J. Dezert- Ph. D.
- Senior Researcher & Maître de Recherches at The French Aerospace Lab / ONERA
J. Dezert
- Ph. D.
- Senior Researcher & Maître de Recherches at The French Aerospace Lab / ONERA
About
448
Publications
51,506
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
8,731
Citations
Introduction
Current institution
The French Aerospace Lab / ONERA
Current position
- Senior Researcher & Maître de Recherches
Publications
Publications (448)
Despite advances in integrating reasoning based on belief functions to generalise probabilistic representations, distance-to-prototype-based evidential deep neural networks are still emerging and require further consolidation. Existing studies in segmentation or classification tasks typically perform prior initialisation and do not address or mitig...
Quantum Dempster-Shafer Theory (QDST) uses quantum interference effects to derive a quantum mass function (QMF) as a fuzzy metric type from information obtained from various data sources. In addition, QDST uses quantum parallel computing to speed up computation. Nevertheless, the effective management of conflicts between multiple QMFs in QDST is a...
In Dempster-Shafer evidence theory (DST), the determination of basic belief assignment (BBA) is an important yet challenging issue. The rational mass determination of compound focal elements is crucial for fully taking advantage of DST, i.e., the ability to represent the ambiguity. In this paper, for the compound focal elements, we select and const...
![Fig. 1. Evidential Lite-CF Architecture: Road Detection [8].](profile/Danut-Vasile-Giurgi-4/publication/383223378/figure/fig1/AS:11431281273169774@1724415026325/Evidential-Lite-CF-Architecture-Road-Detection-8_Q320.jpg)
In the domain of autonomous vehicles, perception tasks are very complex, and deep learning can be coupled with evidence theory for uncertainty management of perception models. If the pieces of evidence involved in the merging process of the deep learning-based model are discordant, the results can be degraded. Therefore, verifying the conflicting l...
This paper proposes to establish the distance between partial preference orderings based on two very different approaches. The first approach corresponds to the brute force method based on combinatorics. It generates all possible complete preference orderings compatible with the partial preference orderings and calculates the Frobenius distance bet...
Traditional pattern recognition systems, tasked with categorizing inputs into known classes, often struggle when they encounter samples they haven't been trained to recognize. This introduces the need for the open set recognition-enhancing models to reject unidentified samples effectively. The Openmax method represents a significant breakthrough in...
In self-navigation problems for autonomous vehicles, the variability of environmental conditions, complex scenes with vehicles and pedestrians, and the high-dimensional or real-time nature of tasks make segmentation challenging. Sensor fusion can representatively improve performances. Thus, this work highlights a late fusion concept used for semant...
Dempster-Shafer evidence theory (DST) is a theoretical framework for uncertainty modeling and reasoning, with modeling the basic belief assignment (BBA) as one of its most crucial and challenging tasks. The prevailing BBA determination methods have their own pros and cons, and the joint use of them is expected to provide a better BBA. To realize an...
In multimodal learning, multimodal coordinated representation is an important yet challenging issue, which establishes the interaction between different modalities to describe multimodal data more effectively. Existing coordinated representation methods are implemented in the deep feature space (or encoding space) of each modality. In this paper, b...
This paper is about the Compromise Ranking Problem (CRP), a well-known problem in the social choice theory. According to the famous Arrow's theorem there is no voting method which is entirely satisfying and fairness if one accepts Arrow's axioms. In this paper we formalize the problem as a minimisation problem in a discrete finite search space. We...
This paper analyzes the behavior of the well-known Spearman's footrule distance (F-distance) to measure the distance between two rankings over the same set of objects. We show that F-distance is not invariant to labeling, and therefore, it suffers from a serious drawback for its use in applications. To circumvent this problem, we propose a new dist...
This paper investigates another global fusion (i.e., N-dimensional) rule of combination (NRoC) called the Weighted Conflict Redistribution #2 (WCR2), which fuses disparate sources of information simultaneously by making use of tensor geometry. WCR2 is the second NRoC of its kind, second to Harris-Lovassy NRoC, which is WCR1. These WCRs address two...
When solving real-world decision-making problems, it is important to deal with imprecise quantitative values modeled by numerical intervals. Although a different extension of the multi-criteria decision-making methods could deal with intervals, many of them are complex and lack such properties as robustness to rank reversal. We present an extension...
This fifth volume on Advances and Applications of DSmT for Information Fusion collects theoretical and applied contributions of researchers working in different fields of applications and in mathematics, and is available in open-access. The collected contributions of this volume have either been published or presented after disseminating the fourth v...
