- SIPTA News - lists.sipta.org

Request for references on real-world applications of credal sets and interval expectation
by Quaeghebeur, Erik 01 Jul '23

01 Jul '23

Dear SIPTA Community, For a course on Uncertainty Representations and Reasoning, I'd like to compile a list of references (papers, book chapters, websites) which discuss (not necessarily as their main topic) real-world applications of credal sets and interval expectation (aka lower and upper previsions). With real-world, I mean those where the application was effectively put in practice. So not toy examples, or (possibly elaborately) worked out potential applications. It does include applications in other scientific domains and not just industry. The role of credal sets or interval expectation does not need to be ‘big’ or prominent, as long as it is there. I would be grateful if you could send me any such references in a private reply, and in particularly those about applications you were involved in yourself. The papers will get visibility among at least the students of the course, year after year. ;-) I will share the list I compile with others upon request. Best regards, Erik -- https://ac.erikquaeghebeur.name

1 0

FW: International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems IPMU 2024
by Kreinovich, Vladik 28 Jun '23

28 Jun '23

FYI, papers using imprecise probabilities are always welcome at this series of conferences 20th International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems IPMU 2024, Lisbon, Portugal, July 22-26, 2024 2024 https://ipmu2024.inesc-id.pt/ The IPMU conference is organized every two years with the focus of bringing together scientists working on methods for the management of uncertainty and aggregation. It also provides a forum for the exchange of ideas between theoreticians and practitioners in these and related areas. The 2024 edition of IPMU will take place at Instituto Superior Tecnico, University of Lisbon, Portugal, located in a vibrant renovated area 10 minutes from downtown. Lisbon is one of the oldest cities in the world, and full of stories to tell. A city where you feel safe wandering around day or night, where you'll find hotels, restaurants and nightlife to suit every taste, budget and requirement. A city full of authenticity, where old customs and ancient history intermix with cultural entertainment and hi-tech innovation. Lisbon is ageless, but it loves company, being famous for its hospitality and the family-like way it welcomes visitors. Lisbon has been elected World's Leading City Destination at the 2018 World Travel Awards. Topics and Scope of the Conference Theory, Methods and Tools Uncertainty, Computational Intelligence, Bayesian and Probabilistic Methods, Information Theory, Measures of Information and Uncertainty, Evidence and Possibility Theory, Utility Theory, Fuzzy Sets and Fuzzy Logic, Fuzzy Control, Rough Sets, Multiple Criteria Decision Methods, Aggregation Methods, Knowledge Representation, Approximate Reasoning, Non-classical Logics, Default Reasoning, Belief Revision, Argumentation, Ontologies, Uncertainty in Cognition, Graphical Models, Knowledge Acquisition, Interpretable Machine Learning, Evolutionary Computation, Neural Networks, Data Analysis/Data Science, Explainable AI. Application Fields Intelligent Systems and Information Processing, Decision Support, Database and Information Systems, Information Retrieval and Fusion, Speech and Natural Language Processing, Image Processing, Multi-Media, Agents, Pattern Recognition, Medicine and Bioinformatics, Finance, Software Engineering, Industrial Engineering, Big Data. IPMU'2024 solicits original research contributions of theoretical and methodological nature as well as application-oriented work. IMPORTANT DATES Special session proposals: November 24th, 2023 Notification of acceptance special sessions: December 1st, 2023 Paper submission: February 23rd, 2024 Notification of acceptance: March 29th, 2024 Camera-ready paper submission: April 30th, 2024 Early/author registration: April 26th, 2024 Conference: July 22nd-26th, 2024 Program Chairs Marek Reformat (Canada) Marie-Jeanne Lesot (France) Susana Vieira (Portugal) Publication Chair Fernando Batista (Portugal) Executive Directors Bernadette Bouchon-Meunier (France) Ronald R. Yager (USA)

1 0

Next SIPTA seminar: 16th June (Friday), 15h CEST, Alexander Erreygers on One way to define an imprecise-probabilistic version of the Poisson process
by sdesterc 12 Jun '23

