the MOBAL system within the ESPRIT project Machine Learning Toolbox (P2154). In 1991, she became full professor at the university of Dortmund. Until 1994 she was the leader of the German special interest group in machine learning of the German Society for Computer Science. Together with Xindong Wu, she started the IEEE International Conference on Data Mining. Katharina Morik is speaker of the collaborative research center SFB876, member of the Scientific Advisory Board of Rapid-I., part of the Scientific Council of The European Institute for Participatory Media. Interests are in all kinds of applications of machine learning, including cognitive modeling of theory acquisition and revision.
Source: Katharina Morik home page.

Wednesday, 22 June
Ronald R. Yager

Ronald R. Yager , Iona College, USA Decision Making with Multi-Criteria

Abstract: The construction of multi-criteria decision functions is strongly dependent upon the use of aggregation operators. Here if D(x) = Agg(C1(x), C2 (x), ..., Cn (x)) represents the satisfaction of alternative x to the collec- tion of criteria a central problem becomes the formulation of the decision function D. The structure of the function Agg must be a reflection of the decision makers perceived relationship between the different crite- ria. We must provide some approaches that can used to help in the construction of these decision functions. One approach is to allow the decision-maker to express their perceived relationship between the cri- teria in a linguistic like manner and then try to model this relationship using fuzzy logic formalisms. Another approach is the use of set measures for the representation of the relationship between criteria. Once having a formal representation of the decision function D we must evaluate it for each alternative. In many real world environments the values of the Cj(x) can only be provided with some uncertainty. Among the different types of imprecise valuations are intervals, probability distributions, D-S belief structures, fuzzy sets, intuitionistic, Pythagorean and generalized orthopair fuzzy sets as well ordinallinguistic valuations. Finally we must choose among these alternatives based their values for D(x). In the case of uncertainty in the Cj(x) the value of D(x) also manifests uncertainty. Choosing requires that we provide an ordering of these uncertain values. In our talk we shall discuss various topics from the above.

Ronald R. Yager is Director of the Machine Intelligence Institute and Professor of Information Systems at Iona College. He is editor and chief of the International Journal of Intelligent Systems. He has published over 500 papers and edited over 30 books in areas related to fuzzy sets, human behavioral modeling, decision-making under uncertainty and the fusion of information. He is among the world’s top 1% most highly cited researchers with over 45,000 citations in Google Scholar. He was the recipient of the IEEE Computational Intelligence Society Pioneer award in Fuzzy Systems. He received the special honorary medal of the 50-th Anniversary of the Polish Academy of Sciences. He received the Lifetime Outstanding Achievement Award from International the Fuzzy Systems Association. He recently received honorary doctorate degrees, honoris causa, from the Azerbaijan Technical University and the State University of Information Technologies, Sofia Bulgaria. Dr. Yager is a fellow of the IEEE, the New York Academy of Sciences and the Fuzzy Systems Association. He has served at the National Science Foundation as program director in the Information Sciences program. He was a NASA/Stanford visiting fellow and a research associate at the University of California, Berkeley. He has been a lecturer at NATO Advanced Study Institutes. He was a program director at the National Science Foundation. He is a visiting distinguished scientist at King Saud University, Riyadh Saudi Arabia. He was an adjunct professor at Aalborg University in Denmark. He received his undergraduate degree from the City College of New York and his Ph. D. from the Polytechnic Institute New York University. He is the 2016 recipient of the IEEE Frank Rosenblatt Award the most prestigious honor given out by the IEEE Computational Intelligent Society.

