|
with partnership of
 
 
 
 
 
|
Plenary talks
Possibility theory in
information fusion
Henri Prade
Institut de Recherche en Informatique de Toulouse (IRIT), France
Abstract
Possibility theory and the body of aggregation operations from fuzzy set theory
provide some tools to address the problem of merging information coming from
several sources. The approach to fusion is set-theoretic and the choice of
conjunctive versus disjunctive fusion modes depends on assumptions on whether
all sources are reliable or not. Quantified, prioritized and weighted and
fusion rules are described. A possibilistic logic counterpart of these
combination modes will be also briefly presented. The fusion of imprecise
information is carefully distinguished from the estimation problem. Fuzzy
extensions of estimation processes are also discussed. The approach, based on
conflict analysis, applies to sensor fusion, aggregation of expert opinions as
well as the merging of databases especially in case of poor, qualitative
information.
Short biography
Henri Prade (Institut de Recherches en Informatique de Toulouse) is a
"Directeur de Recherche" at C.N.R.S. He received a Doctor-Engineer
degree (1977), his "Doctorat d'Etat" (1982) and the"Habilitation
à Diriger des Recherches" (1986). He is the author or the co-author
of a large number of technical papers on uncertainty modelling and
applications. With Didier Dubois he is the co-author of two monographs on fuzzy
sets (Academic Press,1980) and possibility theory (Plenum Press, 1988), and the
co-editor of the 7 volume "Handbooks of Fuzzy Sets Series" (Kluwer,
1998-2000). He is also the co-editor (with D. Dubois and R. Yager) of a volume
entitled "Fuzzy Information Engineering: A Guided Tour of
Applications" (Wiley, 1997). He is co-editor-in chief of Fuzzy Sets and
Systems and a member of the the Editorial Board of several scientific journals
including IEEE Transactions on Fuzzy Systems, the Artificial Intelligence J.,
the Inter. J. of Approximate Reasoning, the Inter. J. of Intelligent Systems,
the J. of Intelligent Information Systems, Fundamenta Informaticae, Information
Sciences, Soft Computing, Pattern Analysis and Applications among others. His
current research interests are in uncertainty and preference modelling,
non-classical logics, approximate and plausible reasoning and decision with
applications to Artificial Intelligence and Information Systems.
Dr. Henri PRADE
Institut de Recherche en Informatique de Toulouse (IRIT)
Universite Paul Sabatier
Bat. 1R3
118 route de Narbonne
31062 Toulouse Cedex 4 France
Tel.: from France: +33 5.61.55.65.79; Fax: +33 5.61.55.62.39
Email: Henri.Prade@irit.fr
Data Fusion in the
transferable belief model
Philippe Smets
IRIDIA - Université Libre de Bruxelles,
Belgium
Abstract
When Shafer introduces his theory of evidence based on the use
of belief functions, he proposed a rule to combine the belief functions induced
by distinct pieces of evidence. Since then, theoretical justifications of this
so-called Dempster's rule of combination have been produced and the meaning of
distinctness has been assessed. We will presents practical applications where
the fusion of uncertain data is well achieved by Dempster's rule of
combination. It is essential that the meaning of the belief functions used to
represent uncertainty be well fixed, as the adequacy of the rule depends
strongly on a correct understanding of the context in which they are applied.
Missing to distinguish between the upper and lower probabilities theory and the
transferable belief model can lead to serious confusions, as Dempster's rule of
combination is central in the transferable belief model whereas it hardly fits
with the upper and lower probabilities theory.
In order to illustrate the possibilities that are offered by the transferable
belief model when it comes to uncertain data fusion, we present some practical
applications. For each of them, the transferable belief model seems well
adapted whereas the classical probability theory might encountered problems,
usually because of some missing information that probability theory requires
and that is not available or worse, not existent.
Short biography
Philippe Smets has a MD and a PhD in Medical Statistics. He was Professor of
Medical Statistics at Université Libre de Bruxelles (ULB). From 1985 to
1999, he was director of IRIDIA, the Institut de Recherches Interdisciplinaires
et de Développements en Intelligence Artificielle, at ULB. He retired in
1999. Over the last few years, he has published over 100 research papers on
quantified approximate reasoning and diagnosis. In particular, he developed
many new methods within the framework of the transferable belief model, a model
to represent quantified beliefs based on belief functions. He is member of the
editorial board of most journals and of the program committee of most
conferences dealing with uncertainty in artifical intelligence. He participated
to several Belgian and European Research and Development Programs. Among
others, he was prime contractor of the ESPRIT projects DRUMS, DRUMS2, UMIS and
FUSION, all dealing with uncertainty and imprecision.
Professor Philippe Smets
web:
http://iridia.ulb.ac.be/~psmets
IRIDIA-CP 194/6, Universite Libre de Bruxelles
50 av. Roosevelt, 1050 Bruxelles, Belgium.
email: psmets@ulb.ac.be
Tel : 32 2 650 27 29; Fax : 32 2 650 27 15
Hypermodality,
shift in mode of evaluation in modal logic
Dov M Gabbay
Professor of Computing Science, Professor of
Philosophy
Docteur Honoris Causa Universite Paul SabatierToulouse III
Augustus De Morgan Professor of Logic
King's College Strand, London
Abstract
The author will discuss logical systems where a connective in a
formula can shift meaning according to his place of occurence in the formula.
In semantical terms this means that evaluation changes mode as one goes along.
Such logics have wide range of applications from time action resource models to
generalised quantifiers. A methodology is presented whereby any connective can
be shifted (ie become a hyperconnective)
Short biography
Dov M. Gabbay is Professor at the Department of Philosophy and the Department
of Computer Science at King's College, London. He received a BSc in Mathematics
