Remerciez-le!

Remerciez @Admin pour avoir partagé cet document gratuitement, de la manière la plus simple, en partageant sur les réseaux sociaux.

See discussions, stats, and author profiles for this publication at: https://ww

See discussions, stats, and author profiles for this publication at: https://www.researchgate.net/publication/329659317 Thesis Manuscript Thesis · December 2017 DOI: 10.13140/RG.2.2.15077.86246 CITATIONS 0 READS 521 1 author: Some of the authors of this publication are also working on these related projects: Multisensory Data Fusion with Detection and Exclusion of Default Based on Kullback-Leibler Divergence View project Personal Localization System View project Mhd Daher Lebanese University - Faculty of Technology 9 PUBLICATIONS 41 CITATIONS SEE PROFILE All content following this page was uploaded by Mhd Daher on 14 December 2018. The user has requested enhancement of the downloaded file. Numéro d’ordre : 42525 Université de Lille École doctorale Sciences Pour l’Ingénieur Unité de recherche CRIStAL Thèse présentée par Mohamad Daher Soutenue le 13 Décembre 2017 En vue de l’obtention du grade de docteur de l’Université de Lille Discipline Informatique, automatique Fusion multi-capteurs tolérante aux fautes pour un niveau d'intégrité élevé du suivi de la personne Composition du jury Rapporteurs Véronique Berge-Cherfaoui Professeur à l’Université de Technologie de Compiègne Ghaleb Hoblos Professeur à l’ESIGELEC Examinateurs Claude Delpha MCF HDR Université Paris Sud Ahmad Diab MCF à l’Université Libanaise Mohamad Khalil Professeur à l’Université Libanaise Christine Perret-Guillaume PU PH CHRU Nancy Directeurs de thèse Maan El Badaoui El Najjar Professeur à l’Université de Lille Francois Charpillet Directeur de recherche INRIA, Nancy Ph.D. Dissertation Towards high integrity personal tracking using fault tolerant multi-Sensor data fusion ii Ph.D. Dissertation Towards high integrity personal tracking using fault tolerant multi-Sensor data fusion iii Mots clés: système de localisation des personnes, reconnaissance des activités de la vie quotidienne, détection des chutes des personnes âgées, extraction des paramètres, sélection des paramètres, détection des signaux, fusion de données, filtre informationnel, détection et exclusion des défauts, divergence de Kullback-Leibler. Keywords: personal localization system, activities daily living recognition, elderly fall detection, features extraction, features selection, signal detection, data fusion, information filter, fault detection and exclusion, Kullback-Leibler divergence. Ph.D. Dissertation Towards high integrity personal tracking using fault tolerant multi-Sensor data fusion iv Preface This thesis is submitted to the Lille University - Science and Technology in partial fulfilment of the requirements for the degree of Doctor of Philosophy. The work has been conducted at CRIStAL (Centre de Recherche en Informatique, Signal et Automatique de Lille) and has been achieved in partnership with the Institut National de Recherche en Informatique et en Automatique (INRIA) in Nancy - Grand Est and the Azm Center for Research in Biotechnology and its Applications. . Ph.D. Dissertation Towards high integrity personal tracking using fault tolerant multi-Sensor data fusion v Abstract About one third of home-dwelling older people suffer a fall each year. The most painful falls occur when the person is alone and unable to get up, resulting in huge number of elders which are associated with institutionalization and high morbidity-mortality rate. The PAL (Personally Assisted Living) system appears to be one of the solutions of this problem. This ambient intelligence system allows elderly people to live in an intelligent and pro-active environment. It is charged with the supervision and control of the entrusted space, monitoring events and detecting falls, recognizing human activities through network sensors, and finally providing support through robotic actuators. Such services have the potential of increasing autonomy of elders while minimizing the risks of living alone. This thesis describes the ongoing work of in-home elder tracking, activities daily living recognition, and automatic fall detection system using a set of non-intrusive sensors that grants privacy and comfort to the elders. In addition, a fault-tolerant fusion method is proposed using a purely informational formalism: information filter on the one hand, and information theory tools on the other hand. Residues based on the Kullback-Leibler divergence are used. Using an appropriate thresholding, these residues lead to the detection and the exclusion of sensors faults. The proposed algorithms were validated with many different scenarios containing the different activities: walking, sitting, standing, lying down, and falling. The performances of the developed methods showed a sensitivity of more than 94% for the fall detection of persons and more than 92% for the discrimination between the different ADLs (Activities of the daily life). Résumé Environ un tiers des personnes âgées vivant à domicile souffrent d'une chute chaque année. Les chutes les plus graves se produisent lorsque la personne est seule et incapable de se lever, ce qui entraîne un grand nombre de personnes âgées admis au service de gériatrique et un taux de mortalité malheureusement élevé. Le système PAL (Personally Assisted Living) apparaît comme une des solutions à ce problème. Ce système d’intelligence ambiante permet aux personnes âgées de vivre dans un environnement intelligent et pro-actif. Il permet la supervision et le contrôle de l'environnement d’évolution, la surveillance des événements et la détection des chutes, tout en reconnaissant les activités humaines grâce à des réseaux de capteurs et en fournissant un support grâce à des actionneurs robotisés. Ces services ont le potentiel d'accroître l'autonomie des personnes âgées tout en minimisant les risques du maintien à