Yes / This paper presents a self-learning technique for adapting modular automated assembly systems. The technique consists of automatically analysing sensor data and acquiring experience on the changes made on an assembly system to cope with new production requirements or to recover from disruptions. Experience is generalised into operational knowledge that is used to aid engineers in future adaptations by guiding them throughout the process. At each step, applicable changes are presented and ranked based on: (1) similarity between the current context and those in the experience base; (2) estimate of the impact on system performance. The experience model and the self-learning technique reflect the modular structure of the assembly machine and are particularly suitable for plug and produce systems, which are designed to offer high levels of self-organisation and adaptability. Adaptations can be performed and evaluated at different levels: from the smallest pluggable unit to the whole assembly system. Knowledge on individual modules can be reused when modules are plugged into other systems. An experimental evaluation has been conducted on an industrial case study and the results show that, with experience-based learning, adaptations of plug and produce systems can be performed in a shorter time. / European Union [grant number 314762].

Under the evolving environment, a utility company is required to improve the operation and maintenance of its physical assets usually in the forms of an asset management program. This paper proposes an organisational learning model for the utility companies with respect to the asset management activities. CommonKADS is utilised as a tool to capture the knowledge associated with managing the assets from the learning processes of the utility company. A case study of Bangpakong power plant in Thailand is presented. The results show that by applying the proposed methodologies, the learning processes within the utility companies can be categorised and explained by five major learning steps of breakdown, corrective, preventive, predictive, and proactive maintenances.

Linear programming is widely used to solve various complex problems with many variables, subject to multiple constraints. Expert systems are created to provide expertise on complex problems through the application of inference procedures and advanced expert knowledge on facts relevant to the problem. The diet problem is well-known for its contribution to the development of linear programming. Over the years many variations and facets of the diet problem have been solved by means of linear programming techniques and expert systems respectively. In this study the feasibility of combining expert system technology and linear programming techniques to solve a diet problem topical to South Africa, is examined. A computer application is created that incorporates goal programming- and multi-objective linear programming models as the inference engine of an expert system. The program is successfully applied to test cases obtained through knowledge acquisition. The system delivers an eating-plan for an individual that conforms to the nutritional requirements of a healthy diet, includes the personal food preferences of that individual, and includes the food items that result in the lowest total cost. It further allows prioritization of the food preference and least cost factors through the use of weights. Based on the results, recommendations and contributions to the linear programming and expert system fields are presented. / MSc (Computer Science), North-West University, Potchefstroom Campus, 2014

Linear programming is widely used to solve various complex problems with many variables, subject to multiple constraints. Expert systems are created to provide expertise on complex problems through the application of inference procedures and advanced expert knowledge on facts relevant to the problem. The diet problem is well-known for its contribution to the development of linear programming. Over the years many variations and facets of the diet problem have been solved by means of linear programming techniques and expert systems respectively. In this study the feasibility of combining expert system technology and linear programming techniques to solve a diet problem topical to South Africa, is examined. A computer application is created that incorporates goal programming- and multi-objective linear programming models as the inference engine of an expert system. The program is successfully applied to test cases obtained through knowledge acquisition. The system delivers an eating-plan for an individual that conforms to the nutritional requirements of a healthy diet, includes the personal food preferences of that individual, and includes the food items that result in the lowest total cost. It further allows prioritization of the food preference and least cost factors through the use of weights. Based on the results, recommendations and contributions to the linear programming and expert system fields are presented. / MSc (Computer Science), North-West University, Potchefstroom Campus, 2014

This thesis deals with the knowledge engineering for Automated Planning. The concept of state variables has been recently used with benefits for representation of planning problems. In this thesis the same concept is used in a novel formalism for planning domain and problem modeling. A proof-of-concept knowledge modeling tool is developed based on the new formalism. This tool is then used for modeling of example classical planning domain to show its capabilities. The export to standard domain modeling language is also implemented in the tool in order to provide connection to existing planning systems.