This paper analyzes the different definitions of a negator of a probability mass function (pmf) and a Basic Belief Assignment (BBA) available in the literature. To overcome their limitations we propose an involutory negator of BBA, and we present a new indirect information fusion method based on this negator which can simplify the conflict manageme...
This paper introduces the concept of cross-entropy and relative entropy of two basic belief assignments. It is based on the new entropy measure presented recently. We prove that the cross-entropy satisfies a generalized Gibbs-alike inequality from which a generalized Kullback-Leibler divergence measure can be established in the framework of belief...
Human Activity Recognition (HAR) based on wear-able device has become a hot topic of research due to its wide range of applications in health-care, fitness and smart homes. However, the classification of some activities with similar sensor readings, such as standing and sitting, is usually more challenging for the design of efficient activity recog...
Human Activity Recognition (HAR) based on sensor information has become a hot topic of research due to its wide range of applications in health-care, fitness and smart homes. However, the classification of activities with similar sensor signals such as standing and sitting is usually more challenging for the design of efficient activity recognition...
The belief functions (BFs) introduced by Shafer in the mid of 1970s are widely applied in information fusion to model epistemic uncertainty and to reason about uncertainty. Their success in applications is however limited because of their high-computational complexity in the fusion process, especially when the number of focal elements is large. To...
This short technical note points out an erroneous claim about a new rule of combination of basic belief assignments presented recently by Kenn et al. in [1], referred as Kenn's rule of combination (or just as KRC for short). We prove thanks a very simple counterexample that Kenn's rule is not associative. Consequently, the results of the method pro...
In this paper, we present a method to solve analytically the simplest Entropiece Inversion Problem (EIP). This theoretical problem consists in finding a method to calculate a Basic Belief Assignment (BBA) from the knowledge of a given entropiece vector which quantifies effectively the measure of uncertainty of a BBA in the framework of the theory o...
In this paper, we present a method to solve analytically the simplest Entropiece Inversion Problem (EIP). This theoretical problem consists in finding a method to calculate a Basic Belief Assignment (BBA) from the knowledge of a given entropiece vector which quantifies effectively the measure of uncertainty of a BBA in the framework of the theory o...
In this paper, we present a measure of Information Content (IC) of Basic Belief Assignments (BBAs), and we show how it can be easily calculated. This new IC measure is interpreted as the dual of the effective measure of uncertainty (i.e. generalized entropy) of BBAs developed recently.KeywordsBelief functionsInformation contentGeneralized entropy
Thunderstorms, the main generator of lightning on earth, are characterized by the presence of extreme atmospheric conditions (turbulence, hail, heavy rain, wind shear, etc.). Consequently, the atmospheric conditions associated with this kind of phenomenon (in particular the strike itself) can be dangerous for aviation. This study focuses on the est...
This paper presents a new effective measure of uncertainty (MoU) of basic belief assignments. This new continuous measure is effective in the sense that it satisfies a small number of very natural and essential desiderata. Our new simple mathematical definition of MoU captures well the interwoven link of randomness and imprecision inherent to basic...
![Illustration of the refinement function ρ\documentclass[12pt]{minimal}...](publication/361732836/figure/fig1/AS:11431281123110057@1677641268744/Illustration-of-the-refinement-function-rdocumentclass12ptminimal_Q320.jpg)
![The refinement frames of θi,j\documentclass[12pt]{minimal}...](publication/361732836/figure/fig2/AS:11431281123117275@1677641268777/The-refinement-frames-of-thi-jdocumentclass12ptminimal-usepackageamsmath_Q320.jpg)
Data association has become pertinent task to interpret the perceived environment for mobile robots such as autonomous vehicles. It consists in assigning the sensor detections to the known objects in order to update the obstacles map surrounding the vehicle. Dezert–Smarandache Theory (DSmT) provides a mathematical framework for reasoning with imper...
In information fusion, the uncertain information from different sources might be modeled with different theoretical frameworks. When one needs to fuse the uncertain information represented by different uncertainty theories, constructing the transformation between different frameworks is crucial. Various transformations of a Fuzzy Membership Functio...
In this paper, we present a fast Belief Function based Inter-Criteria Analysis (BF-ICrA) method based on the canonical decomposition of basic belief assignments defined on a dichotomous frame of discernment. This new method is then applied for evaluating the Multiple-Objective Ant Colony Optimization (MO-ACO) algorithm for Wireless Sensor Networks...