Thursday, 23 June

Invited Overview Talks

Joseph Y. Halpern

Joseph Y. Halpern, Cornell University, USA Plausibility measures: a uniform approach to counterfactual reasoning, default reasoning, and belief change

Abstract: Counterfactual reasoning involves reasoning about events that are counter to fact, as in ``If my brakes weren't defective, I wouldn't have had the accident''. Default reasoning involves reasoning about typicality, as in ``Drunk drivers typically have accidents''. Belief change involves characterizing how beliefs should change, particularly when you discover that something that you believed was false is actually true. While these may seem to be very different notions, they are in fact closely related. I discuss the three notions, and present one uniform approach to modeling all three. Central to the approach is a new formalism for reasoning about uncertainty called a plausibility measure. Plausibility is a generalization of probability: the plausibility of a set is just an element of some arbitrary partial order (instead of being an element of [0,1], as in the case of probability). As the framework shows, plausibility is a reasonable generalization of probability that allows more qualitative reasoning.

Joseph Halpern received a B.Sc. in mathematics from the University of Toronto in 1975 and a Ph.D. in mathematics from Harvard in 1981. In between, he spent two years as the head of the Mathematics Department at Bawku Secondary School, in Ghana. After a year as a visiting scientist at MIT, he joined the IBM Almaden Research Center in 1982, where he remained until 1996, also serving as a consulting professor at Stanford. In 1996, he joined the CS Department at Cornell, and was department chair 2010-14.
Halpern's major research interests are in reasoning about knowledge and uncertainty, security, distributed computation, decision theory, and game theory. He is a Fellow of AAAI, AAAS (American Association for the Advancement of Science), the American Academy of Arts and Sciences, ACM, IEEE, and SEAT (Society for the Advancement of Economic Theory). Among other awards, he received the ACM SIGART Autonomous Agents Research Award in 2011, the Dijkstra Prize in 2009, the ACM/AAAI Newell Award in 2008, the Godel Prize in 1997, was a Guggenheim Fellow in 2001-02, and a Fulbright Fellow in 2001-02 and 2009-10. Two of his papers have won best-paper prizes at IJCAI (1985 and 1991), and another two received best-paper awards at the Knowledge Representation and Reasoning Conference (2006 and 2012). He was editor-in-chief of the Journal of the ACM (1997-2003) and has been program chair of a number of conferences.

Monday, 20 June
Chris Dyer

James M. Keller, University of Missouri, USA, Fuzzy and possibilistic clustering and the curious case of coincident clusters

Abstract: The first part of this tutorial will cover the development and application of fuzzy and possibilistic clustering with emphasis on the Fuzzy C-Means (FCM) and Possibilistic C-Means (PCM) along with several of their variations and generalizations. Then we will analyze the often reported curious tendency of the PCM to produce coincident clusters, i.e., more than one cluster whose cluster centers are essentially identical. Is this a demon or angel (defect or benefit)?

James M. Keller James M. Keller received the Ph.D. in Mathematics in 1978. He holds the University of Missouri Curators’ Professorship in the Electrical and Computer Engineering and Computer Science Departments on the Columbia campus. He is also the R. L. Tatum Professor in the College of Engineering. His research interests center on computational intelligence: fuzzy set theory and fuzzy logic, neural networks, and evolutionary computation with a focus on problems in computer vision, pattern recognition, and information fusion including bioinformatics, spatial reasoning in robotics, geospatial intelligence, sensor and information analysis in technology for eldercare, and landmine detection. His industrial and government funding sources include the Electronics and Space Corporation, Union Electric, Geo-Centers, National Science Foundation, the Administration on Aging, The National Institutes of Health, NASA/JSC, the Air Force Office of Scientific Research, the Army Research Office, the Office of Naval Research, the National Geospatial Intelligence Agency, the Leonard Wood Institute, and the Army Night Vision and Electronic Sensors Directorate. Professor Keller has coauthored over 400 technical publications.

Monday, 20 June
Chris Dyer

Arthur ter Hofstede, Queensland University of Technology, Australia, Process Query Language: A Tutorial

Abstract: Companies that have taken up business process management in earnest may acquire hundreds if not thousands of process models over time. Managing these collections of process models can be challenging and a process query language that can facility the search for models with certain characteristics can be of assistance. In this tutorial PQL (Process Query Language) is introduced, a language that can be used to search for process models that exhibit certain semantic (as opposed to syntactic) features. Dealing with execution semantics is nontrivial and untangling is explained as a technique for deriving semantic properties of tasks and relationships between tasks. A number of illustrative queries will be discussed.

