Fusion 2003 - Special session SS8

(As available on Feb 15th, 2003)

 

Fusion of conflictual information :

Plausible, paradoxical and neutrosophical reasoning.

 

Organizers :

Jean Dezert (Onera, France) and Florentin Smarandache (Univ. of New Mexico, USA)

 

Contacts : Jean.Dezert@onera.fr, smarand@unm.edu

 

Date : July 8-11, 2003

Location : Radisson hotel, Cairns, Australia

Web site : http://www.fusion2003.org

 

Email addresses of participants :

 

tchamova@bas.bg,signal@bas.bg, john.j.sudano@lmco.com, Hongyan.Sun@rmc.ca,

Laurence.Hubert@Uhb.Fr, gregoire.mercier@enst-bretagne.fr, samuel.corgne@Uhb.Fr,

mohammadkhosh@yahoo.com, liufeng49@sina.com, jebrenner@compuserve.com,

Patrick.Vannoorenberghe@univ-rouen.fr, milan.daniel@becherovka.cz, ajosang@dstc.edu.au, Jean.Dezert@onera.fr, smarand@unm.edu, Farooq@rmc.ca

 

List of papers (the order is subject to change) :

 

1 - Jean Dezert, Onera, France ;

Florentin Smarandache, Dept. of Mathematics, Univ of New Mexico, USA.

Title : "On the Generation of Hyper-powersets for the DSmT"

Abstract :  The recent theory of plausible and paradoxical reasoning (DSmT) developped by the authors appears to be a nice promising theoretical tools to solve many information fusion problems where a strong internal conflict between sources arise. The main idea of DSmT is to work on the hyper-powerset of the frame of discernment of the problem under consideration. Although the definition of hyper-powerset is well established, the major difficulty in practice is to generate such hyper-powerset in order to implement DSMT Fusion rule on computers. We propose in this paper an efficient algorithm for generating hyper-powersets and discuss the limitations of our computers to generate such sets when the dimension of the problem increases.

 

2 - Jean Dezert, Onera, France ;

Florentin Smarandache, Dept. of Mathematics, Univ of New Mexico, USA.

Title : "Partial Ordering of Hyper-powerset and Matrix Representation of Belief Function within DSmT Framework"

Abstract : In this paper we define a partial order on the hyper-power set of generlized frame of discernement and show how such partial order can help to obtain an easy an elegant representation of the relationship (linear transformation through unimodular triangular binary matrix) between the generalized mass function and belief functions in the DSmT framework. This representation  is useful for implementation of the combination rule of the DSmT and information fusion problems where strong internal conflict and paradoxes arise.

 

3 - Samuel Corgne, Laurence Hubert-Moy, CNRS Costel Lab, Rennes, France;

Jean Dezert, Onera, France;

Grégoire Mercier, ENST Bretagne, France.

Title : Land Cover Change Prediction with a New Theory of Plausible and Paradoxical Reasoning

Abstract : In intensive agricultural regions, land cover during winter has an important impact on the water quality, and the identification and monitoring of vegetation covering dynamics at high spatial scales constitute a prior approach for the restoration of water resources. The spatial prediction modeling of land cover at the field scale in winter that appears useful for land management and helping local decision making, is specially complex because of the high variability of the factors that motivate the land cover changes between each winter. Thus, uncertainty in the data and the results has to be integrated in the modelling process for better decision making. Dempster's fusion rule has been used in a preceding study to spatially predict the location of bare winter fields for the next season on a watershed located in an intensive agricultural region. The data integrated in the model come from different sources : remote sensing, expert knowledge and alphanumeric data. They statistically express the driven factors that motivate land cover changes : the past-observed bare soils, field size, distance from farm buildings and agro-environmental actions. Identified factors which support the hypothesis "bare soils" and "covered soils" are transformed through fuzzy membership functions into mass function maps before being fused using the Dempster's rule. The model well predicts the presence of bare soils on 4/5 of the total area, but clearly presents some limits in generating errors in land cover assignment when the level of conflict, between the sources of evidence that support the hypothesis, becomes important.To solve this problem, we applied the Dezert-Smarandache Theory (DSmT), which can be considered as a generalization of the Dempster-Shafer Theory (DST). In this new theory, the rule of combination takes into account both uncertain and paradoxical information. This method offers a specific framework because unlike the DST, the frame of discernment is exhaustive but not necessarily exclusive. Thus, any source of information that can be rational, uncertain or paradoxical can be combined. The aim of this study is to evaluate the  reliability of DSmT in managing conflicts between sources which support the hypothesis defined here to predict land cover vegetation presence in the fields. The framework is set up with the dealing of paradoxical information for the four sources of evidence, through an hyper-power set created with union and intersection operators. The fusion process applied is justified from the maximum entropy principle and decision making relies on a pignistic probability function. Results are presented and compared with the results drawn from the classical Dempster-Shafer theory.We point out that higher levels of well predicted fields are achieved for both assignment classes "bare soils" and "covered soils". Furthermore, the conflict management between the sources of evidence allows to spatially represent fields where the conflict is the strongest and to contribute to a better understanding of the factors that motivate land cover changes. Finally, the fusion process lead to relevant results to make a decision for the issue of bare soils reduction in agricultural intensive regions.Through this first application of the Dezert-Smarandache Theory, we show an example of this new approach ability to solve practical problems where the Dempster-Shafer usually fails.

