Das eHealth Service Engineering für seltene Erkrankungen erörtert die systematische Entwicklung von wissensbasierten medizinischen Dienstleistungen (eHealth-Services). Im Fokus der Forschungsarbeit steht das komplexe Problem der Informationsversorgung von Patienten mit degenerativen Nervenerkrankungen (hier: Amyotrophe Lateralsklerose, kurz: ALS). Der unvorhersehbare Krankheitsverlauf, der mit schwerwiegenden Symptomen einhergeht, stellt hohe Anforderungen an die behandelnden Ärzte und beteiligten Akteure, um den betroffenen Patienten eine umfassende Beratung anzubieten. Die Herausforderung ist es, das persönliche Beratungsgespräch IT-basiert zu unterstützen und Patienten eine bedarfsgerechte Informationsbasis für die partizipative Entscheidungsfindung zu bieten. Der exemplarische Anwendungsfall wird anhand umfangreicher Quellenanalysen multidimensional konzeptualisiert. Die extrahierten Konzepte und Relationen werden strukturiert und zu einem semiformalen Gesamtgraphen aggregiert. Dieser Wissensgraph verdeutlicht die fünf systemischen Entwicklungsbereiche Informationen über Patienten (1), Informationen für Patienten (2), Dokumentation bisher getroffener Entscheidungen (3) und dementsprechende Offerten von medizinischen Produkten und Dienstleistungen (4) sowie Management und Koordination der Versorgung (5). Für die Teilbereiche (1-4), welche die Informationsversorgung betreffen, wird eine formale Repräsentation in Form einer RDF-basierten Ontologie (Dispedia) entwickelt und als Linked Data veröffentlicht. Die Nutzung der Dispedia Ontologie wird durch die prototypische Implementierung einer eHealth Anwendung demonstriert. Das Ergebnis ist eine bedarfsgerechte Informationsversorgung für Patienten mit seltenen Erkrankungen.

Despite the influential impact of knowledge transfer insuccess of industrial domains, organizations still struggle tomanage and maintain their experts’ knowledge andexpertise. In this work, I target remote support engineers,and propose a model that supports them in capturing,visualizing, validating and sharing their knowledge in away that is easily replicable in the future as well providingthe means to access the right expert with the requiredexpertise in case of shortage on documented knowledge.Based on field studies conducted, I identified remotesupport engineers’ needs for exchanging their knowledgeand experiences gained during troubleshooting tasks. Thedesign of the model was achieved by combining thetheories of knowledge acquisition and applying HCIvisualization tools. Finally, I conducted a participatoryevaluation with experts from industrial sites to evaluate themodel. The results of the evaluation indicate positivefeedback towards the model presented and potential forimproving the efficiency of troubleshooting procedures. / Trots den inflytelserika effekterna av kunskapsöverföring i framgången för industriella domäner, organisationerfortfarande kämpar för att hantera och underhålla deras experter kunskap och expertis. I detta arbete, jag riktafjärrsupport ingenjörer, och föreslå en modell som stöder dem i fånga, visualisera, validering och dela sin kunskap påett sätt som är lätt replikerbar i framtiden ger möjlighet att få tillgång till rätt expert med erforderlig expertis i frågaom brist på dokumenterad kunskap. Baserat på fältstudier som genomförts, identifierade jag fjärrsupport ingenjörerbehov av utbyte av sina kunskaper och erfarenheter under felsökning uppgifter. Utformningen av modellen uppnåddesgenom att kombinera teorier om kunskapsinhämtning och tillämpa människa-datorinteraktion visualiseringsverktyg.Slutligen genomförde jag en utvärdering deltagande med experter från industriområden att utvärdera modellen.Resultaten av utvärderingen visar positiv feedback till modellen presenteras och potential för att förbättraeffektiviteten i felsökning.

Despite the influential impact of knowledge transfer in success of industrial domains, organizations still struggle to manage and maintain their experts’ knowledge and expertise. In this work, I target remote support engineers, and propose a model that supports them in capturing, visualizing, validating and sharing their knowledge in a way that is easily replicable in the future as well providing the means to access the right expert with the required expertise in case of shortage on documented knowledge. Based on field studies conducted, I identified remote support engineers’ needs for exchanging their knowledge and experiences gained during troubleshooting tasks. The design of the model was achieved by combining the theories of knowledge acquisition and applying HCI visualization tools. Finally, I conducted a participatory evaluation with experts from industrial sites to evaluate the model. The results of the evaluation indicate positive feedback towards the model presented and potential for improving the efficiency of troubleshooting procedures.