Arthur ter Hofstede Arthur ter Hofstede is a Professor in the Information Systems School in the Science and Engineering Faculty, Queensland University of Technology, Brisbane, Australia, and he is also a Professor in the Information Systems Group of the School of Industrial Engineering of Eindhoven University of Technology, Eindhoven, The Netherlands. His research interests are in the areas of business process automation and process mining.

Monday, 20 June
Chris Dyer

Gijs Wobben, Marianne Faro, Olaf Klooster, Itility, the Netherlands, Data science in the enterprise

Abstract: “The interesting aspects of Data Science”: that is the main subject during the 16th edition of the International Conference on Information processing and Management of Uncertainty in Knowledge-Based systems (IPMU). Bringing together scientists, and exchan- ging ideas between theoreticians and practitioners in Data Science – that is Itility’s focus. Based on our practical experience, we will discuss the practice of data science for the enterprise. The session bridges theory and practice of Data Science. The underlying question is that we develop many methods, but how do we make them used on a daily basis?

Gijs Wobben is a Chief Data Scientist at Itility. Wobben graduated in 2012 at the TU/e, where he studied Industrial Design, Bachelor of Science. He graduated his Master of Science, Science and Innovation Management, in 2014. Gijs Wobben’s specialties are business analytics, Big Data, and Data Science using Splunk in projects such as: designing the architecture for the Itility Managed Analytics Platform (IMAP, a Big Data SaaS solution), implementing a capacity management environment to manage a 4000+ server platform, creating algorithms for auto scaling, designing an ‘R’ app to incorporate R in Splunk.

Chris Dyer

Marianne Faro is principal consultant and Analytics competence lead at Itility. Faro graduated in 1991, Bachelor of Science in Business Informatics, and 1995, Master of Science, Business Studies. Before joining the Itility team in 2008, Marianne Faro worked as European Information Manager at Nike, and as Project Manager at various companies. Her focus is on Smart Factories, Analytics as a Service, Big Data, Data Science, Machine Learning and Internet of Things.

Chris Dyer

Olaf Klooster is a graduate intern at Itility. Klooster finished his Bachelor of Science in 2013 at the TU/e, where he studied Industrial Engineering & Management. At the moment Klooster is writing his Master Thesis at Itility to acquire a Master of Science degree in Operations Management & Logistics at the TU/e. Topic of his Master Thesis is to implement agility in big data analytics.

Industry Round Table - flyer

Friday, 24 June
 

Client
Client

Smart Industry refers to recent, revolutionary developments in ICT technology such as Internet of Things and Cyber Physical Systems. These technological developments cause machines, resources, people, and organizations to become intertwined and blended. New, smarted ways of production (for instance, 3D printing) and new business models (for instance, based on servitization) are emerging. Smart production processes have a flexible capacity with respect to product (specification, quality, design), volume, timing, and efficiency. Moreover, the products themselves are becoming increasingly smart.

These developments result in complex networks of organisations, people, and machines, through which massive amounts of data are flowing. Data science, that is, analyzing and managing these data streams for decision making, is essential to maintain a firm grip on these networks. Important problems are for instance how to make optimal use of the available, flexible production capability with respect to time, costs and quality.

Speakers & Panelists

Joris van Agtmaal

Joris van Agtmaal, Wärtsilä, Netherlands, Smart industry - Smart analytics in practice

Abstract: Wärtsilä is a global leader in power solutions for the marine and energy markets. Their huge engines contain ever more sensors, generating lots of data that can be repurposed for smart analytics. The new digital services they deliver to their customers use the insights extracted from this data to generate new value for their customers. The latest developments in data science, like the latest tools, advanced algorithms and cloud computing make it possible to automate more and more of the steps in the process of turning this pile of data into money. Sounds great, right? Let’s look at a case and see what we can learn.