and Physics and an MSc in Logic from Hebrew University, Jerusalem in 1966 and
1967, respectively. In 1969 he completed his PhD in Logic, also at Hebrew
University. He has been Assistant (1970-1973) and Associate (1973-1975)
Professor of Philosophy at Stanford University, Professor of Logic at Bar-Ilan
University (1977-1983) , and Professor of Computing at Imperial College London
(1983-1998). He joined King's College in 1998. He has also been a Visiting
Member of the Royal Society and Visiting Research Professor, Mathematics
Institute, University of Oxford (1978); Visiting Research Professor of Logic
and Language, University of Tübingen (1988); Visiting Research Professor
of Logic and Language, University of Munich (1990); Visiting Professor of Logic
and Language, University of Stuttgart (1992); A Research Professor, Max-Planck
Institute, Saarbruecken (1991-1995) and a Visiting Professor of Philosophy,
King's College, London (1997). During 1979-1981, he served as Chairman,
Department of Mathematics and Computer Science, Bar-Ilan University. During
1985-1996, he was an Adjunct Professor, University of Georgia and during
(1992-1997), he has got a SERC Senior Research (sabbatical) Fellowship at
Imperial College. His research interests include Logic and Computation,
Dynamics of Practical Reasoning, Proof Theory and Goal-directed Theorem
Proving, Non-classical Logics and Non-monotonic Reasoning, Labelled Deductive
Systems, Fibring Logics, and Logical Modelling of Natural Language. More
recently he has been looking at practical reasoning structures in Plato and
Aristotle. Professor Dov M. Gabbay is one of the world's most active and
influential researchers in logic. He has published over two hundred research
papers and many books and he is Editor of several international journals,
Executive of European Foundation of Logic Language and Information and
president of The International IGPL Logic Group.
Dov M Gabbay
King's College Strand, London WC2R 2LS
Email : dg@dcs.kcl.ac.uk
Telephone: + 44 20 7848 2930
Fax: + 44 20 7240 1071
www.dcs.kcl.ac.uk/staff/dg/
www.kcl.ac.uk/kis/schools/hums/philosophy/staff/dovg.html
Information
Fusion and Inference Networks: Evidential Foundations
Professor David A. Schum
George Mason University, USA
Applied Probability, Human Information Processing,
Inference Analysis, Cognitive Science
Abstract
Devices frequently employed in the fusing of information in
many situations come in the form of complex inference networks. The
construction and analysis of inference networks have a surprisingly long
history, dating back to 1913 in the work of an American legal evidence scholar
named John H. Wigmore. Methods for probabilistic analyses of complex inference
networks have a more recent history and now form an area of vigorous research.
Many of the current strategies for analyzing inference networks rest on
extensions of Bayes's rule and are collectively referred to as Bayes's Nets.
Inference networks can take many forms and can capture an assortment of
probabilistic interactions or nonindependencies among the variables represented
on an inference network. Most of the current work on Bayes's Nets has involved
the development of algorithms for the efficient propagation of probabilities
throughout a network as new evidence arrives. But not so much attention has
been paid to the fact that there are many logically distinguishable and
recurrent forms and combinations of evidence that can serve to activate an
inference network. Different forms of evidence require different methods for
establishing the credibility or believability of evidence. This is a most
important step in the fusion of evidence since credibility-related
considerations form the very foundation for all subsequent arguments based on
evidence. Part of my talk involves how these important credibility-related
foundations are established in the analysis of inference networks. It is also
true that evidence performs different roles in the analysis of inference
networks. Some evidence directly instantiates nodes or probabilistic variables
on an inference network. Such evidence is said to be directly relevant
evidence. But other evidence, termed indirectly relevant or ancillary evidence,
serves to justify the probabilistic strength of the arcs or linkages on an
inference network. There is some controversy at present about the role of
ancillary evidence in the analysis of Bayes's Nets that I will also address. In
the process, I will show how many of the original insights Wigmore had 1913
about the construction of inference networks deserve more serious consideration
than they are in fact receiving today.
Short biography
David A. Schum - received the B.A. and M.A. degrees from Southern Methodist
University and the Ph.D. degree from Ohio State University, the latter in 1964.
Following a two-year post-doctoral appointment at the Laboratory of Aviation
Psychology at Ohio State, he joined the faculty of Rice University, where he
held appointments in the departments of Psychology and Mathematical Sciences
until 1985 (also an adjunct appointment at Baylor College of Medicine). In the
fall of 1985 he joined the faculty of George Mason University where he now
holds the rank of professor in the Department of Operations Research and
Engineering. He also holds the rank of professor in the George Mason School of
Law. He is coauthor of a book on probability theory and the author of three
books on evidence and inference. His other published works are to be found in
engineering, law and behavioral science journals and in various monographs. He
has had a career-long interest in both formal and behavioral evidential issues
in probabilistic reasoning. His research has involved: (i) study of recurrent
forms and combinations of evidence and the many subtleties they reveal, (ii)
study of ways to provide computer assistance in the task of drawing conclusions
from masses of evidence, and (iii) study of ways to enhance the process of
discovery in which new possibilities and evidence are generated.
David A. Schum
School of Information Technology and Engineering
School of Law
George Mason University
Fairfax, Virginia, USA
Email: schum@iet.com
Last Updated: May 22, 2000
Web site by: dezert@onera.fr (content),
gaultier@onera.fr (form)
copyright © ISIF 2000
|