O Brasil é um dos maiores produtores mundiais de cana-de-açúcar. As operações agrícolas da cana-de-açúcar representam aproximadamente 67% dos custos de produção de açúcar e álcool e é um setor que faz uso intenso de tecnologia. Um dos problemas mais comuns na área de sistemas de informação agrícolas é a dificuldade de interoperabilidade entre os agentes da cadeia produtiva. A falta de um padrão para representar o conhecimento técnico das operações agrícolas da cana-de-açúcar dificulta o compartilhamento deste conhecimento, além de aumentar o custo de manutenção dos sistemas especialistas. O presente trabalho propõe um modelo conceitual para uma ontologia de tarefa que represente as operações agrícolas da cana-de-açúcar afim de possibilitar a interoperabilidade entre sistemas computacionais e o compartilhamento do conhecimento utilizando formalismo ontológico. Foram estudados os padrões para troca de dados na área agrícola, métodos para modelagem de tarefas e ontologias. O modelo conceitual proposto foi baseado em uma extensão de um perfil UML para representar tarefas existentes, sendo adicionada uma notação para representação de eventos externos a tarefa que podem alterar seu estado, não existente no perfil original. Os resultados foram avaliados em relação a conformidade da extensão proposta com o meta-modelo da linguagem de modelagem conceitual original e da capacidade do modelo em representar as estruturas específicas das operações agrícolas da cana-de-açúcar. O modelo proposto serve de base para implementações via RDF ou OWL garantindo através do formalismo ontológico a interoperabilidade entre os sistemas agrícolas canavieiros. / Brazil is one of the world\'s largest producers of sugar cane. Sugar cane agricultural operations account for approximately 67% of sugar and alcohol production costs and is a sector that makes intense use of technology. One of the most common problems in the agricultural information systems area is the difficulty of interoperability among agents in the production chain. The lack of a standard to represent the technical knowledge of the sugar cane agricultural operations makes it difficult to share this knowledge, and it increases the cost of maintenance of expert systems. The present work proposes a conceptual model for a task ontology that represents the sugar cane agricultural operations in order to enable the interoperability between computational systems and the knowledge sharing by using an ontological formalism. The standards for agricultural data exchange, methods for task modeling and ontologies have been studied. The proposed conceptual model was based on an extension of an existing UML profile to represent tasks, but a notation to represent external tasks that can change its state was added. This notation did not exist in the original profile. The results were evaluated in relation to the conformity of the proposed extension with the meta-model of the original conceptual modeling language and the capacity of the model to represent the specific structures of the sugarcane agricultural operations. The proposed model could be implemented in RDF or OWL and allowing the interoperability between sugar cane software systems.

Construire des terminologies de maladies est un enjeu majeur dans le développement des systèmes d’information épidémiologiques et d’aide à la décision de santé publique qui soient efficients et durables. A partir du contexte du registre français de l'Insuffisance Rénale Terminale, une analyse des besoins de représentation des termes de maladies a été réalisée mettant en évidence le problème aigu et occulté de continuité statistique dans les bases de données et de connaissances. La « continuité terminologique » est proposée comme une réponse au besoin de continuité statistique. Une méthode générative de construction de Ressources Termino-Ontologiques a été conçue et expérimentée. Plutôt que de s’intéresser à l’ensemble des termes qui sont nécessaires pour décrire un domaine, nous nous sommes concentré uniquement sur la modélisation d'un sous ensemble de connaissances élémentaires sur les maladies. Cette méthode générative produit simultanément des termes normalisés (Nomenclature artificielle) et leur représentation sémantique/conceptuelle formelle se basant sur le formalisme des Graphes Conceptuels (GC). Les opérations de généralisation/spécialisation des GC sont utilisées pour déduire l’organisation poly-hiérarchique La continuité terminologique doit être considéré comme étant un critère majeur dans la construction de terminologies de maladies au même titre que la couverture terminologique. Les approches génératives contribuent à améliorer la continuité terminologique, car elles imposent cette contrainte de créer chaque nouveau terme sur des bases formelles avec des propriétés définitoires nécessairement sémantiquement définis dans une ontologie existante. / Expressing terms referring to pathological conceptualization is an important issue toward the development of clinical research and public health decision support systems. From the context of the French Registry of End Stage Renal Disease, requirements for disease terms representation are anlysed highlighting the acute and hidden problem of statistical continuity in disease data and knowledge representation. The underpinned assumption relies on the idea of ensuring terminological continuity through agenerative method of building Ontology Based Terminological systems. Rather than looking at all the terms that are necessary to describe a domain, we focused solely on the modeling of basic and definitional knowledge about disease. A set ontological rules for diseases hierachies were defined. Eperiments have been designed and implemented taking advantage of GC formalism and a logic programming toll called prolog-GC. The results confimed that such method allow performing two major activities that are carried out in the conventional building process of medical terminologies : refinement of disease terms granularity and consistency improvement. Terminological continuity needs to be considered as major criteria in disease terminological building. Generative approaches helps to improve the terminological continuity as imposes to create news terms of the bases of existing ones formal definitions.