In recent years, wearable sensor-based human activity recognition (HAR) is becoming more and more attractive, especially in health monitoring and sports management. However, in order to obtain high-quality HAR, it is often necessary to get sufficient labeled activity data, which is very difficult, time-consuming and costly in a natural environment....
In pattern classification, there may not exist labeled patterns in the target domain to train a classifier. Domain adaptation (DA) techniques can transfer the knowledge from the source domain with massive labeled patterns to the target domain for learning a classification model. In practice, some objects in the target domain are easily classified b...
This paper describes a complete solution of a new dropped wireless sensor network (called “abandoned” since it is never picked up) dedicated to intelligence operation. The sensor network, named SEXTANT for Smart sEnsor X for Tactical situation AssessmeNT and presented in this paper is the achievement of several years of research and development in...
The objective of this paper is to present a general methodology for storm risk assessment and prediction based on several physical criteria thanks to the belief functions framework to deal with conflicting meteorological information. For this, we adapt the Soft ELECTRE TRI (SET) approach to this storm context and we show how to use it on outputs of...
Levee security assessment is a complex expert assessment process based on several heterogeneous data. In our previous research works, we applied information fusion techniques to characterize flood protection levees. We used the proportional conflict redistribution rule no.6 (PCR6) proposed in DSmT (Dezert Smarandache Theory) framework to combine da...
In the theory of belief functions, the evidence combination is a kind of decision-level information fusion. Given two or more Basic Belief Assignments (BBAs) originated from different information sources, the combination rule is used to combine them to expect a better decision result. When only a combined BBA is given and original BBAs are discarde...
We present a new methodology for decision-making support based on belief functions thanks to a new theoretical canonical decomposition of dichotomous basic belief assignments (BBAs) that has been developed recently. This decomposition based on proportional conflict redistribution rule no 5 (PCR5) always exists and is unique. This new PCR5-based dec...
We present a new methodology for decision-making support
based on belief functions thanks to a new theoretical canonical decomposition of dichotomous basic belief assignments (BBAs) that has been developed recently. This decomposition based on proportional conflict redistribution rule no 5 (PCR5) always exists and is unique. This new PCR5-based dec...
In this paper, we propose a new fusion approach to combine basic belief assignments (BBAs) defined on a di-chotomous frame of discernment based on their canonical decomposition. In a companion paper, we have already proved that the canonical decomposition of this type of BBA (called dichotomous BBA) is always possible and unique thanks to the propo...
In Body Sensor Networks (BSNs), evaluating reliability of sensors is an important research topic which aims to optimize the overall performance of BSNs. Previous studies have often addressed this problem based only on a single criterion. However, it is often unreliable to rely on a single criterion to assess sensors in real situations. Accordingly,...
This paper discusses and analyzes the behaviors of the Proportional Conflict Redistribution rules no. 5 (PCR5) and no. 6 (PCR6) to combine several distinct sources of evidence characterized by their basic belief assignments defined over the same frame of discernment. After a brief review of these rules, the paper shows through simple examples why t...
In original Belief Functions (BF) theory, precise-valued belief structure has been widely used to represent uncertain information. However, this mentioned belief structure is difficult to effectively measure the specific hesitant situation, especially when decision makers have a set of possible values for the belief assignments of focal elements. I...
The methods for combining multiple classifiers based on belief functions require to work with a common and complete (closed) Frame of Discernment (FoD) on which the belief functions are defined before making their combination.This theoretical requirement is however difficult to satisfy in practice because some abnormal (or unknown) objects that do...
The paper presents a study on the human learning process during the classification of stimuli, defined by motion and color visual cues and their combination. Because the classification dimension and the features that define each category are uncertain, we model the learning curves using Bayesian inference and more precisely the Normalized Conjuncti...
In this paper we present two applications of a new Belief Function-based Inter-Criteria Analysis (BF-ICrA) approach for the assessment of redundancy of criteria involved in Multi-Criteria Decision-Making (MCDM) problems. This BF-ICrA method allows to simplify the original MCDM problem by suppressing redundant criteria (if any) and thus diminish the...
We present a new methodology for decision-making support based on belief functions thanks to a new theoretical canonical decomposition of dichotomous basic belief assignments (BBAs) that has been developed recently. This decomposition based on proportional conflict redistribution rule no 5 (PCR5) always exists and is unique. This new PCR5-based dec...
In the applications of domain adaptation (DA), there may exist multiple source domains, and each source domain usually provides some auxiliary information for object classification. The combination of such complementary knowledge from different source domains is helpful for improving the accuracy. We propose an evidential combination of augmented m...