Uganda has registered more than a million deaths since the HIV virus was first offi¬cially reported in the country over 3 decades ago. The governments in partnership with different groups have implemented different programmes to address the epidemic. The support from different donors and reduction in prices of treatment resulted in the focus on antiretroviral therapy access to those affected. Presently only a quarter of the approximately 1 million infected by HIV in Uganda are undergoing antiretroviral therapy. The number of patients pause a challenge in monitoring of therapy given the overall resource needs for health care in the country. Furthermore the numbers on antiretroviral therapy are set to increase in addition to the stringent requirements in tracking and monitoring of each individual patient during therapy. This research aimed at developing a framework for adopting knowledge engineering in information systems for monitoring HIV/AIDS patients. An open source approach was adopted due to the resource constrained context of the study to ensure a cost effec¬tive and sustainable solution. The research was motivated by the inconclusive literature on open source dimensional models for data warehouses and data mining for monitor¬ing antiretroviral therapy. The first phase of the research involved a situational analysis of HIV in health care and different health care information systems in the country. An analysis of the strengths, weaknesses and opportunities of the health care system to adopt knowledge bases was done. It proposed a dimensional model for implementing a data warehouse focused on monitoring HIV patients. The second phase involved the development of a knowledge base inform of an open source data warehouse, its simulation and testing. The study involved interdisciplinary collaboration between different stakeholders in the research domain and adopted a participatory action research methodology. This involved identification of the most appropriate technologies to foster this collabora¬tion. Analysis was done of how stakeholders can take ownership of basic HIV health information system architecture as their expertise grow in managing the systems and make changes to reflect even better results out of system functionality. Data mining simulations was done on the data warehouse out of which two machine learning algorithms (regression and classification) were developed and tested using data from the data warehouse. The algorithms were used to predict patient viral load from CD4 count test figures and to classify cases of treatment failure with 83% accu¬racy. The research additionally presents an open source dimensional model for moni¬toring antiretroviral therapy and the status of information systems in health care. An architecture showing the integration of different knowledge engineering components in the study including the data warehouse, the data mining platform and user interac-tion is presented.

Les travaux présentés dans cette thèse s’inscrivent dans une problématique d’amélioration continue appliquée aux produits et aux processus industriels, par la mise en place d’un système de Retour d’Expérience (REx) couplé au système PLM (Product Lifecycle Management) de gestion du cycle de vie du produit. Les développements, menés dans le cadre d’un partenarial industriel, ciblent l’établissement d’une solution de valorisation du patrimoine immatériel de l’entreprise, constitué des expériences et des connaissances détenues par les experts métier. L’objectif visé est d’assurer la pérennisation de cette expertise, la prévention et la limitation des erreurs et l’application de bonnes pratiques dans une démarche générale d’amélioration des produits et des processus. La solution est portée par la mise en place d’un système REx appliqué aux connaissances tacites et explicites impliquées dans les activités techniques de l'entreprise et visant à capitaliser au fur et à mesure les informations métier, porteuses de sens. L’intégration du REx au système PLM permet de lever une part des difficultés d’appropriation par les experts métier, utilisateurs du système REx. L’ancrage de ce REx aux méthodes de résolution de problèmes (PSM, Problem Solving Methods) induit une instrumentation tout à fait performante pour l’acquisition des connaissances tacites issues d’événements négatifs. L’extension aux processus d’évolution des Normes Techniques qui formalisent les règles métier de l’entreprise permet leur évolution vers des connaissances explicites. Le caractère non intrusif du système REx dans son utilisation est assuré par un couplage étroit au processus de Gestion des Modifications du PLM, la capitalisation des informations étant naturellement induite par la démarche mise en œuvre dans ce processus. Au final, le système REx proposé et instrumenté dans l’outil PLM permet, en différentes étapes, de capitaliser, de traiter puis d’exploiter dans des formes performantes le patrimoine immatériel mis en exergue au cours des expériences de résolution de problèmes produit ou processus. / The work presented in this thesis considers continuous improvement issues which are applied to industrial products and processes through the implementation of a Lesson Learned System (LLS) coupled with the Company's Product Lifecycle Management (PLM) system. As an industrial partnership, these developments aim to increase the value of the intangible assets of the business including the business agent’s experiences and knowledge. In order to ensure the sustainability of expertise, to prevent errors and to encourage the application of good practices, all within a general approach of product improvement. The solution relies on the implementation of the LLS process which is applied to tacit and explicit knowledge related to the technical activities of the company. The integration of the LLS and PLM Systems removes some of the difficulties of ownership of business agents. The implementation of LLS and Problem Solving Methods (PSM) infers an efficient instrumentation for the acquisition of tacit knowledge. The extension of the evolution processes of technical documents that formalise the techincal business rules allows its evolution towards explicit knowledge. Using non-intrusive LLS is provided by close coupling with the process of Change Management (CM) where information capitalisation is naturally led by the approach implemented in this processes. Finally, the proposed and instrumented LLS in the PLM tool allows to efficiently capitalise, process, and exploit the intangible capital of the company (information and knowledge) highlighted during the modification experiments of product data.