12 Jun '23

Dear SIPTiAns and IP enthusiasts, We are delighted to announce our upcoming eight SIPTA online seminar on imprecise probabilities (IP). These monthly events are open to anyone interested in IP, and will be followed by a Q&A and open discussion. They also provide an occasion for the community to meet, keep in touch and exchange between in-person events. The tenth seminar will take place on the 16th of June (Friday). The zoom link for this seminar is https://utc-fr.zoom.us/j/85217156757. For this tenth seminar, we are very happy to have Alexander Erreygers as our speaker. Alexander Erreygers is currently postdoctoral researcher at Ghent University, and has been an active researcher in the field of imprecise probabilities. In particular, he has made many core contribution to the study of stochastic processes when transition probabilities become imprecise. On the 16th of June, at 15:00 CEST:paris time (up to 17:00 CEST, with a talk duration of 45min/1h), he will talk about "One way to define an imprecise-probabilistic version of the Poisson process”. Curious? Then check out the abstract on the webpage of the SIPTA seminars: sipta.org/events/sipta-seminars. The zoom link for attending the seminar can be found on that same page. So please mark your calendars on the 16th of June, at 15:00 CEST, and join us for the occasion. You can find more information at https://sipta.org/events/sipta-seminars/ And for those who missed the previous seminar and want to catch up, or simply want to see it again and again, it is now online at https://www.youtube.com/watch?v=1RvysxPT4jA&t. See you at the seminar! Sébastien, Enrique and Jasper

1 0

ISIPTA'2023 information
by Enrique Miranda 05 Jun '23

05 Jun '23

Dear fellow SIPTAns, We are happy to inform you that the list of accepted contributions at ISIPTA'2023 is now available at Accepted Papers - ISIPTA 2023 <https://isipta23.sipta.org/accepted-papers/> In addition, you can also see the preliminary program of the conference at Program - ISIPTA 2023 <https://isipta23.sipta.org/program/> Interested? Then remember that you can still register until June 15, using the following link: Registration - ISIPTA 2023 <https://isipta23.sipta.org/registration/> Looking forward to meeting you all in Oviedo. Best regards, Enrique Miranda On behalf of the ISIPTA'2023 PCBoard

1 0

Re: IUKM 2023 -- deadline extended to June 15!
by Kreinovich, Vladik 03 Jun '23

03 Jun '23

FYI, papers related to all kinds of uncertainty are welcome at this series of conferences including imprecise probabilities ******************************************************** IUKM 2023: The Tenth International Symposium on INTEGRATED UNCERTAINTY in KNOWLEDGE MODELLING and DECISION MAKING Kanazawa, JAPAN, November 02-04, 2023 Conference website: https://www.jaist.ac.jp/IUKM/IUKM2023/ Submission link: https://cmt3.research.microsoft.com/User/Login?ReturnUrl=%2FIUKM2023 Submission deadline: June 15, 2023 -- extended! ---------------------------------------------------- The International Symposium on Integrated Uncertainty in Knowledge Modelling and Decision Making (IUKM) aims to provide a forum for exchanges of research results, ideas for and experience of application among researchers and practitioners involved with all aspects of uncertainty management and application. The Tenth International Symposium on Integrated Uncertainty in Knowledge Modelling and Decision Making (IUKM 2023) will be held in Kanazawa, Japan during 02-04 November, 2023, and be jointly organized by Japan Advanced Institute of Science and Technology (JAIST), University of Science (Vietnam National University Ho Chi Minh City), Vietnam, and Osaka University, Japan. Submission Guidelines: All papers must be original and not simultaneously submitted to another journal or conference. The authors are invited to submit their full papers by May 15, 2023. The submissions will be peer-reviewed for originality and scientific quality. Authors are requested to prepare their papers in the Springer format. Submissions should not exceed 12 pages and must be submitted as PDF electronically through the conference's CMT submission page. List of Topics Relevant topics for the IUKM 2023 Symposium include (but are not limited to) the following: - Theory and Methodology * Uncertainty formalisms: Bayesian probability, Dempster-Shafer theory, imprecise probability, random sets, rough sets, fuzzy sets and interval methods * Modelling uncertainty and inconsistency in big data * Learning and reasoning with uncertainty * Logics for reasoning under uncertainty * Uncertainty modelling in machine learning and deep learning * Information fusion and knowledge integration in uncertain environments * Decision making under various types of uncertainty * Aggregation operators for decision making * Copulas for dependence modelling * Granular and soft computing * Computational intelligence - Application * Data mining and knowledge discovery * Multi-agent reinforcement learning * Ontology engineering and Semantic Web * Privacy preserving data analysis * Intelligent data analysis and modelling * Agents and argumentation * Natural language processing * Medical informatics and bioinformatics * Ranking and recommendation systems * Big data and cloud computing * Social network analysis and mining * Sensor fusion * System identification and modelling * Diagnosis and reliability * Decision support systems * Kansei/affective engineering * Service computing * Engineering management * Supply chain management * Environmental management * Economics and econometrics * Statistics and Applications ------------------------------------------- Publication As done in previous editions, the proceedings of IUKM 2023 will be published by Springer-Verlag in the Lecture Notes in Artificial Intelligence series, and be available at the Conference. _______________________________________________ General Chairs: Masahiro Inuiguchi (Osaka University, Japan) Youji Kohda (Japan Advanced Institute of Science and Technology, Japan) Program Chairs: Van-Nam Huynh (Japan Advanced Institute of Science and Technology, Japan) Bac H. Le (University of Science, Vietnam National University (VNU)-Ho Chi Minh City, Vietnam) Katsuhiro Honda (Osaka Prefecture University, Japan)