 

4 - Mohammad Khoshevisan, School of Accounting and Finance, Griffith Univ. Australia ;

Sukanto Bhattacharya, School of Information and Technology, Bond University, Australia.

Title :"Information Fusion Based on Neutrosophic Logic to Reconcile Between Theoretical and Market Prices of Long-term Options Separated by Mass Cognitive Dissonance"

Abstract : In this paper we basically make two propositions - firstly a non-linear feedback process that is primarily fueled by mass cognitive dissonance could generate systematic deviations between the theoretical and market prices of long-term options, and secondly such deviations are best reconciled in terms of neutrosophic rather than rule-based reasoning, especially in the context of the users of automated trading systems designed to generate trading signals often based on analysis of information from conflicting sources. 

 

5 - Feng Liu, Associate Professor, School of Information, (xinxi xueyuan) Xi'an University of Finance and Economics, (Xi'an caijing xueyuan) No.44 Cuihua Nan Road, (cuihua nanlu 44 hao) Xi'an, Shaanxi, 710061, P. R. China

Title :" Toward Excitation and Inhibition in Neutrosophic Logic - A multiagent

Model Based on Ying-Yang Philosophy"

Abstract: Logic should have been defined as the unity of contradictions between logic director and logic implementation. Chinese Daoism asserts that everything is defined in the unity of opposites, namely yin and yang, accordingly yang conducts change and yin brings it up (I-ching, also known as Book of Changes). In this way logic is redefined in an indeterminate style to facilitate both <A> and <Anti-A> in neutrosophic logic. The unity of opposites is also described as neutrality in neutrosophy. An intermediate multi-referential model of excitation and inhibition is developed to derive a multiagent architecture of logic, based on Chinese yin-yang philosophy. This methodology of excitation/inhibition suggests a rhymed way of logic, leading to a dynamic methodology of weight strategy that links logic with neural network approach. It also confirms the crucial role of indeterminacy in logic as a fatal criticism to classical mathematics and current basis of science.

 

6 - Feng Liu, Associate Professor, School of Information, (xinxi xueyuan) Xi'an University of Finance and Economics, (Xi'an caijing xueyuan) No.44 Cuihua Nan Road, (cuihua nanlu 44 hao) Xi'an, Shaanxi, 710061, P. R. China

Title :"Truth and Absolute Truth in Neutrosophic Logic"

Abstract: As a philosophical analysis of some fatal paradoxes, the paper distinguishes the conceptual difference between representation of truth and source of truth, and leads to the conclusion that in order to acquire the genuine source of truth, independently of specific representations possibly belonging to different worlds, one is necessary to compromise even to get rid of all the ideas, logics, conceptions, philosophies and representable knowledge, returning to his infant nature, as a preliminary step for his cultivation of unconstrained wisdom. It also carries out some coordinative crucial issues as natural-doctrine, minded-unwitting, logic-infancy, conception-deconception, determinacy-indeterminacy. The paper tries to verify the role of neutrosophy and neutrosophic logic in religious issues and opens a gateway toward the oriental classics, excavating the lost treasure..

