Dissimmetric Fusion of Incomplete Data for Classification of Underwater Objects
Fusion Dissymétrique d'Informations Incomplètes pour la Classification d'Objets Sous-Marins
OPEN ACCESS
To classify objects located in their environment, underwater mobile robots use sequential sensory data (sonar) . These pieces of information are imperfect, that means imprecise, uncertain and incomplete. Incompleteness is defined as the unavailability of some parameters which makes some classification criteria impossible to compute and which delays the decisions. The paper proposes to model data in the framework of possibility theory, and to apply fuzzy calculus to evaluate criteria even in the case of incompleteness. Results are sequentially fused by a dissymmetric combination process . The different dissymmetric fusion rules are reviewed and a specific dissymmetric operator is proposed to solve the incompleteness problem .
Résumé
Afin de classer les objets présents dans leur environnement, les robots mobiles sous-marins peuvent exploiter des informations sensorielles acquises séquentiellement (sonar). Elles sont généralement qualifiées d'imparfaites, c'est-à-dire qu'elles sont imprécises, incertaines et incomplètes. L'incomplétude est vue ici comme l'indisponibilité d'un jeu de paramètres rendant impossible le calcul des critères de classification qui en dépendent, retardant ainsi la prise de décision . L'article propose de modéliser les informations dans le cadre de la théorie des possibilités, et d'appliquer le calcul flou afin d'évaluer des critères même en présence d'incomplétude. Les résultats ainsi obtenus sont fusionnés séquentiellement par un processus de combinaison dissymétrique. Les différentes lois de fusion dissymétrique sont passées en revue et une loi spécifique au traitement de l'incomplétude est proposée.
Incomplete data, possibility theory, revision, updating.
Mots clés
Information incomplète, théorie des possibilités, révision, mise-à-jour.
[1] Grabisch M., Dispot F., «A comparison of some methods of fuzzy classification on real data», Proc. conf IIZUKA'92, lizuka, Japan, pp. 659-662.
[2] Mascarilla L., Zahzah E.H., Desachy J., «Combination of remote sensing and geocoded data for satellite image interpretation based on neural networks», IEEE IGARSS'93 international geoscience and remote sensing symposium, Tokyo, august 1993, pp 725-727.
[3] FaureB., Goncalves D., Propagationacoustiqueen milieuocéanique aléatoire, Quinzième colloque GRETSI, 18-21 sept. 95, pp. 837-840.
[4] Trassoudaine L., Solution multi-sensorielle temps-réel pour la détection d'obstacles surroute,thèsededoctorat soutenue le 16-02-1993 àl'Université Blaise Pascal (DU479), ClermontFerrand.
[5] ReynaudR., Berschandy D., Bouaziz S.,Maurin T., Fusion dedonnéespour leprogramme PROCHIP France :bilanset perspectives, Annalesdu 15 ème colloque GRETSI,Juans lespins,sept. 1995, pp. 953-956.
[6] Bloch I., Maître H., Fusion de données en traitement d'images : modèles d'information et décisisions, Revue «Traitement du signal», vol. 11, n°6, 1994, pp. 435-446.
[7] Smets P., Imperfect Information :Imprecision - Uncertainty, Technical report n°TR/IRIDIA/93-3.
[8] Gross F., Hanrahan D.J., Hood S.T., The application of fuzzy-set theory to the Burnthrough range equation. 1982, Naval Research Laboratory Report 8619.
[9] Marek V.W.,Truszczynski M., Revision specifications by means of programs, Proc. workshop JELIA, 1994, pp. 122-136.
[10] Witteveen C., van derHock W., deNivelleH., Revision of non-monotonie theories, Proc. workshop JELIA, Logics in artificial intelligence, 1994, pp. 137-151.
[11] Aravindan C., DungP.M., Belief dynamics, abduction, and databases, Proc. workshop JELIA, Logicsin artificial intelligence, 1994, pp. 66-85.
[12] Dubois D., Prade H., The logical view of conditioning and its application to possibility and evidence theories, Int. journal of approximate reasoning, 1990, n°4, pp. 23-46.
[13] Dubois D., Prade H., Updating with belief functions, ordinal conditional functions and possibility measures, Uncertainty in artificial intelligence 6, P.P. Bonissone et al. ed., Elsevier science publishers, 1991, pp. 311-329.
[14] Vidoret P., Equation du sonar appliquée à la torpillerie, Rapport n° 0777/CTSN/DLSM/95 du 20/04/95.
[15] O. Strauss, E. Aimé, Filtering data by using three error theories together, 4th European Congress on Intelligent Techniques and Soft Computing, EUFIT'96, Aachen, Germany, pp. 1640-1644.
[16] Gärdenfors P., Knowledge in flux : modeling the dynamics of epistemic states. The MIT Press, Cambridge, MA, 1988 .
[17] Katsuno H., Mendelzon A.O., On the difference between updating a knowledge base and revising it, in Belief revision(P. Gärdenfors ed.), Cambridge University Press, Cambridge, UK, pp. 183-203, 1992.
[18] Dubois D., Prade H., Smets P., Representing partial ignorance, IEEE transactions on Systems Man Cybernetics Part A : systems and humans, 1996,vol.26, n° 3, pp. 361-377.
[19] Dubois D., Prade H., A survey of belief revision and updating rules in various uncertainty models,Int. J. of intelligent Systems. 9, 1994, pp. 61-100.
[20] Dubois D., Prade H. in AbidiM.A.,Gonzalez R.C.,Data fusion in robotics and machine intelligence, Abidi M .A., Gonzalez R.C. editors, Academic Press, 1992, p. 498.
[21] Lewis D.K.,Probabilities of conditionals and conditional probabilities, The philosophical review, 85, pp. 297-315, 1976.
[22] M. Delplanque, A.M. Desodt and D. Jolly, Fuzzy calculus for robotic data processing : problems linked with implementation, 4th European Congress on Intelligent Techniques and Soft Computing, EUFIT'96, Aachen, Germany, pp. 60-64.
[23] ZimmermannH.J.,Fuzzy Sets Theory and its applications, Kluwer Academic Publishers, Boston, second edition, 1991.
[24] Buckley J.J., Solving fuzzy equations, Fuzzy sets and systems 50, 1992, pp . 1-14.
[25] Dubois D., Prade H., Fuzzy sets and systems : theory and applications, Mathematics in science and engineering, vol. 144, Academic Press, 1980, pp. 42-48.
[26] Rifqi M.,Mesuresde similitude etleur agrégation, Rencontres francophones surlalogique floue etsesapplications, 1995, pp. 80-87.
[27] Roecker J.A., A class of near optimal JPDA algorithms, IEEE transactions on Aerospace Electronic Systems, 1994,vol.30, n° 2, pp. 504-510.
[28] Houlès A., Bar-Shalom Y.,Multisensortracking of a maneuvering target in clutter, IEEE transactions on Aerospace Electronic Systems, 1989, vol. 25, n° 2, pp. 176-189.