1 0

Open PhD position at Leibniz University Hannover
by Jingyao Su 25 May '23

25 May '23

The Institut für Erdmessung (IfE) at Leibniz Universität Hannover (Germany)/DFG funded Research Unit (FOR5455) invites applications for the position of a Research Assistant (Doctoral Candidate, m/f/d) on *Distribution-free Uncertainty Description for Terrestrial Laser Scanner-based Areal Deformation Analysis (Salary Scale 13 TV-L, 100 %)* The position starts October 1st 2023 and is limited to 4 years. In the DFG funded Research Unit (FOR5455) “Deformation Analysis Based on Terrestrial Laser Scanner Measurements” (TLS-Defo, www.tlsdefo.de) relevant topics in TLS based deformation analysis will be investigated in a consortium of five universities (Uni Bonn, TU Munich, Leibniz University Hannover, KIT Karlsruhe, and TU Vienna). Project 5 "Distribution-free Uncertainty” will use intervals and sets to derive observation intervals for terrestrial laser scanner (TLS) measurements based on data analysis of terrestrial laser scans. Next, a concept has to be developed to propagate them to TLS point clouds. Subsequently, uncertainty regions of each TLS point can be derived as well as concepts for deformation analysis by intersection of these regions over subsequent epochs. For more information please consult the job listing at https://www.ife.uni-hannover.de/en/institute/job-opportunities The application deadline is June 4, 2023.

1 0

Open CIFRE-funded PhD position in Human-Centered Artificial Intelligence
by fredericpichon 22 May '23

