A tecnologia de agentes surge como uma solução que fornece flexibilidade e robustez para lidar com domínios dinâmicos e complexos. Tal flexibilidade pode ser alcançada através da adoção de abordagens já existentes baseadas em agentes, como a arquitetura BDI, que provê agentes com características mentais de crenças, desejos e intenções. Essa arquitetura é altamente personalizável, deixando lacunas a serem preenchidas de acordo com aplicações específicas. Uma dessas lacunas é o algoritmo de seleção de planos, responsável por selecionar um plano para ser executado pelo agente buscando atingir um objetivo, e tendo grande influência no desempenho geral do agente. Grande parte das abordagens existentes requerem considerável esforço para personalização e ajuste a fim de serem utilizadas em aplicações específicas. Nessa dissertação, propomos uma abordagem para seleção de planos apta a aprender quais planos possivelmente terão os melhores resultados, baseando-se no contexto atual e nas preferências do agente. Nossa abordagem é composta por um meta-modelo, que deve ser instanciado a fim de especificar metadados de planos, e uma técnica que usa tais metadados para aprender e predizer resultados da execução destes planos. Avaliamos nossa abordagem experimentalmente e os resultados indicam que ela é efetiva. Adicionalmente, fornecemos uma ferramenta para apoiar o processo de desenvolvimento de agentes de software baseados em nosso trabalho. Essa ferramenta permite que desenvolvedores modelem e gerem código-fonte para agentes BDI com capacidades de aprendizado. Um estudo com usuários foi realizado para avaliar os benefícios de um método de desenvolvimento baseado em agentes BDI auxiliado por ferramenta. Evidências sugerem que nossa ferramenta pode auxiliar desenvolvedores que não sejam especialistas ou que não estejam familiarizados com a tecnologia de agentes. / Agent technology arises as a solution that provides flexibility and robustness to deal with dynamic and complex domains. Such flexibility can be achieved by the adoption of existing agent-based approaches, such as the BDI architecture, which provides agents with the mental attitudes of beliefs, desires and intentions. This architecture is highly customisable, leaving gaps to be fulfilled in particular applications. One of these gaps is the plan selection algorithm that is responsible for selecting a plan to be executed by an agent to achieve a goal, having an important influence on the overall agent performance. Most existing approaches require considerable effort for customisation and adjustment to be used in particular applications. In this dissertation, we propose a plan selection approach that is able to learn plans that provide possibly best outcomes, based on current context and agent’s preferences. Our approach is composed of a meta-model, which must be instantiated to specify plan metadata, and a technique that uses such metadata to learn and predict plan outcomes. We evaluated our approach experimentally, and results indicate it is effective. Additionally, we provide a tool to support the development process of software agents based on our work. This tool allows developers to model and generate source code for BDI agents with learning capabilities. A user study was performed to assess the improvements of a tool-supported BDI-agent-based development method, and evidences suggest that our tool can help developers that are not experts or are unfamiliar with the agent technology.

Orientador: Ricardo Ribeiro Gudwin / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Eletrica e de Computação / Made available in DSpace on 2018-08-05T14:04:06Z (GMT). No. of bitstreams: 1 Dario_ClaudiaFilomenaBratficher_M.pdf: 11451853 bytes, checksum: 8ecd6ccb893fcfa7790f5da4d3011ffd (MD5) Previous issue date: 2005 / Resumo: Este trabalho propõe uma Metodologia Unificada para o desenvolvimento de sistemas orientados a agentes. A elaboração desta metodologia foi realizada a partir de um estudo do papel do agente dentro da Engenharia de Software e da análise de diversas metodologias orientadas a agentes encontradas na literatura, enfocando-se principalmente em três destas: MaSE (Muitiagent Systems Engimering Metkodoiogy), Prornetheus e Tropos, além da linguagem de modelagem AÜML {Agem Vnijied Modeling Language). A Metodologia Unificada proposta visa aproveitar o que há de melhor nestas metodologias, buscando elementos comuns a todas elas, de modo análogo ao que ocorreu com a metodologia unificada (RUP - Raiional Unified Process) em sistemas orientados a objetos. Para validar a Metodologia Unificada e analisar as demais metodologias, um estudo de caso foi modelado. A Metodologia Unificada se mostrou eficiente no projeto, documentação e construção de sistemas multi-agentes, sendo considerada uma metodologia detalhada e mais completa por cobrir os estágios de especificação de requisitos, de análise e de projeto no desenvolvimento de software orientados a agentes / Abstract: This work proposes a Unified Methodology for the development of agent-oriented systems. The methodology was elaborated based