Les tsunamis sont l’une des catastrophes naturelles les plus dangereuses. Ils peuvent tuer des milliers de personnes (par exemple : le tsunami de l’Océan Indien en 2004 et le tsunami Tohoku Japan en 2011). L’évacuation est une solution efficace pour sauver les gens dans ces cas des désastres. Avant que le tsunami n’arrive, il faut que les gens atteignent des bâtiments en hauteur ou des zones éloignées de la mer. Notre objectif est d’aider les personnes à se diriger vers les bons endroits durant l'évacuation, en plaçant de façon judicieuse des panneaux signalétiques. Pour le placement optimal de ces panneaux est formulé dans cette thèse comme un problème d’optimisation. Dans un premier temps, nous utiliserons un simulateur multi-agents pour estimer le nombre de survivants en cas de tsunamis. Ce simulateur intégre un modèle de comportement des individus, en fonction des panneaux signalétiques placés dans la ville. L’optimisation basée sur ce simulateur étant inefficace, nous utiliserons des techniques d’apprentissage pour estimer plus rapidement le nombre de survivants dans différents cas. / In recent years, whenever we talked about tsunami, we mentioned the terrible destruction and huge casualties (the tsunami from Indian Ocean in 2004 and the tsunami in Tohoku Japan 2011). The evacuation is the most effective solution to save people in this kind of disaster. Before a tsunami arrival, people should go to the high buildings (called vertical shelters) or high ground areas or zones far from the sea (called horizontal shelters). However, there are always the part of evacuees (e.g. the tourist) who lack information of the city map, we then focus on the solution to guide people in evacuation.This thesis presents the approach of Efficient Optimization in a Multi-Agent Decision Support System : Application to Sign Placement for Tsunami Evacuation. More precisely, we study the approach to place signs and also evacuation maps in the city (at certain crossroads or junctions) to have as many people (call survivors) as possible reach the shelters before tsunami arrival. Our multiagent simulator allows us to estimate the number of survivors after a tsunami. Using various optimization techniques, we then place signs in the city in order to maximize the estimated number of survivors

<p>The study aimed to investigate the acute medical chain consisting of SOS operator, ambulance nurse, emergency nurse and emergency physician with regard to the assessment and prioritization of the victim.</p><p>The design of this journal study is retrospective with descriptive approach. Data were collected from all ambulance missions carried out in Uppsala county 2009-01-01 between the hours 00:00 to 12:00. Sample period was chosen because the prerequisite for high frequency on the ambulance mission was supposed to be good. In order to be able to systematize the compilation of data a protocol were prepared and used. Applicable data were collected from three databases SOS Alarms, ambulance operations, and the University Hospital in Uppsala. The study was divided into three stages and record documents usefulness was assessed individually based on inclusion criteria's. During the measurement period the SOS operator assessed need of an ambulance at 62 occasions in Uppsala County. Of these 62 ambulance missions there were 18 that could be followed during the whole acute medical chain.</p><p>The results showed that the participants of the acute medical chain most of the time did the same assessment of the victim main problem/symptom and thus the criterion. Without considering the priority it appeared that the criteria were the same in 83% of all 18 included ambulance missions. SOS operator assessed ambulance mission as a priority one in 39% (7/18), and the ambulance nurse judged that priority one on the way to the hospital was justified in 17% (3/18). Of the 18 victims who were transported by ambulance to the emergency department at the University Hospital in Uppsala 72% (13/18) went home the same day.</p> / <p>Studiens syfte var att undersöka den akutmedicinska vårdkedjan bestående av SOS operatör, ambulanssjuksköterska, akutsjuksköterska och akutläkare med avseende på bedömning och prioritering av drabbad.</p><p>Designen på denna journalstudie är retrospektiv med deskriptiv ansats. Data insamlades från samtliga ambulansuppdrag som genomfördes i Uppsala län 2009-01-01 mellan klockan 00:00 - 12:00. Urvalsperioden valdes därför att förutsättningen för hög frekvens på ambulansuppdrag förmodades vara goda. För att systematisera sammanställningen av data utarbetades och användes ett protokoll. Tillämpbara uppgifter inhämtades från tre databaser SOS Alarms, ambulansverksamhetens och Akademiska sjukhusets. Studien delades upp i tre steg och journalhandlingarnas användbarhet bedömdes var för sig utifrån inklusionskriterier. Under mätperioden bedömde SOS operatören behov av ambulans vid 62 tillfällen i Uppsala län. Av dessa 62 ambulansuppdrag gick 18 att följa under hela vårdkedjan.</p><p>Resultatet visade att aktörerna i akutmedicinska vårdkedjan för det mesta gjorde samma bedömning av den drabbades huvudproblem/symtom och därmed kriteriet. Utan hänsyn taget till prioritet så visade det sig att kriterierna övrrensstämde vid 83% av alla 18 inkluderade ambulansuppdrag. SOS operatören bedömde ambulansuppdraget som prioritet ett i 39% (7/18) och ambulanssjuksköterskan bedömde att prioritet ett på väg till sjukhus var motiverat i 17% (3/18). Av de18 drabbade som transporterats med ambulans till akutmottagningen på Akademiska sjukhuset fick 72% (13/18) åka hem samma dag.</p>

Modifications of footers in title page, page-2 and page-3.