22 May '23

* TITLE Assistance in reasoning under inconsistencies for uncertainty resolution * THEME Human-Centered Artificial Intelligence (HCAI) * KEYWORDS Consistency, Conflict, Uncertainty, Fusion, Belief Functions, Dempster-Shafer Theory, Anomaly, Knowledge Engineering, Human-Systems Integration. * STARTDATE AND DURATION September/October 2023, 36 months * FUNDING CIFRE scholarship (junior engineer position during the thesis) * LOCATION The work will possibly be carried out on several sites located in France: at the CS GROUP Research Lab (Paris-Saclay); at the CS GROUP offices in La Garde in the Toulon area; within the Laboratory of Computer Engineering and Automation of Artois (Béthune). * SUBJECT The objective of this thesis, situated in the field of human-centered artificial intelligence, is to develop a formal and tooled approach for reasoning assistance in the presence of inconsistent information, framed in belief function theory. More detail available here: https://www.lgi2a.univ-artois.fr/spip/en/open_positions/ * SUPERVISION Prof. Frédéric Pichon (frederic.pichon(a)univ-artois.fr <mailto:frederic.pichon@univ-artois.fr>), Laboratory of Computer Engineering and Automation of Artois (LGI2A) Dr. Anne-Laure Jousselme (anne-laure.jousselme(a)csgroup.eu <mailto:anne-laure.jousselme@csgroup.eu>), CS Group France Dr. Edwige Quillerou-Grivot (edwige.quillerou(a)inrs.fr <mailto:edwige.quillerou@inrs.fr>), FlexTech CentraleSupélec – ESTIA Chair. * PROFILE SOUGHT The candidate must hold a master degree or an engineer degree in computer science or related field, and *must be a national of EU countries, the United Kingdom or Switzerland*. Knowledge in artificial intelligence will be an asset, as well as an awareness of cognitive sciences. Qualities required to successfully complete a doctoral program such as curiosity, creativity, autonomy, critical thinking, and enthusiasm will be necessary. * APPLICATION Send *before June 12, 2023,* an e-mail, with all supervisors of the thesis in copy, containing the following documents in a single pdf file: your CV, a cover letter, your transcripts (with rankings) of the current year (master or equivalent) and previous years, and, optionally, up to two letters of recommendation.

1 0

Re: 6th School on Belief Functions and their Applications: Call for Participation
by Kreinovich, Vladik 22 May '23

22 May '23

FYI -----Original Message----- From: Van-Nam HUYNH Sent: Sunday, May 21, 2023 8:57 AM ######################################################### BFTA 2023 - Call for Participation The 6th School on Belief Functions and their Applications October 27 — Nov 1, 2023 Japan Advanced Institute of Science and Technology, Ishikawa, Japan https://bfasociety.org/BFTA2023/ ######################################################### The BELIEF school is a biennial event organized by the Belief Functions and Applications Society (BFAS) that offers a unique opportunity for students and researchers to learn about fundamental and advanced aspects of the theory of belief functions (also referred to as Dempster-Shafer theory, or evidence theory), a formalism for reasoning with uncertainty. The school will be organized around a set of lectures by prominent researchers. Lectures will gradually tackle basic to more advanced theoretical concepts. They will also highlight the links with other uncertainty theories such as random sets and possibility theory, and present applications of belief functions in various domains including machine learning, information fusion, statistical inference and materials science. Important dates: • May 1, 2023: Registration opens • July 31, 2023: Deadline for early-bird registration • September 15, 2023: Deadline for registration Financial support: Financial support will be offered by BFAS to some students for attending the school. Details of the application procedure will be announced soon. For further information, contact: bfta2023(a)bfasociety.org Organizing committee: • Van-Nam Huynh (Chair), JAIST, Japan • Thierry Denœux, Université de technologie de Compiègne, France • Anne-Laure Jousselme, CS Group Research Lab, France • Fréderic Pichon, Université d'Artois, France

1 0

Re: IUKM 2023, 2-4 November 2023, Kanazawa, Japan [Extended deadline]
by Kreinovich, Vladik 22 May '23