on a study of agent's role within software engineering and the analysis of different agent-based software development methodologies found in the literature, focusing in three main ones: MaSE (Muitiagent Systems Engineering Methodology), Prometheus and Tropos, in addition to the modeling language AUM.L (Agent Unified Modeling Language). The Unified Methodology aims at taking advantage of the best from each methodology, searching for common elements among them, in an effort similar to what happened with the Unified Methodology (RUP - Rational Unified Process) in object-oriented systems. To validate the Unified Methodology and analyze the other methodologies, a case study was developed. The Unified Methodology has shown to be efficient in the design, documentation and construction of multi-agent systems. We conclude it to be a detailed and more complete methodology, covering requirements specification, analysis and design stages of agent-based software development / Mestrado / Engenharia de Computação / Mestre em Engenharia Elétrica

Submitted by PPG Ci?ncia da Computa??o (ppgcc@pucrs.br) on 2018-03-26T18:03:05Z No. of bitstreams: 1 ARTUR_FREITAS_TES.pdf: 1489846 bytes, checksum: 61623f4503a4a916e72487f33c15e294 (MD5) / Approved for entry into archive by Tatiana Lopes (tatiana.lopes@pucrs.br) on 2018-04-06T16:46:51Z (GMT) No. of bitstreams: 1 ARTUR_FREITAS_TES.pdf: 1489846 bytes, checksum: 61623f4503a4a916e72487f33c15e294 (MD5) / Made available in DSpace on 2018-04-06T16:57:00Z (GMT). No. of bitstreams: 1 ARTUR_FREITAS_TES.pdf: 1489846 bytes, checksum: 61623f4503a4a916e72487f33c15e294 (MD5) Previous issue date: 2017-08-31 / A engenharia orientada a modelos fornece abstra??es e nota??es para melhorar a compreens?o e para apoiar a modelagem, codifica??o e verifica??o de aplica??es em dom?nios espec?ficos. As ontologias, por outro lado, fornecem defini??es formais e expl?citas de conceitualiza??es compartilhadas e permitem o uso de racioc?nio sem?ntico. Embora essas ?reas tenham sido desenvolvidas por diferentes comunidades, sinergias importantes podem ser alcan?adas quando ambas s?o combinadas. Essas vantagens podem ser exploradas no desenvolvimento de sistemas multiagentes, dada a sua complexidade e a necessidade de integrar v?rios componentes que s?o frequentemente abordados de diferentes ?ngulos. Este trabalho investiga como aplicar ontologias para engenharia de software orientada a agentes. Inicialmente, apresentamos uma nova abordagem de modelagem onde os sistemas multiagentes s?o projetados usando a ontologia OntoMAS proposta. Ent?o, descrevemos t?cnicas, implementadas em uma ferramenta, para ajudar os programadores a trazer seus conceitos em c?digo e tamb?m gerar c?digo automaticamente a partir de modelos instanciados da ontologia. V?rias vantagens podem ser obtidas a partir dessas novas abordagens para modelar e codificar sistemas multiagentes, como o racioc?nio sem?ntico para realizar infer?ncias e mecanismos de verifica??o. Mas a principal vantagem ? a linguagem de especifica??o unificada de alto n?vel (conhecimento) que permite modelar as tr?s dimens?es que est?o unidas em JaCaMo para que as especifica??es dos sistemas possam ser melhor comunicadas entre equipes em desenvolvimento. As avalia??es dessas propostas indicam que elas contribuem com os diferentes aspectos da engenharia de software orientada a agentes, como a especifica??o, verifica??o e programa??o desses sistemas. / Model-driven engineering provides abstractions and notations for improving the understanding and for supporting the modelling, coding, and verification of applications for specific domains. Ontologies, on the other hand, provide formal and explicit definitions of shared conceptualisations and enable the use of semantic reasoning. Although these areas have been developed by different communities, important synergies can be achieved when both are combined. These advantages can be explored in the development of multi-agent systems, given their complexity and the need for integrating several components that are often addressed from different angles. This work investigates how to apply ontologies for agentoriented software engineering. Initially, we present a new modelling approach where multiagent systems are designed using the proposed OntoMAS ontology. Then, we describe techniques, implemented in a tool, to help programmers bring their concepts into code and also generate code automatically from instantiated ontology models. Several advantages can be obtained from these new approaches to model and code multi-agent systems, such as semantic reasoning to carry out inferences and verification mechanisms. But the main advantage is the unified high (knowledge) level specification language that allows modelling the three dimensions that are united in the JaCaMo framework so that systems specifications can be better communicated across developing teams. The evaluations of these proposals indicate that they contribute with the different aspects of agent-oriented software engineering, such as the specification, verification, and programming of these systems.