Joris van Agtmaal Joris van Agtmaal finished a master degree in technology management at the TU/e, after which he decided being a fulltime DJ and playing records all night seemed like a more appealing option. After various other weird and wonderful side jobs he ended up with ASML reporting and analysing the reliability of complex Lithography equipment and this is where the interest in data analysis got sparked. Now, about 10 years later he is working as the product owner of the data science team in the digitalization department of Wartsila.

Friday, 24 June
Jan Eite Bullema

Jan Eite Bullema, TNO, Netherlands, How to make Big Data in a Semiconductor Manufacturing environment productive?

Abstract: In the ENIAC project Integrate an architecture has been developed that is meant to enable fab-wide implementation of advanced process control methods. Koenig estimated in 2004 that a typical semiconductor manufacturing line produces an excess of 1 Terabyte per day. In the Big Data section of the ITRS 2013 data volumes are shown in the unit “Terabyte per day” (TBD). Mariano expected in 2014 that in future FABS will have to deal with multiple Petabytes of data on a daily basis. According to Mariano, this data is not fully used. Routine reports are extracted for common purposes like maintenance, documentation, process control and optimization and quality management. Much data that are stored, whether in the equipment or in a database, are kept only for a limited time or in a rolling log file subject to the storage requirements. The infamous data graveyard.
According to the 2013 ITRS roadmap fab wide solutions to make big data streams productive are required. But: “The current state of the art is that fab-wide implementation of Advanced Manufacturing Technology remains an aspiration”
In this presentation I will present an Agent Based Control architecture -more specific a holarchy- for Semiconductor Manufacturing that will enable the productive use of all available data. The elegance of the presented architecture is that it (a) uses already existing industrial standards (b) building an fab-wide solution can be done from simple to increasing complexity. The system can be built into an existing system. Starting with autonomous entities, towards cooperative entities, thus gradually creating fab-wide integration. An example of autonomous entity would be an agent that performs the function of a statistical process control chart (i.e. in control or out of control decision) or an agent that performs a predictive maintenance function (i.e. prediction of remaining useful life of a tool). A cooperative entity could be a dispatching agent that uses the statistical control chart agent and the predictive maintenance agent to decide whether a specific production batch can be dispatched to a specific tool.
By building upon existing SEMI standards (i.e. SEMI E133) and data mining / machine learning standards (i.e. PMML) implementation costs are expected to be comparable to the cost of running traditional process control methods (e.g. SPC) An advantage of the use of PMML is the standard is applicable in Big Data environments (e.g. Hadoop, Spark) and can be used for massive parallel scoring of machine learning models.
The concept of holonic manufacturing system already exists for several decades. At the current moment – emergence of Big Data analytics – the holonic approach has become more relevant. As the holonic approach can be put into practice to maintain control in inherent complex Big Data environments.

Jan Eite Bullema Jan Eite Bullema (1959) received an M.Sc in Inorganic Chemistry and Physics from the University of Groningen (NL) in 1987, after obtaining a B.Eng. in Chemical Technology. Before graduating from University, he worked as process engineer for AKZO, starting in 1984. After graduating from the University, he started working for Royal Philips Electronics Philips in the field of Process Control / Quality Improvement at the Centre for Manufacturing Technologies (CFT), eventually as a Six Sigma Master Black Belt.
In 1999 he joined TNO, as Senior Scientist in the field of Micro and Nano Technology mainly for development of micro systems technology. Mr. Bullema has been a part-time professor (lector) at the University for Applied Sciences in Utrecht in the field of micro systems technology. Mr. Bullema holds several patents in the field of micro systems technology. At TNO Mr. Bullema has contributed to development of various micro devices (e.g. MEMS oscillator, micro Gas chromatograph, RF Switch, Autonomous Sensors), currently with a focus on 3D Printed microfluidic devices.
Mr. Bullema is certified by the American Productivity and Inventory Control Society (APICS) in Production and Inventory Management (CPIM) and Integrated Resource Management (CIRM) and is certified by ASQ (American Society for Quality) as Certified Six Sigma Black Belt (CSSBB) and Certified Reliability Engineer (CRE). Besides manufacturing and process control expertise, Mr. Bullema has a demonstrated track record in application of advanced process control and machine learning, with an interest in big data based deep learning for complex manufacturing control.