The study aimed to investigate the acute medical chain consisting of SOS operator, ambulance nurse, emergency nurse and emergency physician with regard to the assessment and prioritization of the victim. The design of this journal study is retrospective with descriptive approach. Data were collected from all ambulance missions carried out in Uppsala county 2009-01-01 between the hours 00:00 to 12:00. Sample period was chosen because the prerequisite for high frequency on the ambulance mission was supposed to be good. In order to be able to systematize the compilation of data a protocol were prepared and used. Applicable data were collected from three databases SOS Alarms, ambulance operations, and the University Hospital in Uppsala. The study was divided into three stages and record documents usefulness was assessed individually based on inclusion criteria's. During the measurement period the SOS operator assessed need of an ambulance at 62 occasions in Uppsala County. Of these 62 ambulance missions there were 18 that could be followed during the whole acute medical chain. The results showed that the participants of the acute medical chain most of the time did the same assessment of the victim main problem/symptom and thus the criterion. Without considering the priority it appeared that the criteria were the same in 83% of all 18 included ambulance missions. SOS operator assessed ambulance mission as a priority one in 39% (7/18), and the ambulance nurse judged that priority one on the way to the hospital was justified in 17% (3/18). Of the 18 victims who were transported by ambulance to the emergency department at the University Hospital in Uppsala 72% (13/18) went home the same day. / Studiens syfte var att undersöka den akutmedicinska vårdkedjan bestående av SOS operatör, ambulanssjuksköterska, akutsjuksköterska och akutläkare med avseende på bedömning och prioritering av drabbad. Designen på denna journalstudie är retrospektiv med deskriptiv ansats. Data insamlades från samtliga ambulansuppdrag som genomfördes i Uppsala län 2009-01-01 mellan klockan 00:00 - 12:00. Urvalsperioden valdes därför att förutsättningen för hög frekvens på ambulansuppdrag förmodades vara goda. För att systematisera sammanställningen av data utarbetades och användes ett protokoll. Tillämpbara uppgifter inhämtades från tre databaser SOS Alarms, ambulansverksamhetens och Akademiska sjukhusets. Studien delades upp i tre steg och journalhandlingarnas användbarhet bedömdes var för sig utifrån inklusionskriterier. Under mätperioden bedömde SOS operatören behov av ambulans vid 62 tillfällen i Uppsala län. Av dessa 62 ambulansuppdrag gick 18 att följa under hela vårdkedjan. Resultatet visade att aktörerna i akutmedicinska vårdkedjan för det mesta gjorde samma bedömning av den drabbades huvudproblem/symtom och därmed kriteriet. Utan hänsyn taget till prioritet så visade det sig att kriterierna övrrensstämde vid 83% av alla 18 inkluderade ambulansuppdrag. SOS operatören bedömde ambulansuppdraget som prioritet ett i 39% (7/18) och ambulanssjuksköterskan bedömde att prioritet ett på väg till sjukhus var motiverat i 17% (3/18). Av de18 drabbade som transporterats med ambulans till akutmottagningen på Akademiska sjukhuset fick 72% (13/18) åka hem samma dag.

Telefonrådgivning är en vanlig vårdform. I en alltmer medicinskt och tekniskt utvecklad ögonsjukvård efterfrågas ögonsjuksköterskornas omvårdnadskompetens av både patienter, anhöriga och kollegor inom andra delar av sjukvården. Syftet med studien var att undersöka ögonsjuksköterskors upplevelser av att använda sin specifika omvårdnadskunskap vid telefonrådgivning inom ögonsjukvård. Studien genomfördes med en kvalitativ metod och data samlades in genom semistrukturerade intervjuer. Materialet analyserades med kvalitativ innehållsanalys. Resultatet visade att ögonsjuksköterskorna upplevde arbetet som utvecklande och utmanande. De såg sig själva som en lots i vården med en stor rådgivande funktion relaterat till sin specifika kunskap. De beskrev också en del svårigheter med att triagera via telefon. De önskade bättre bedömningsunderlag men var dock trygga med sina bedömningar och någon rädsla för anmälningar till tillsynsmyndighet framkom inte. De uttryckte även ett behov av utbildning inom samtalsmetodik. Ögonsköterskorna saknade tid för kollegiala reflektioner för att utveckla sin professionella hållning i arbetet med telefonrådgivningen / Telephone counseling is a common form of care. In an increasing medical and technical development in ophthalmological care is ophthalmic nurses skills demanded by both patients, relatives and colleagues in other areas of health care. The purpose of this study was to examine the eye nurses experiences of telephone counseling in ophthalmology. The study was conducted using a qualitative approach and data were collected through semi-structured interview. The material was analyzed using qualitative content analysis. The results showed that eye nurses were confident and proud of their professional role. They experienced the work as fun, stimulating and challenging. They saw themselves as a pilot in the care of a large advisory role related to their specific knowledge. They also described some difficulties in triagera by phone. They wanted better assessment documentation but was confident in their assessments and any fear of notifications to the regulator were not revealed. They also expressed a need for training in counseling skills. Ophthalmic nurses lacked the time for collegial reflection to develop their professional attitude in the work of telephone counseling.