Agent-oriented software engineering is a new software engineering paradigm that is ideally suited to the analysis and design of complex systems. Open distributed environments place a growing demand on complex systems to be adaptive as well. Complex systems that can learn from and adapt to dynamically changing environments are called complex adaptive systems. These systems are characterized by emergent behaviour caused by interactions between system components and the environment. Agent-oriented software engineering methodologies attempt to control emergence during analysis and design by engineering the complex system in such a way that the correct emergent behaviour results during run-time. In a complex adaptive system however, emergent behaviour cannot be predicted during analysis and design, as it evolves only after implementation. By restricting emergent behaviour, as is done in most agent-oriented software engineering approaches, a complex system cannot be fully adaptive as well. We propose the BaBe methodology that will enable a complex system to be adaptive by learning from its environment and modifying its behaviour during run-time. This methodology adds a run-time emergence model consisting of distributed Bayesian behaviour networks to the agent-oriented software engineering lifecycle. These networks are initialised by the human software engineer during analysis and design and deployed by Bayesian agencies (also complex adaptive systems). The Bayesian agents are simple, and collectively they implement distributed Bayesian behaviour networks. These networks, being specialized Bayesian networks, enable the Bayesian agents to collectively mine relationships between emergent behaviours and the interactions that caused them to emerge, in order to adapt the behaviour of the system. The agents are organized into heterarchies of agencies, where each agency activates one or more component behaviour depending on the inference in the underlying Bayesian behaviour network. These agencies assist the human software engineer to bridge the gap between the implementation and the understanding of emergent behaviour in complex adaptive systems. Due to the simplicity of the agents and the minimal communication amongst them, they can be implemented using a commercially available component architecture. We describe a prototype implementation of the Bayesian agencies using Sun’s Enterprise JavaBeans™ component architecture. / Thesis (PhD (Computer Science))--University of Pretoria, 2005. / Computer Science / unrestricted

Made available in DSpace on 2015-03-05T14:01:21Z (GMT). No. of bitstreams: 0 Previous issue date: 3 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / Este trabalho apresenta o desenvolvimento do HRCSystem (Sistema de Consulta a Recursos Humanos), desde concepção até os experimentos de validação. Intrínseco ao desenvolvimento do sistema estão os conceitos de áreas como Gestão de Projetos, Gestão por Competências e Engenharia de Software Orientada a Agentes. O principal objetivo do HRCSystem é auxiliar gerentes de projetos na escolha de um profissional que seja mais adequado à realização de uma atividade, considerando características de qualificação e disponibilidade deste profissional. Para isso, o HRCSystem implementa um modelo cognitivo para representar conceitos de competência humana e processos de gestão de competência de natureza psicológica. Este modelo cognitivo de competências também é proposto na dissertação, sendo outro importante resultado deste trabalho. Metodologias como TROPOS, Prometheus e Métodos Derivados de ITS (Intelligent Tutoring System) dão suporte às fases de análise e projeto do sistema. A fase de implementação é executada com aux / This work presents the development of the HRCSystem (System to Query Human Resources) from conception up to the experiments for validation. Intrinsic to the development of the application are the concepts of research areas as Project Management, Competencies Management and Agent-Oriented Software Engineering. HRCSystem goal is to assist project managers in choosing a professional that is more appropriate for some activity, considering the competencies and availability of the professional. To do so, HRCSystem implements a cognitive model aimed to represent human competency concepts and competence management processes of psychological nature. This cognitive model of competencies is also proposed in this work, being another important result of it. Methodologies like TROPOS, Prometheus and Methods Derived from ITS ( Intelligent Tutoring System) support analysis and design phases of the system. The implementation phase is executed with the help of AgentSpeak(L) language and JASON tool. Finally, both model and s