 

7 - Milan Daniel, Czech Academy of Sciences, Prague, Czech Republic ;

Audun Josang, DSTC, Brisbane, Qld 4001, Australia ;

Patrick Vannoorenberghe, PSI FRE 2645 CNRS,Université de Rouen, 76821 Mont Saint Aignan, France.

Title : "Strategies for Handling Conflicting Dogmatic Beliefs"

Abstract: The combination of possibly conflicting beliefs andevidence forms an important part of various disciplines of artificial reasoning. Dogmatic beliefs are expressed by observers when they are certain about the subject of interest. This paper describesmethods for combining belief when they are dogmatic.

 

8 - Joseph E. Brenner, Ph.D., P.O. Box 235, CH-1865 Les Diablerets, Switzerland

Title : "Stephane Lupasco and Florentin Smarandache: Conflicting Logics of Contradiction and an Included Middle"

Abstract :  Responding to the failure of classical logic as a foundation for 20th Century science, Stephane Lupasco (1900 - 1988) developed the principle of dynamic opposition and a logic of the included middle. Basarab Nicolescu extended this with the principle of resolution of real contradictions at a higher level of reality. In this logic of existence, every phenomenon is accompanied by its contradictory one, such that no ideal, abstract identity is possible, and the classical values of truth and falsity are replaced by the reciprocally determined values of the actualization and potentialization of the phenomena themselves.  Currently, Florentin Smarandache‚s neutrosophic logic, as does Lupasco‚s, results in abrogation of all three axioms of classical logic. Smarandache defines, in addition to truth and falsity, a third variable  indeterminacy. Both logics involve generalizations of Hegelian dialectics, with different emphasis however, and attempts to apply them in specific examples lead to conflicting interpretations. In this paper, we will analyze the sources of these differences. For example, the logic of Lupasco could be considered as a „physics‰ in the sense of focus on and description of the real, energetic interactions in which both physical and mental phenomena are involved in a ternary relation to which, as Peirce has shown, more complex ones can be reduced. Smarandache‚s approach focuses on the informational aspects of propositions and beliefs, and could be considered a mathematical epistemic logic. Since energy and information must be equivalent, however, work on the foundational aspects of these emerging approaches promises to yield interesting results.    

 

9 - John Sudano, Lockheed Martin, Moorestown, NJ, 08057, USA

Title : Equivalence Between Belief Theories and Naive Bayesian Fusion for Systems with Independent Evidential Data: Part I, The Theory

Abstract : The process of fusing multiple independent sensor measurements, communication link data from other independent systems, and dynamic data base information is essential to support critical decisions in a timely way. Many real systems can be mapped to such a process. The independence of the input evidential data with an equal probable uniform prior probability distribution (i.e. Naive Bayesian fusion) greatly simplifies the mathematical techniques used to properly fuse the evidential data. Equivalence between Belief Fusion and Naive Bayesian is shown for this process. The equivalence comparison is done in probability space. A title of a 2001 colloquium "Data Fusion & Target ID: Dempster-Shafer & Probability Theories Holy War" depicts the state of mind of many researchers. The goal of this paper is to show that large areas from both mathematical camps are equivalent.

 

10 - John Sudano, Lockheed Martin, Moorestown, NJ, 08057, USA

Title : Equivalence Between Belief Theories and Naive Bayesian Fusion for Systems with Independent Evidential Data: Part II, The Example

Abstract : The process of fusing multiple independent sensor measurements, communication link data from other independent systems, and dynamic data base information is essential to support critical decisions in a timely way. Many real systems can be mapped to such a process. The independence of the input evidential data with an equal probable uniform prior probability distribution (i.e. Naive Bayesian fusion) greatly simplifies the mathematical techniques used to properly fuse the evidential data. Equivalence between Belief Fusion and Naive Bayesian is shown for this process. The equivalence comparison is done in probability space. A title of a 2001 colloquium "Data Fusion & Target ID: Dempster-Shafer & Probability Theories Holy War" depicts the state of mind of many researchers. The goal of this paper is to show that large areas from both mathematical camps are equivalent.