Friday, 24 June
Marianne Faro

Marianne Faro, Itility, Netherlands , Smart industry - manage uncertainties via smart analytics

Abstract: Itility is a IT consultancy firm, serving enterprise customers in high tech and manufacturing. What does Smart Industry mean to them? And can data science help them in the struggle to manage uncertainties? We cover this question via a practical example of the STORM motor race around the world: fighting the uncertainties of driving around the world in 80 days in territories you have never been to, on a motor bike that you do not know well since it has only been completed 1 month before starting your journey. Data science will help, by collecting as much data as possible and create algorithms to alert and predict what the motor will do and which parts might break down.

Marianne Faro is principal consultant and Analytics competence lead at Itility. Faro graduated in 1991, Bachelor of Science in Business Informatics, and 1995, Master of Science, Business Studies. Before joining the Itility team in 2008, Marianne Faro worked as European Information Manager at Nike, and as Project Manager at various companies. Her focus is on Smart Factories, Analytics as a Service, Big Data, Data Science, Machine Learning and Internet of Things.

Friday, 24 June

Women in Engineering

Wednesday, 22 June
 

A well-known adage says “diversity brings innovation”. Diversity can be in culture, in thinking, in discipline, in gender, and in many more aspects. The result is the same: the chances for creating innovation in a given context increase when diversity is involved. We have been investing for decades in achieving gender balance in fields related to Engineering and Computer Science. We complain that too few women choose a technology-related career. But is it really true that gender diversity contributes to innovation, or more in general, brings concrete, technical advantages to the engineering outcomes? How to defeat the stereotypes about genders? In the Women in Engineering Panel we will explore these questions.

Panelists

Bernadette Bouchon-Meunier

Bernadette Bouchon-Meunier
Director of research emeritus, National Center for Scientific Research, France

Panelist
Jannie Minnema

Jannie Minnema
Senior Director Business Operations, Oracle, The Netherlands

Panelist
Marianne Faro

Marianne Faro
EIC Mathware & Soft Computing Magazine

Panelist
Rui Jorge Almeida

Rui Jorge Almeida
 
 

Chair
Maryam Razavian

Maryam Razavian
Assistant Professor in Information Systems, TUe, The Netherlands

Panelist

Open Access Publishing

Wednesday, 23 June
 

This panel is organized under the auspicies of the Netherlands Organization for Scientific Research (NWO).

Open Access (OA) publishing is high on the agenda of researchers and research funding agencies. European Union is expecting more and more that the research it funds is published in Open Access journals. Although the need for OA publications is generally acknowledged amongst the scientific community of IPMU, many researchers prefer more established non-OA journals for publishing. In this session, we will highlight the status of OA publishing amongst the journals related to the IPMU field of research. The session brings together a number of editor-in-chiefs (EIC) of journals. The discussion will consider which challenges OA publishing brings to our community and how these challenges are being dealt with.

Panelists

Bernadette Bouchon-Meunier

Bernadette Bouchon-Meunier
EIC International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems

Panelist
Didier Dubois

Didier Dubois
EIC Fuzzy Sets and Systems

Panelist
Humberto Bustince

Humberto Bustince
EIC Mathware & Soft Computing Magazine

Panelist
Janusz Kacprzyk

Janusz Kacprzyk
IC Journal of Automation, Mobile Robotics & Intelligent Systems

Panelist
Bernadette Bouchon-Meunier

Uzay Kaymak
 

Chair
Anna Wilbik

James Keller
Chair IEEE TAB Transactions Committee
 

Panelist
Anna Wilbik

Ronald Yager
EIC International Journal of Intelligent Systems

Panelist

Registration

Each paper needs full registration. One full registration will cover publication of one paper.