domicile. Le travail de cette thèse s’inscrit dans le cadre du suivi des personnes âgées avec un maintien à domicile, la reconnaissance quotidienne des activités et le système automatique de détection des chutes à l'aide d'un ensemble de capteurs non intrusifs qui accorde l'intimité et le confort aux personnes âgées. En outre, une méthode de fusion tolérante aux fautes est proposée en utilisant un formalisme purement informationnel : filtre informationnel d’une part, et outils de la théorie de l’information d’autre part. Des résidus basés sur la divergence de Kullback-Leibler sont utilisés. Via un seuillage adéquat, ces résidus conduisent à la détection et à l’exclusion des défauts capteurs. Les algorithmes proposés ont été validés avec plusieurs scénarii différents contenant les différentes activités : marcher, s’asseoir, debout, se coucher et tomber. Les performances des méthodes Ph.D. Dissertation Towards high integrity personal tracking using fault tolerant multi-Sensor data fusion vi développées ont montré une sensibilité supérieure à 94% pour la détection de chutes de personnes et plus de 92% pour la discrimination entre les différentes ADL (Activités de la vie quotidienne). CRIStAL Centre de Recherche en Informatique, Signal et Automatique de Lille – CNRS UMR 9189 – Avenue Paul Langevin – Villeneuve d’Ascq – 59650 Ph.D. Dissertation Towards high integrity personal tracking using fault tolerant multi-Sensor data fusion vii Acknowledgements First and above all, I praise God, the almighty for providing me this opportunity and granting me the capability to proceed successfully. This thesis appears in its current form due to the assistance and guidance of several people. I would therefore like to offer my sincere thanks to all of them. First, I wish to warmly thank my Research Directors: Professor Maan El-Badaoui El-Najjar and Mr. François Charpillet for having offered me the possibility to pursue this doctorate under their guidance. I would also like to thank the Professor Mohamad Khalil; director of the Azm Center for Research in Biotechnology and its Applications; for hosting me in the laboratory. I would like to express my deepest sense of gratitude to Mr. Ahmad Diab, who offered his continuous advice and encouragement throughout the course of this thesis. I am very grateful to the official referees of this thesis: Pr. Claude Delpha for having presided the jury; Mrs. Véronique Cherfaoui and Mr. Ghaleb Hoblos for reviewing my thesis; Mrs. Christine Perret-Guillaume for her valuable comments. Mr. Abdallah Dib and Mr. Thomas Moinel, thanks for your excellent technical assistance in the INRIA-Nancy laboratory, particularly for data acquisition technique, and your kindly answers to my general questions. I am grateful to my CRIStAL laboratory colleague Ms. Joelle Al Hage for her continuous support. I would also like to thank our assistant Mrs. Véronique Constant, who helped organizing all the missions to conferences and project meetings. I cannot finish without thanking my family, I warmly thank and appreciate my beloved parents for their love and positive support on my life. Ph.D. Dissertation Towards high integrity personal tracking using fault tolerant multi-Sensor data fusion viii Finally, I want to express my gratitude and deepest appreciation to my lovely sweet wife “Reem”, thank you for your love, your support, and your encouragement given to me in life and especially during the progression of this thesis. My Daughters and my Son: Lynn, Lea, Ahmad and Celia, thank you my good for your presents. Villeneuve d’Ascq, on December 13, 2017 Mohamad Daher Ph.D. Dissertation Towards high integrity personal tracking using fault tolerant multi-Sensor data fusion ix Table of contents Abstract .......................................................................................................................................... v Acknowledgements ..................................................................................................................... vii Table of contents .......................................................................................................................... ix Acronyms .................................................................................................................................... xiv Chapter I - Introduction ............................................................................................................... 1 I.1 Ambient Intelligence (AmI) ................................................................................................... 1 I.2 AmI System Flow .................................................................................................................. 1 I.3 Aging population ................................................................................................................... 2 I.4 Elderly falls in aging population ............................................................................................ 4 I.5 Causes of elderly falls ............................................................................................................ 5 I.6 Consequences of elderly falls ................................................................................................ 5 I.7 Advances in AmI as a driver for seniors independent living ................................................. 7 I.8 Existing AmI projects ............................................................................................................ 7 I.9 Background of the thesis ........................................................................................................ 9 I.10 Objectives and structure of the thesis .................................................................................. 9 I.12 Key contributions of this thesis .......................................................................................... 11 uploads/Science et Technologie/ thesis-manuscript.pdf