Este trabalho apresenta um modelo para sistemas multiagentes constituídos por agentes de informação destinados a auxiliar comunidades humanas que partilham conhecimento. Tais agentes são cientes do entorno social dos usuários, pois possuem representações do conhecimento dos mesmos e também das redes sociais que os circundam, organizadas subjetivamente. Conceitos pertencentes às suas ontologias são estendidos com informação organizacional para representar de forma explícita as situações nas quais foram aprendidos e utilizados. Discute-se como tais agentes autônomos podem raciocinar sobre o uso e a privacidade de conceitos em termos de construções organizacionais, possibilitando raciocinar sobre papéis sociais em comunidades abertas na Internet. / This work presents a model for multi-agent systems for information agents supporting information-sharing communities. Such agents are socially aware in the sense that they have representations of the users' knowledge and also of their social networks, which are subjectively organized. Concepts in their ontologies are extended with organizational information to record explicitly the situations in which they were learned and used. It is discussed how such autonomous agents are allowed to reason about concept usage and privacy in terms of organizational constructs, paving the way to reason about social roles in open Internet communities.

L’opérationnalisation des terminologies à des fins de traitement de l’information requière une représentation computationnelle du système conceptuel. La théorie du concept sur laquelle se fonde la Terminologie ISO ne permet pas aujourd’hui une telle représentation informatique [Roche TKE 2012]. Même si les normes ISO sur la Terminologie n’ont pas pour objectif l’opérationnalisation de terminologies mais la communication entre humains, elles doivent pouvoir – elles le précisent – servir à la modélisation des informations et des données [ISO 704 :2009]. Les résultats de disciplines telles que l’ingénierie des connaissances ont permis de mettre en évidence la nécessité de disposer d’une théorie du concept qui puisse donner lieu à une représentation informatique. Dans ce cadre, les ontologies, issues de l’ingénierie des connaissances, constituent une des perspectives les plus intéressantes pour la modélisation du système conceptuel d’une terminologie [Roche 2015, Handbook of Terminology].Mots clés en français : Terminologie, ontologie, ingénierie des connaissances ISO-1087, ISO-704, ISO-860 / The operationalization of terminologies for information processing purposes requires a computational representation of the conceptual system. The theory of concept of the theory currently defined in ISO Terminology does not allow a computer representation [Roche TKE 2012]. Although ISO standards on Terminology does not aim to operationalize terminologies but communication between humans and used to model information and data [ISO 704: 2009]. The results of disciplines such as engineering knowledge helped to highlight the need for a theory of concept that could lead to a computer representation. In this context, ontologies, from knowledge engineering, is one of the most interesting perspectives to model the conceptual system of Terminology [Roche, 2015, Handbook of Terminology]