In this paper, we propose a new Multi-Criteria Decision-Making method (MCDM) which is rank reversal free. We call it the SPOTIS method standing for Stable Preference Ordering Towards Ideal Solution method. Our method is exempt of rank reversal because the preference ordering established from the score matrix of the MCDM problem under consideration...
The management and combination of uncertain, imprecise, fuzzy and even paradoxical or highly conflicting sources of information has always been, and still remains today, of primal importance for the development of reliable modern information systems involving artificial and approximate reasoning. In this short paper, we present an introduction of o...
In this paper, we propose a new fusion approach to combine basic belief assignments (BBAs) defined on a di-chotomous frame of discernment based on their canonical decomposition. In a companion paper, we have already proved that the canonical decomposition of this type of BBA (called dichotomous BBA) is always possible and unique thanks to the propo...
Data association is one of the main tasks to achieve in perception applications. Its aim is to match the sensor detections to the known objects. To treat such issue, recent research focus on the evidential approach using belief functions, which are interpreted as an extension of the probabilistic model for reasoning about uncertainty. The data fusi...
Data association is one of the main tasks to achieve in perception applications. Its aim is to match the sensor detections to the known objects. To treat such issue, recent research focus on the evidential approach using belief functions, which are interpreted as an extension of the probabilistic model for reasoning about uncertainty. The data fusi...
Classifier fusion remains an effective method to improve classification performance. In applications, the classifiers learnt using different attributes may work with various frames of discernment (FoD) of classification. There generally exist more or less complementary knowledge among these classifiers. However, how to efficiently combine such clas...
In this paper, we prove that any dichotomous basic belief assignment (BBA) m can be expressed as the combination of two simple belief assignments m p and m c called, respectively, the pros and cons BBAs thanks to the proportional conflict redistribution rule no 5 (PCR5). This decomposition always exists and is unique and we call it the canonical de...
Multi-sensor fusion strategies have been widely applied in Human Activity Recognition (HAR) in Body Sensor Networks (BSNs). However, the sensory data collected by BSNs systems are often uncertain or even incomplete. Thus, designing a robust and intelligent sensor fusion strategy is necessary for high-quality activity recognition. In this paper, Dez...
The management and combination of uncertain, imprecise, fuzzy and even paradoxical or highly conflicting sources of information has always been, and still remains today, of primal importance for the development of reliable modern information systems involving artificial reasoning. In this introduction, we present a survey of our recent theory of pl...
The dynamical systems in various science and engineering problems are often governed by nonlinear equations (differential equations). Due to insufficiency and incompleteness of system information, the parameters in such equations may have uncertainty. Interval analysis serves as an efficient tool for handling uncertainties in terms of closed interv...
In many machine learning tasks, it is usually difficult to obtain enough labeled samples. Semi-supervised learning that exploits unlabeled samples in addition to labeled ones has attracted a lot of research attentions. Traditional semi-supervised methods may encounter uncertainty problems and information loss when dealing with those samples having...
This paper addresses the assessment of trust in items reported by opportunistic sources and develops a model taking into account the reliability of sources and the credibility of information. Opportunistic sources are witnesses describing events, scenes or actions of interest and often such sources may also indicate confidence, doubt, skepticism or...
In this paper we present a simple formulation of the Generalized Bayes' Theorem (GBT) which extends Bayes' theorem in the framework of belief functions. We also present the condition under which this new formulation is valid. We illustrate our theoretical results with simple examples.
The theory of belief functions is an important tool in the field of information fusion. However, the fusion of Basic Belief Assignments (BBAs) requires high computational cost and long computing time when a large number of focal elements are involved in the fusion rules. This problem becomes a bottleneck of application of Belief Functions (BF) in h...
In this paper we propose a new Belief Function-based Inter-Criteria Analysis (BF-ICrA) for the assessment of the degree of redundancy of criteria involved in a multicriteria decision making (MCDM) problem. This BF-ICrA method allows to simplify the original MCDM problem by withdrawing all redundant criteria and thus diminish the complexity of MCDM...
The evidence combination is a kind of decision-level information fusion in the theory of belief functions. Given two basic belief assignments (BBAs) originated from different sources, one can combine them using some combination rule, e.g., Dempster's rule to expect a better decision result. If one only has a combined BBA, how to determine the origi...
To combine different types of uncertain information from different sources under different frameworks, we need transformations between different frameworks. For the transformation of a fuzzy membership function (FMF) into a basic belief assignment (BBA), several approaches have been proposed. Among these approaches, the uncertainty optimization bas...