22 May '23

FYI -----Original Message----- From: Van-Nam HUYNH Sent: Sunday, May 21, 2023 8:33 AM [Apologies for cross-posting. Your help in circulating this call for papers to potentially interested parties is highly appreciated.] ———————————————————————————————————————————————————— CALL FOR PAPERS ———————————————————————————————————————————————————— IUKM 2023: The Tenth International Symposium on INTEGRATED UNCERTAINTY in KNOWLEDGE MODELLING and DECISION MAKING Kanazawa, JAPAN, November 02-04, 2023 Conference website: https://www.jaist.ac.jp/IUKM/IUKM2023/ Submission link: https://cmt3.research.microsoft.com/IUKM2023 Submission deadline: May 31, 2023 [Extended deadline] ———————————————————————————————————————————————————— The International Symposium on Integrated Uncertainty in Knowledge Modelling and Decision Making (IUKM) aims to provide a forum for exchanges of research results, ideas for and experience of application among researchers and practitioners involved with all aspects of uncertainty management and application. The Tenth International Symposium on Integrated Uncertainty in Knowledge Modelling and Decision Making (IUKM 2023) will be held in Kanazawa, Japan during 02-04 November, 2023, and be jointly organized by Japan Advanced Institute of Science and Technology (JAIST), University of Science (Vietnam National University Ho Chi Minh City), Vietnam, and Osaka University, Japan. Submission Guidelines: All papers must be original and not simultaneously submitted to another journal or conference. The authors are invited to submit their full papers by May 31, 2023. The submissions will be peer-reviewed for originality and scientific quality. Authors are requested to prepare their papers in the Springer format. Submissions should not exceed 12 pages and must be submitted as PDF electronically through the conference's CMT submission page. List of Topics Relevant topics for the IUKM 2023 Symposium include (but are not limited to) the following: — Theory and Methodology • Uncertainty formalisms: Bayesian probability, Dempster-Shafer theory, imprecise probability, random sets, rough sets, fuzzy sets and interval methods • Modelling uncertainty and inconsistency in big data • Learning and reasoning with uncertainty • Logics for reasoning under uncertainty • Uncertainty modelling in machine learning and deep learning • Information fusion and knowledge integration in uncertain environments • Decision making under various types of uncertainty • Aggregation operators for decision making • Copulas for dependence modelling • Granular and soft computing • Computational intelligence — Application • Data mining and knowledge discovery • Multi-agent reinforcement learning • Ontology engineering and Semantic Web • Privacy preserving data analysis • Intelligent data analysis and modelling • Agents and argumentation • Natural language processing • Medical informatics and bioinformatics • Ranking and recommendation systems • Big data and cloud computing • Social network analysis and mining • Sensor fusion • System identification and modelling • Diagnosis and reliability • Decision support systems • Kansei/affective engineering • Service computing • Engineering management • Supply chain management • Environmental management • Economics and econometrics • Statistics and Applications ——————————————————————————————————————————— Publication As done in previous editions, the proceedings of IUKM 2023 will be published by Springer-Verlag in the Lecture Notes in Artificial Intelligence series, and be available at the Conference. Authors of selected accepted IUKM 2023 papers will be also invited to submit substantially extended and updated version of their work for possible inclusion in a special issue of Annals of Operations Research. _______________________________________________ General Chairs: Masahiro Inuiguchi (Osaka University, Japan) Youji Kohda (Japan Advanced Institute of Science and Technology, Japan) Program Chairs: Van-Nam Huynh (Japan Advanced Institute of Science and Technology, Japan) Bac H. Le (University of Science, Vietnam National University (VNU)-Ho Chi Minh City, Vietnam) Katsuhiro Honda (Osaka Prefecture University, Japan)