L’objectif de la thèse est d’abord d’analyser les rapports croisés existant entre modélisation d’entreprise et gestion des connaissances (modélisation comme explicitation des connaissances et connaissances comme une vue en modélisation) et ensuite de déboucher sur un ensemble méthodologique unifiant les deux approches. L’apport de nos travaux est décomposé comme suit : 1.Une étude comparative conceptuelle et théorique de ces méthodes. 2.Une chaîne de valeur ajoutée de la création des connaissances nommée VCKC. 3.Un cadre générique pour la mise en place de gestion des connaissances en entreprise nommé I2CE. 4.Un cadre d’ingénierie d’entreprise basé sur la connaissance nommé KBEE. / The main objective of this thesis is to analyze the relation between enterprise modeling and knowledge management (modeling as a way of knowledge externalization and knowledge as a view in modeling) and next to propose a global framework which will be able to unify two approaches. The contribution of this research is divided into four major axes: 1. To propose a conceptual and theoretic comparison study of two approaches. 2. To propose a value chain of knowledge creation in a value added way to unify the basic terminology in the context of knowledge in the organizations. This proposition named Value Chain of Knowledge Creation (VCKC). 3. To propose a reference model as the theoretic foundation of implementing knowledge management approach in the organizations named Intent-Content-Context-Evolution (I2CE). 4. To propose a knowledge engineering framework in the enterprises named Knowledge Based Enterprise Engineering (KBEE).

Este trabalho apresenta um modelo para sistemas multiagentes constituídos por agentes de informação destinados a auxiliar comunidades humanas que partilham conhecimento. Tais agentes são cientes do entorno social dos usuários, pois possuem representações do conhecimento dos mesmos e também das redes sociais que os circundam, organizadas subjetivamente. Conceitos pertencentes às suas ontologias são estendidos com informação organizacional para representar de forma explícita as situações nas quais foram aprendidos e utilizados. Discute-se como tais agentes autônomos podem raciocinar sobre o uso e a privacidade de conceitos em termos de construções organizacionais, possibilitando raciocinar sobre papéis sociais em comunidades abertas na Internet. / This work presents a model for multi-agent systems for information agents supporting information-sharing communities. Such agents are socially aware in the sense that they have representations of the users' knowledge and also of their social networks, which are subjectively organized. Concepts in their ontologies are extended with organizational information to record explicitly the situations in which they were learned and used. It is discussed how such autonomous agents are allowed to reason about concept usage and privacy in terms of organizational constructs, paving the way to reason about social roles in open Internet communities.

近年來由於國內經濟之持續成長，證券市場的交易也日益活絡，因此藉著在證券市場發行證券的方式來籌措資金，以便從事大規模經營的公司家數也越來越多。隨著股票上市申請案件的增加，證交所上市部負責股票上市案件審查人員的升遷、調職及離職，精通審查程序的證券專家便相對的稀少。為加速申請案件之審查、保留證券專家的工作經驗與知識、及訓練新進人員，發展專家系統是值得一試的措施。 在人工智慧領域中，專家系統技術已成為由實驗理論進入商品化的一種技術，為人工智慧技術中較為成熟的一環。國外已經有不少成功的應用專家系統實例，國內各單位目前對於人工智慧的研究，也多半集中在專家系統的開發上。然而，擷取領域專家的知識及經驗，並由這些知識及經驗架構而成的知識庫，是專家系統的主體。因此，本研究目的有二：一、收集相關資料，整理出在股票上市案件審查程序上的知識與經驗，並以恰當的知識表示法轉換成電腦程式。二、利用GoldWorks Ⅲ在個人電腦上設計一個專家系統的雛型系。 本研究已經運用專家系統建構工具GoldWorks Ⅲ建構完成輔助股票上市案件審查的專家系統雛型，本雛型系統包含了兩大子系統：(1)分類子系統，(2)審查準則子系統。經由本研究之探討及系統實際設計，可得以下結論：ぇ經系統評估的結果發現，將專家系統之觀念與技術應用在輔助股票上市案件審查過程上是可行的；え將股票上市案件審查所需的專業知識及經驗予以形式化後，並以規則基礎知識表示法設計成知識庫，保存在電腦系統中。因此，如果審查人員都在系統的引導之下作出合理的判斷，當能提高股票上市案件審查判斷結果的一致性。(3)透過本研究專家系統雛型之執行及解釋，使得經過適當訓練的非專家，亦能享受專家的知識及經驗，亦可藉以輔助股票上市案件審查專業人才的培訓。(4)使用專家系統建構工具設計系統雛 型，能快速的在短期間內建立一個雛型系統，應該是未來應用的主流。