In recent years many people have built Personal Assistant Agents, Information Agents and the like, and have simply added them to the operating system as auxiliary applications, without regard to architecture. This thesis argues that an agent architecture, one designed as a sophisticated representation of an individual user, should be embedded deep in the device system software, with at least equal status to the GUI – the graphical user interface. A sophisticated model of the user is then built, drawing upon contemporary Analytical Psychology – the Psychology of Subselves. The Shadowboard Agent architecture is then built upon that user model, drawing both structural and computational implications from the underlying psychology. An XML DTD file named Shadowboard.dtd is declared as a practical manifestation of the semantics of Shadowboard. An implementation of the Shadowboard system is mapped out, via a planned conversion of two existing integrated systems: SlimWinX, an event-driven GUI system; and XSpaces, an object-oriented tuplespace system with Blackboard-like features. The decision making mechanism passes logic terms and contraints between the various sub-agent components (some of which take on the role of Constraint Solvers), giving this agent system some characteristics of a Generalised Constraint Solver. A Shadowboard agent (built using the system) consists of a central controlling autonomous agent named the Aware Ego Agent, and any number of sub-agents, which collectively form an integrated but singular whole agent modelled on the user called the Digital Self. One such whole-agent is defined in a file named DigitalSelf.xml – which conforms to the schema in Shadowboard.dtd - which offers a comprehensive and generic representation of a user’s stance in a 24x7 network, in particular - the Internet. Numerous types of Shadowboard sub-agents are declared.

Submitted by Mariana Dornelles Vargas (marianadv) on 2015-05-25T12:29:15Z No. of bitstreams: 1 AutoEduMat.pdf: 1060362 bytes, checksum: 25b8156de4b9c2c2c5b9dc0f69aea011 (MD5) / Made available in DSpace on 2015-05-25T12:29:15Z (GMT). No. of bitstreams: 1 AutoEduMat.pdf: 1060362 bytes, checksum: 25b8156de4b9c2c2c5b9dc0f69aea011 (MD5) Previous issue date: 2010 / Nenhuma / Esta dissertação apresenta uma pesquisa relacionada as ferramentas que dão suporte a utilização de objetos de aprendizagem em plataformas digitais. Mais especificamente, a pesquisa se direciona para as ferramentas de apoio a autoria destes objetos, em particular dos seus metadados. Inicialmente é apresentada a contextualização do problema de pesquisa, sua fundamentação teórica e os trabalhos relacionados ao tema. Em seguida são apresentadas as principais características do sistema proposto, o AutoEduMat - Ferramenta de Apoio a Autoria de Metadados de Objetos de Aprendizagem para o Domínio de Ensino de Matemática. A ferramenta AutoEduMat dá apoio a autoria de objetos de aprendizagem, oferecendo assistência ao projetista (designer) de objetos na criação e edição de metadados destes objetos. A principal inovação do trabalho é a combinação das tecnologias de Engenharia de Software de Agentes e de Engenharia de Ontologias para construir um sistema multiagente que oferece suporte inteligente para a geração dos metadados dos objetos de aprendizagem, sendo capaz de interagir com o usuário com termos de seu próprio contexto profissional e educacional. No trabalho é proposta a ontologia Onto-EduMat que incorpora os conhecimentos sobre o domínio de ensino de matemática, incluindo aspectos pedagógicos, necessários para o auxílio a geração dos metadados. Tanto a ferramenta quanto seu modelo ontológico são validados através de experimentos descritos no final do trabalho. / This dissertation presents a research related to the tools that support the utilization of learning objects in digital platforms. More precisely, the research is directed to the tools that support the authoring process of these objects, in particular of their metadata. Initially are presented the characterization of the problem, its theoretical foundations and related works. Then are presented the main characteristics of the proposed system, the AutoEduMat - Metadata Authoring Tool for Mathematics Learning Objects. The AutoEduMat system will provide assistance to the object designer in the metadata creation and edition of these objects. The main innovation of this work is the combination of Agent Oriented Software Engineering and Ontology Engineering technologies to built a multiagent system able to offer intelligent support for metadata creation, interacting with users using terms related to their professional and educational context. This work proposes the Onto-EduMat ontology, which incorporates the mathematical and pedagogical knowledge necessary to generate the metadata. The authoring tool and its ontological model are validated through experiments described in the end of the work.