O Brasil é um dos maiores produtores mundiais de cana-de-açúcar. As operações agrícolas da cana-de-açúcar representam aproximadamente 67% dos custos de produção de açúcar e álcool e é um setor que faz uso intenso de tecnologia. Um dos problemas mais comuns na área de sistemas de informação agrícolas é a dificuldade de interoperabilidade entre os agentes da cadeia produtiva. A falta de um padrão para representar o conhecimento técnico das operações agrícolas da cana-de-açúcar dificulta o compartilhamento deste conhecimento, além de aumentar o custo de manutenção dos sistemas especialistas. O presente trabalho propõe um modelo conceitual para uma ontologia de tarefa que represente as operações agrícolas da cana-de-açúcar afim de possibilitar a interoperabilidade entre sistemas computacionais e o compartilhamento do conhecimento utilizando formalismo ontológico. Foram estudados os padrões para troca de dados na área agrícola, métodos para modelagem de tarefas e ontologias. O modelo conceitual proposto foi baseado em uma extensão de um perfil UML para representar tarefas existentes, sendo adicionada uma notação para representação de eventos externos a tarefa que podem alterar seu estado, não existente no perfil original. Os resultados foram avaliados em relação a conformidade da extensão proposta com o meta-modelo da linguagem de modelagem conceitual original e da capacidade do modelo em representar as estruturas específicas das operações agrícolas da cana-de-açúcar. O modelo proposto serve de base para implementações via RDF ou OWL garantindo através do formalismo ontológico a interoperabilidade entre os sistemas agrícolas canavieiros. / Brazil is one of the world\'s largest producers of sugar cane. Sugar cane agricultural operations account for approximately 67% of sugar and alcohol production costs and is a sector that makes intense use of technology. One of the most common problems in the agricultural information systems area is the difficulty of interoperability among agents in the production chain. The lack of a standard to represent the technical knowledge of the sugar cane agricultural operations makes it difficult to share this knowledge, and it increases the cost of maintenance of expert systems. The present work proposes a conceptual model for a task ontology that represents the sugar cane agricultural operations in order to enable the interoperability between computational systems and the knowledge sharing by using an ontological formalism. The standards for agricultural data exchange, methods for task modeling and ontologies have been studied. The proposed conceptual model was based on an extension of an existing UML profile to represent tasks, but a notation to represent external tasks that can change its state was added. This notation did not exist in the original profile. The results were evaluated in relation to the conformity of the proposed extension with the meta-model of the original conceptual modeling language and the capacity of the model to represent the specific structures of the sugarcane agricultural operations. The proposed model could be implemented in RDF or OWL and allowing the interoperability between sugar cane software systems.

When selecting life-insurance a person has to rely on subjective decisions of insurance agents or try to analyze all existing life-insurance products for himself. Not only there is a considerable amount of life-insurance products, but also their rules differ significantly. Therefore, a person who wants to choose the best life-insurance for himself must dedicated vast time to this task and have a great understanding of life-insurance in general. The outlined best life-insurance problem is solved by designing the Best Life Insurance Selection System, which is able to assess person’s finance liabilities, determine which type of life-insurance and on what conditions he needs, and where he is able to purchase it. The Most Suitable Life-Insurance Selection System designed in this work was subdivided into the following subsystems: Information about Life-Insurance, Finance Liabilities Assessment, Life-Insurance Type Selection, Conditions of Life-Insurance Selection, and the Best Life-Insurance Selection subsystems. The Life-Insurance Type Selection subsystem design was based on CommonKADS knowledge engineering methodology.

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.