In this paper we present an application of a new Belief Function-based Inter-Criteria Analysis (BF-ICrA) approach for Global Positioning System (GPS) Surveying Problems (GSP). GPS surveying is an NP-hard problem. For designing Global Positioning System surveying network, a given set of earth points must be observed consecutively. The survey cost is...
Belief function theory manages uncertain information and offers useful combination rules for multi-sensor fusion. However, when sensor readings are in conflict or even unreliable, the quality of the fusion result is significantly affected. Recently, many discounting approaches have been proposed to combine unreliable sensor readings. The discountin...
The management and combination of uncertain, imprecise, fuzzy and even paradoxical or highly conflicting sources of information has always been, and still remains today, of primal importance for the development of reliable modern information systems involving artificial reasoning. In this introduction, we present a survey of our recent theory of pl...
Evidence theory, also called belief functions theory, provides an efficient tool to represent and combine uncertain information for pattern classification. Evidence combination can be interpreted, in some applications, as classifier fusion. The sources of evidence corresponding to multiple classifiers usually exhibit different classification qualit...
Dempster-Shafer evidence theory, also called the theory of belief function, is widely used for uncertainty modeling and reasoning. However, when the size and number of focal elements are large, the evidence combination will bring a high computational complexity. To address this issue, various methods have been proposed including the implementation...
In mountainous areas, decision-makers must find the best solution to protect elements-at-torrential risk. The decision process involves several criteria and is based on imperfect information. Classical Multi-Criteria Decision-Aiding methods (MCDAs) are restricted to precise criteria evaluation for decision-making under a risky environment and suffe...
Image registration is a crucial and fundamental problem in image processing and computer vision, which aims to align two or more images of the same scene acquired from different views or at different times. In image registration, since different keypoints (e.g., corners) or similarity measures might lead to different registration results, the selec...
In order to pursue the high accuracy in classification task, we propose a new pattern classification accuracy improvement (CAI) method working with local quality matrix. The quality matrix expresses the conditional probability of the object belonging to one class when classified to another class, and it is estimated based on the K-nearest neighbors...
The extraction of building changes from very high resolution
satellite images is an important but challenging task in remote
sensing. Digital Surface Models (DSMs) generated from stereo
imagery have proved to be valuable additional data sources for
this task. In order to efficiently use the change information from
the DSMs and spectral images, beli...
This paper presents two new theoretical contributions
for reasoning under uncertainty: 1) the Total Belief
Theorem (TBT) which is a direct generalization of the Total
Probability Theorem, and 2) the Generalized Bayes’ Theorem
drawn from TBT. A constructive justification of Fagin-Halpern
belief conditioning formulas proposed in the nineties is also...
In this paper, new theoretical results for reasoning with belief functions are obtained and discussed. After a judicious decomposition of the set of focal elements of a belief function, we establish the total belief theorem (TBT). which is the direct generalization of the total probability theorem when working in the framework of belief functions....
The classifier based on rough sets is widely used in
pattern recognition. However, in the implementation of rough setbased
classifiers, there always exist the problems of uncertainty.
Generally, information decision table in Rough Set Theory
(RST) always contains many attributes, and the classification
performance of each attribute is different. It...
In this paper the notion of (probabilistic) independence
of two events defined classically in the theory of
probability is extended in the theory of belief functions as
the credibilistic independence of two propositions. This new
notion of independence which is compatible with the probabilistic
independence as soon as the belief function is Bayesia...
Questions
Question (1)
Snowball metrics is used by scival.com to report some performance indicators. This metrics seems rather obscure from the mathematical standpoint. Unfortunately there is apparently (after a quick google search) no detailed mathematical paper with mathematical formula and simple numerical examples of this "metrics" showing how it is really calculated. This "snowball metrics" seems to make some fusion (or aggregation) of different metrics through only a web interface. But how this is done precisely and mathematically? What is the fusion process hidden under the hood?
This lack of transparency makes the method of scival.com quite doubtful, hazardous and maybe nor reliable and turstable (?). People using scival tools must know how it precisely works (if they want to figure out if this snowball metrics makes sense, or not). A full transparency of this metrics is very necessary imho for the benefit of all.
Is there somewhere a mathematical proof that "Snowball metrics" is a true metrics from the mathematical standpoint? Maybe I miss a good mathematical paper about this question, if so please just provide the proper reference. Thank you in advance.
Can someone provide clarification? Thank you.