Full Registration 540* Before March 31st, 2016
  • 5 day sessions
  • 1 paper publication
  • Proceedings
  • Lunch, coffee breaks
  • Banquet
  • Before May 31st, 2016 - €590
  • After June 1st, 2016 - €640
Register
Student Registration1 350* Before March 31st, 2016
  • 5 day sessions
  • 1 paper publication
  • Proceedings
  • Lunch, coffee breaks
  • Banquet
  • Before May 31st, 2016 - €400
  • After June 1st, 2016 - €450
Register
Single Day Registration 200* Before March 31st, 2016
  • 1 day sessions
  • 1 paper publication
  • Proceedings
  • Lunch, coffee breaks
  • Banquet
  • Before May 31st, 2016 - €200
  • After June 1st, 2016 - €250
Register

Notes:

*Fees may apply:
     Credit Card (+4.5% transfer fee)
     Bank transfer (sender pays transfer costs)
     iDEAL (no costs)

1Proof of student enrollment must be sent separately by email to ipmu2016tue.nl.

Additional fees:

€200 - 1 additional paper (associated with the same registration, maximum 2 papers per registration).

€100 - additional banquet ticket.

€50 - additional page (beyond limit of 12, maximum 2 additional pages are allowed).

Venue & Travel

Venue

The conference will take place at the Eindhoven University of Technology (TU/e) campus, in Eindhoven, The Netherlands. The campus of TU/e (Den Dolech 2, 5612 AZ Eindhoven) is located right in the center of the city of Eindhoven, next to the railway station.

Sessions will take place in the Blauwe Zaal, Collegezaal 12 and Collegezaal 13 of the Auditorium (indicated as AUD on the map of the campus) and the Filmzaal of De Zwarte Doos.

Client
Client
Client

Conference Banquet

The conference banquet will be held at the Philips Stadion (Frederiklaan 10, 5616 NH Eindhoven). This stadium is the home of the football team PSV (originally meaning Philips Sport Vereniging), also known as PSV Eindhoven. With a capacity of 35,000, it is the third-largest football stadium in the country. The entrance is main entrance, indicated as number 8 on the map.

Client

Travel information

VISA information

Nationals of many non-EU countries require a visa for an uninterrupted stay of up to three months. Please note that the Dutch Ministry of Foreign Affairs requires that the requests for visa are submitted three months in advance. The proper actions necessary to acquire a valid visa are entirely the participant’s own responsibility. Information regarding how to obtain a visa for the Netherlands can be found on the Dutch Ministry of Foreign Affairs website.

Letter of acceptance & Invitation letters

Invitation letters will be provided by the conference organizing committee, after paper acceptance and registration for the conference.
Please send an email to ipmu2016 @ tue.nl with Author name, Paper ID, Paper Title, Work address.

By plane

The city of Eindhoven is accessible through multiple airports. The train distance from the national Dutch airport Amsterdam-Schiphol is about 1,5 hours, but Eindhoven itself also has a regional airport and is also close by to other international airports.

Eindhoven Airport

Eindhoven has a small international airport, Eindhoven Airport, with direct connections to more than thirty destinations in Europe, including Budapest, Dublin, London, Milan, Rome, and Stockholm with such low cost carriers as RyanAir and WizzAir. Eindhoven airport is about a 15 minute drive from the city center, either by bus or taxi. Bus 401 runs to the city center every ten minutes from Monday to Friday, every fifteen minutes on Saturdays and every half an hour on Sundays. Bus tickets can be bought on the bus from the driver, or at the AKO-shop (news agent) in the arrivals hall of Eindhoven Airport. Multiple Eindhoven taxi companies operate a service to the Eindhoven Airport (with a cost of about €25), including the AATK taxis (++31 650625202), Airport Taxi service (++ 31 638249525), Deeltaxi Eindhoven (+31 620626464), and Taxi Happy (+31 641036574).