1 0

2nd Call for papers: GRID Workshop @ KR2023
by Sihem Belabbes 17 May '23

17 May '23

** Apologies for multiple postings ** CALL FOR PAPERS The First International Workshop on Graphical Reasoning with Imperfect Data, collocated with KR2023 (https://imsva91-ctp.trendmicro.com:443/wis/clicktime/v1/query?url=https%3a%…) Website: GRID2023 [1] INTRODUCTION The quality of real-world data is a major issue in many application domains, especially in data-intensive AI applications. As a matter of fact, the presence of inconsistent, incomplete, inaccurate or uncertain data may not only hamper problem modeling and solving, but also the process of explaining the solutions. More theoretical approaches, on the other hand, have provided graphical tools for principled knowledge representation and reasoning that are much more transparent than opaque real-world AI applications. Indeed, graphical models such as Bayesian networks, knowledge graphs and ontologies have long been used to facilitate the representation of and the reasoning with imperfect data. By providing a visual dimension, they contribute to increasing the understanding of the problem, and thus help practitioners, users (lay and expert) as well as engineers in designing solutions that improve trust, efficiency and transparency. The GRID workshop aims at bringing the applied and the theoretical approaches together for the benefit of both. Real-world applications can gain in explainability through the use of graphical models, while addressing the intrinsic challenges of poor quality data can improve the understanding and use of graphical models. Small workshops are often organised around one unifying theme, be it a methodological theme or a challenge. We here focus on both a methodological theme and a challenge. Our approach will bring together 1) a variety of methods drawing on graphical representation and 2) a variety of application domains dealing with different aspects of imperfect data. The varieties generate the necessary distance between approaches to provide opportunities for cross-pollination, while similarities of methods and domains make for a sufficient closeness guaranteeing mutual relevance. TOPICS This workshop welcomes submissions dealing with the general topics of graphical models and imperfect data and their integration, from the perspective of knowledge representation and reasoning. A non-exhaustive list of keywords includes: + Bayesian nets + Markov nets + Credal nets + Dung-style argumentation + Knowledge graphs + Ontologies + Data visualization tools + Inconsistent data + Uncertain data + Data integration + Multi-source data + Heterogeneous data + Consistency maintenance + Real-world data + Data imputation + Missing data + Spurious data + Data loss + Outliers + Adversarial data SUBMISSION GUIDELINES Papers should be formatted according to the LNCS style and submitted as a single PDF file. We welcome submissions of theoretical and practical work including early-stage research ideas, methods, tools and applications. We welcome short papers (2-6 pages), and long papers (up to 12 pages). All accepted papers will be considered for an oral presentation. The reviewing process will be light and driven more by relevance to the workshop and the paper's potential to foster discussion than by the technical maturity of the contribution. Workshop submissions and camera-ready versions will be handled by EasyChair. Please submit at: https://easychair.org/my/conference?conf=grid2023 IMPORTANT DATES - May 31, 2023: Submission deadline - July 4, 2023: Paper notification - July 31, 2023: Camera-ready papers due PROCEEDINGS The accepted papers will appear on the workshop website and the online proceedings will be non-archival. The copyright will remain with the authors. ORGANIZING COMMITTEE Sihem Belabbes, LIASD, IUT de Montreuil, Université Paris 8, France. Jürgen Landes, University of Milan, Italy. PROGRAM COMMITTEE Leila Amgoud (CNRS, Université Toulouse 3, FR), Martin Adamčík (Assumption University, TH), Paolo Baldi (University of Milan, IT), Sadok Ben Yahia (Tallinn University of Technology, EE), Salem Benferhat (Université d'Artois, FR), Meghyn Bienvenu, (CNRS, Université de Bordeaux, FR), Richard Booth (Cardiff University, UK), Camille Bourgaux (Ecole Normale Supérieure, FR), Katarina Britz (Stellenbosch University, SA), Giovanni Casini (ISTI-CNR, IT), Esther Anna Corsi (University of Milan, IT), Madalina Croitoru (Université de Montpellier, FR), Glauber De Bona (Universidade de São Paulo, BR), Francesco De Pretis (University of Modena and Reggio Emilia, IT), Andreas Herzig (CNRS, Université Toulouse 3, FR), Saïd Jabbour (Université d'Artois, FR), Mardi Jankowitz (University of South Africa, SA), Souhila Kaci (Université de Montpellier, FR), Myriam Lamolle (Université Paris 8, FR), Marie-Jeanne Lesot (Sorbonne Université, FR), Quentin Manière (Universität Leipzig, DE), Nédra Mellouli (Université Paris 8, FR), Tommie Meyer (University of Cape Town, SA), Petrus Potgieter (University of South Africa, SA), Soroush Rafiee Rad (ILLC Universiteit van Amsterdam, NL), Adrien Revault d'Allonnes (Université Paris 8, FR), Kai Sauerwald (FernUniversität in Hagen, DE), Karima Sedki (Université Paris 13, FR), Tom Sterkenburg (Ludwig-Maximilians-Universität Munich, DE), Chris Swanepoel (University of South Africa, SA), Karim Tabia (Université d'Artois, FR), Matthias Thimm (FernUniversität in Hagen, DE), Ivan Varzinczak (Université Paris 8, FR), Srdjan Vesic (CNRS, Université d'Artois, FR). CONTACT belabbes@1 and juergen_landes@2 1: iut.univ-paris8.fr 2: yahoo.de Links: ------ [1] https://jlandes.wordpress.com/graphical-reasoning-with-imperfect-data-grid-…

1 0