Les habitats intelligents, résultants de la convergence de la domotique, de l'informatique ubiquitaire et de l'intelligence artificielle, assistent leurs habitants dans les situations du quotidien pour améliorer leur qualité de vie.En permettant aux personnes dépendantes et âgées de rester à domicile plus longtemps, ces habitats permettent de fournir une première réponse à des problèmes de société comme la dépendance due au vieillissement de la population.En nous plaçant dans un habitat contrôlé par la voix, l'habitat doit répondre aux requêtes d’un utilisateur concernant un ensemble d’actions pouvant être automatisées (contrôle des lumières, des volets, des dispositifs multimédia, etc.).Pour atteindre cet objectif, le système de contrôle de l'habitat a besoin de prendre en compte le contexte dans lequel un ordre est donné mais également de connaitre les habitudes et préférences de l’utilisateur.Pour cela, le système doit pouvoir agréger les informations issues du réseau de capteurs domotiques hétérogènes et prendre en compte le comportement (variable) de l'utilisateur.La mise au point de systèmes de contrôle intelligent d'un habitat est particulièrement ardue du fait de la grande variabilité concernant aussi bien la topologie des habitats que les habitudes des utilisateurs.Par ailleurs, l'ensemble des informations contextuelles doivent être représentées dans un référentiel commun dans un objectif de raisonnement et de prise de décision.Pour répondre à ces problématiques, nous proposons de développer un système qui d'une part modifie continuellement son modèle de manière à s'adapter à l'utilisateur, et qui d'autre part utilise directement les données issues des capteurs à travers une représentation graphique. L'intérêt et l'originalité de cette méthode sont de ne pas nécessiter d'inférence pour déterminer le contexte.Notre système repose ainsi sur une méthode d'apprentissage par renforcement profond qui couple un réseau de neurones profond du type convolutif permettant l'extraction de données contextuelles, avec un mécanisme d'apprentissage par renforcement pour la prise de décision.Ce mémoire présente alors deux systèmes, un premier reposant uniquement sur l'apprentissage par renforcement et montrant les limites de cette approche sur des environnements réels pouvant comporter plusieurs milliers d'états possibles.L'introduction de l'apprentissage profond a permis la mise au point du second système, ARCADES, dont les bonnes performances montrent la pertinence d'une telle approche, tout en ouvrant de nombreuses voies d'améliorations. / Smart-homes, resulting of the merger of home-automation, ubiquitous computing and artificial intelligence, support inhabitants in their activity of daily living to improve their quality of life.Allowing dependent and aged people to live at home longer, these homes provide a first answer to society problems as the dependency tied to the aging population.In voice controlled home, the home has to answer to user's requests covering a range of automated actions (lights, blinds, multimedia control, etc.).To achieve this, the control system of the home need to be aware of the context in which a request has been done, but also to know user habits and preferences.Thus, the system must be able to aggregate information from a heterogeneous home-automation sensors network and take the (variable) user behavior into account.The development of smart home control systems is hard due to the huge variability regarding the home topology and the user habits.Furthermore, the whole set of contextual information need to be represented in a common space in order to be able to reason about them and make decisions.To address these problems, we propose to develop a system which updates continuously its model to adapt itself to the user and which uses raw data from the sensors through a graphical representation.This new method is particularly interesting because it does not require any prior inference step to extract the context.Thus, our system uses deep reinforcement learning; a convolutional neural network allowing to extract contextual information and reinforcement learning used for decision-making.Then, this memoir presents two systems, a first one only based on reinforcement learning showing limits of this approach against real environment with thousands of possible states.Introduction of deep learning allowed to develop the second one, ARCADES, which gives good performances proving that this approach is relevant and opening many ways to improve it.