Amsterdam Airport

The main airport of the Netherlands is the Amsterdam Airport, Schiphol. All major airlines fly to Schiphol, including but not limited to Air France, British Airways, Delta Air Lines, KLM Royal Dutch Airlines, Korean Air, Malaysia Airlines, and United Airlines. Schiphol has a direct train connection to Eindhoven. The journey takes about 1.5 hours, with trains running up to four times an hour (with a cost of about €20). The Eindhoven central station is within walking distance of both the conference hotels and the conference venue. Taxis can be found at both exits of the station.

Other airports

Additional airports reachable from Eindhoven are such smaller airports as Rotterdam Airport, Maastricht Airport, Charleroi Airport, Antwerp Airport, Cologne/Bonn Airport, and major airports such as Brussels Airport, Zaventem, Düsseldorf Airport and Frankfurt Main Airport. PIN taxi is specialized in service to all the aforementioned airports and reachable at (++31 611483828).

By train

Eindhoven is part of the intercity network of the Dutch railways and has direct rail connections with Amsterdam, Den Haag, Rotterdam, Utrecht, Heerlen, and Maastricht but also Paris, Berlin, and London. Trip planners are available from the Dutch national railway website, international website or alternatively from the Dutch public transportation site (http://9292.nl).

Eindhoven is easily reachable from Brussels, where the trip takes around three hours. Via Brussels, Eindhoven is reachable from Paris, London, Lyon, Berlin, and Bonn. Information about Belgian railways can be found on http://www.nmbs.be.

Similarly, Eindhoven is easily reachable from Germany, where a trip from Frankfurt on Main takes less than four hours. Information about travelling by train from Germany can be found at Deutsche Bahn site.

By car

All motorways to and around Eindhoven (A2, A50, A58, A67 and A270) lead the way to the campus, with signs clearly indicating ‘University’. Detailed information is available here.

Practical Information

About Eindhoven

Eindhoven is located in the southeast of the Netherlands, within 50 km of both the German and Belgian borders. The closest large cities are Düsseldorf (Germany) and Antwerp (Belgium). The Dutch capital Amsterdam is 125 km away. With a population of 215,000 the city of Eindhoven is the fifth largest city in the Netherlands and the largest in the southern Netherlands. Around 700,000 people live in the region of Eindhoven.

The Eindhoven region has become one of the leading technology hotspots in Europe, which is also known by the name Brainport Eindhoven. This region is a breeding ground for innovation and the home base for companies, and world-class knowledge and research institutes. Many top international high-tech companies are located in Eindhoven, such as Philips, DAF Trucks and ASML.

Eindhoven offers good social and cultural facilities and plenty of facilities for concerts or theatre performances and a museum of modern art. Numerous cafés and restaurants lend the town center the pleasant and lively air of the big city.

Health

It is unlikely that you will encounter unusual health problems in the Netherlands, and if you do, standards of care are world-class. The emergency phone number for police, ambulance and the fire department is 112. If you are an EU citizen, a European Health Insurance Card (EHIC) covers you for most medical care. It will not cover you for non-emergencies or emergency repatriation. Citizens from other countries should find out if there is a reciprocal arrangement for free medical care between their country and the Netherlands. No vaccinations are necessary for travelling to the Netherlands.

Money

In the Netherlands the Euro is used as currency. There are six coins; 5, 10, 20 and 50 cents, and 1 and 2 Euro coins. There are the bills of 5, 10, 20 and 50, 100, 200 and 500 Euro. However, not many places will accept the 100, 200 and 500 euro note.

Language

The official language of The Netherlands is Dutch. However, most of Dutch people speak at least one foreign language, mostly English since this language is taught at school during basic education. Many Dutch people also speak German, which is in many aspects similar to the Dutch language, and some of them speak French. Electricity The electrical current in The Netherlands is 230 volts with a frequency of 50 Hz. Round two-pin plugs are used (type-F).

Accomodation information

Several hotels are available within walking distance of the conference venue, such as Holiday inn, Hampshire Hotel Crown, Hotel Queen, Sandton Hotel Eindhoven and Crown Inn. Cheaper options include Hotel Van Neer and Best Western Eindhoven. There are also available low budget options, like hostels: Backpackers Bed & Breakfast, Budget Hotel or Lightotel