 

11 - John Sudano, Lockheed Martin, Moorestown, NJ, 08057, USA

Title : A Generalized Belief Fusion Algorithm

Abstract : For a given body of belief evidential data, a processing objective is to glean the most correct knowledge from such data (but not more). The author introduced a new methodology of combining independent multi-source beliefs in 2002. This generalized belief fusion algorithm depending on the probability proportionally weighting functions used is shown to be equivalent to the Dempster-Shafer (DS) theory of evidence, the Modified Dempster-Shafer (MDS) theory and other fusion methodologies that will converge faster to correct results. A more computationally friendl representation of the generalized belief fusion algorithm is given.

 

12 - Albena Tchamova, CLPP, Bulgarian Academy of Sciences, Sofia, Bulgaria ;

Tzvetan Semerdjiev, Central Laboratory for Parallel Processing, Bulgarian Academy of  Sciences, Bulgaria ;

Jean Dezert, Onera, France.

Title : Tendencies of  Target Behavior Estimation using Dezert-Smarandache Theory

Abstract:  The objective of the paper is to present a new approach for target behavior tendency estimation, graded as “Approaching”, “Stationary”, “Receding”. It is developed on the principles of Dezert-Smarandache theory of plausible and paradoxical reasoning. The case of two independent sensors is considered in the paper. They provide amplitude feature measurements, which serve as an evidence for corresponded decision-making procedures. In some real world situations it is difficult to finalize these procedures, because of discrepancies in measurements interpretation. In these cases the decision-making process leads to conflicts, which cannot be resolved using the well-known methods. The aim of the performed study is to present and to approve the ability of DSmT to finalize successfully the decision-making process and to assure awareness about the tendencies of target behavior in case of discrepancies in measurements interpretation. An example is provided to illustrate the benefit of the proposed approach application in comparison of fuzzy logic approach, and its ability to improve the overall tracking performance.

 

13 – Mohammad Khoshnevisan, School of Accounting & Finance, Griffith University, Australia

Sukanto Bhattacharya, School of Information Technology, Bond University, Australia

Title : Modified Assignment (MASS) Algorithm -  A Semi-heuristic Technique of Optimal Plant Layout Design for Process-focused Systems Using Neutrosophic Statistics

Abstract : In this paper we have proposed a semi-heuristic optimization algorithm for designing optimal plant layouts in process-focused manufacturing/service facilities. Our proposed algorithm marries the well-known CRAFT (Computerized Relative Allocation of Facilities Technique) with the Hungarian assignment algorithm. Being a semi-heuristic search, our algorithm is likely to be more efficient in terms of computer CPU engagement time as it tends to converge on the global optimum faster than the traditional CRAFT algorithm - a pure heuristic. We also present a numerical illustration of our algorithm. We also suggest an extension to the problem under study through the incorporation of principles of neutrosophic statistics.

 

14 - Hongyan Sun, M. Farooq, Dept. of Electrical & Computer Engineering, Royal Military College of Canada, Kingston, ON, Canada, K7K 7B4

Title : Dempster-Shafer Rule on Sensitive Information Sources

Abstract : This paper is concerned with the Dempster-Shafer (D-S) rule on sensitive information sources. The properties of fusion of D-S rule on sensitive information sources are obtained. The robustness of fusion of D-S rule on sensitive information sources is discussed. A number of examples are included to demonstrate the application of the results in the paper.

 

15 - Jean Dezert, Onera, France

Florentin Smarandache, Dept of Mathematics, Univ of New Mexico, USA

Albena Tchamova, CLPP, Bulgarian Acad. of Sciences, Sofia, Bulgaria

Title : "Entropy-Like Measure to Solve the Blackman's Data Association Problem"

Abstract :  This paper presents a new general approach to solve the famous Blackman's

Data Association problem based on an Entropy-Like measure defined from a partial ordering function of hyper-powerset. We will show how this new measure, coherent with the classical definition of entropy, improves the separation power of the decision process.

 

16 - Flavian Vasile, Academy of Economic Science – Faculty of Cybernetics – Computer Science Department, Bucharest, 6 Piata Romana, Romania.

Title: “Processes of Consciousness”.

Abstract: This paper presents consciousness as the sum of describable processes, without limiting it only to verbal understanding. Consciousness is presented as a buffer space of the unconscious, accessed by any mental decision-taking processes. Consciousness is composed of sequential outputs of non-conscious processes that form, as frames in a picture, the impression of our ego continuity. The functional consequences of this point of view are then further discussed.