This research has two facets within separate research areas. The research area of Belief, Desire and Intention (BDI) agent capability development was extended. Deception detection research has been advanced with the development of automation using BDI agents. BDI agents performed tasks automatically and autonomously. This study used these characteristics to automate deception detection with limited intervention of human users. This was a useful research area resulting in a capability general enough to have practical application by private individuals, investigators, organizations and others. The need for this research is grounded in the fact that humans are not very effective at detecting deception whether in written or spoken form. This research extends the deception detection capability research in that typical deception detection tools are labor intensive and require extraction of the text in question following ingestion into a deception detection tool. A neural network capability module was incorporated to lend the resulting prototype Machine Learning attributes. The prototype developed as a result of this research was able to classify online data as either "deceptive" or "not deceptive" with 85% accuracy. The false discovery rate for "deceptive" online data entries was 20% while the false discovery rate for "not deceptive" was 10%. The system showed stability during test runs. No computer crashes or other anomalous system behavior were observed during the testing phase. The prototype successfully interacted with an online data communications server database and processed data using Neural Network input vector generation algorithms within seconds

Submitted by Caroline Xavier (caroline.xavier@pucrs.br) on 2017-06-30T18:24:08Z No. of bitstreams: 1 TES_JOAO_MARIO_LOPES_BREZOLIN_COMPLETO.pdf: 6143939 bytes, checksum: 1a0972ea0dfb3d652f4b28273cc15d43 (MD5) / Made available in DSpace on 2017-06-30T18:24:08Z (GMT). No. of bitstreams: 1 TES_JOAO_MARIO_LOPES_BREZOLIN_COMPLETO.pdf: 6143939 bytes, checksum: 1a0972ea0dfb3d652f4b28273cc15d43 (MD5) Previous issue date: 2017-03-15 / Coordena??o de Aperfei?oamento de Pessoal de N?vel Superior - CAPES / The BDI architecture is the preferred approach for the development of agents situated in complex dynamic environments. The BDI architecture, which is founded on the symbolic model, represents a consolidated model that counts upon substantial theoretical-practical contributions. However, according to G?rdenfors, despite its strengths, there are some aspects of the cognitive phenomena which give rise to the need of a conceptual model that has to establish itself between the perceptual and the symbolic levels. Taking into account the principle that recognition of objects can be set as a process of concept formation, this thesis comprises the design and implementation of a knowledge representation model for BDI agents based on the assumptions of the paradigm of conceptual spaces. In this sense, the actual approach seeks to establish the necessary mechanisms for the development of this model through the use of the Jason platform and the programming language CSML. From the issues which are inherent to the development of an application directed to the aid of visually impaired people, this thesis aims to evaluate the implications of the building processes of the conceptual inference model for BDI agents. / A arquitetura BDI ? a estrat?gia preferencial no que tange ao desenvolvimento de agentes situados em ambientes complexos e din?micos. Alicer?ada no modelo simb?lico, a arquitetura BDI representa um modelo consolidado que conta com um substancial aporte pr?tico-te?rico. Entretanto, conforme assinala G?rdenfors, apesar da robustez desse modelo, h? aspectos do fen?meno cognitivo que suscitam a necessidade de um modelo conceitual que estabelece-se entre os n?veis simb?lico e perceptual. Partindo do princ?pio de que o reconhecimento de objetos pode ser assinalado como um processo de forma??o de conceitos, esta tese abrange a concep??o e a implementa??o de um modelo de representa??o do conhecimento para agentes BDI com base nos pressupostos do paradigma dos espa?os conceituais. Nesse sentido, esta abordagem busca estabelecer atrav?s da plataforma Jason e da linguagem de programa??o CSML os mecanismos necess?rios para o desenvolvimento desse modelo. A partir da problem?tica inerente ao desenvolvimento de uma aplica??o voltada ao aux?lio de pessoas cegas, esta proposta busca avaliar as implica??es do processo de constru??o do modelo de infer?ncia conceitual para agentes BDI.

Network Functions Virtualisation (NFV) separa as funções de rede dos dispositivos físicos, simplificando a implantação de novos serviços. As típicas funções de rede, como firewalls, aceleradores de tráfego, sistemas de detecção de intrusão e sistemas de prevenção de intrusões, são tradicionalmente realizadas por equipamentos físicos proprietários, que devem ser instalados manualmente pelos operadores de rede. A implantação de equipamentos físicos é desafiadora porque eles têm requisitos específicos de encadeamento e ordenação. Ao contrário dos equipamentos físicos tradicionais, as funções de rede virtuais (VNFs) podem ser dinamicamente implementadas e reconfiguradas sob demanda, colocando desafios de gerenciamento rigorosos aos sistemas em rede. A seleção das VNFs mais apropriadas para atingir um objetivo específico e a decisão sobre onde implantar essas VNFs e por quais caminhos elas se comunicarão são responsabilidades de um orquestrador de NFV. Nesta dissertação, propomos orquestrar VNFs usando componentes cognitivos interativos estruturados com a arquitetura belief-desire-intention (BDI), levando a soluções emergentes para enfrentar os desafios da rede. A arquitetura BDI inclui um ciclo de raciocínio que fornece aos agentes um comportamento racional, permitindo que lidem com diferentes cenários nos quais o comportamento flexível e inteligente é necessário. Estendemos a arquitetura NFV substituindo seu orquestrador centralizado por agentes BDI. Nossa proposta inclui um protocolo de leilão reverso e uma nova heurística de licitação que permite que os agentes tomem decisões sobre as tarefas de orquestração. Por fim, nós fornecemos uma plataforma de testes que integra uma plataforma para o desenvolvimento de agentes BDI com um emulador de rede, permitindo que os agentes controlem as VNFs e percebam a rede. Essa plataforma de testes é usada para implementar VNFs e avaliar empiricamente nosso modelo teórico em um ataque de negação de serviço distribuído. Os resultados da avaliação mostram que uma solução para o ataque DDoS surge através da negociação de agentes, mitigando com sucesso o ataque. / Network Functions Virtualisation (NFV) decouples network functions from physical devices, simplifying the deployment of new services. Typical network functions, like firewalls, traffic accelerators, intrusion detection systems and intrusion prevention systems, are traditionally performed by proprietary physical appliances, which must be manually installed by network operators. Their deployment is challenging because they have specific chaining requirements. As opposed to traditional physical appliances, virtual network functions (VNFs) can be dynamically deployed and reconfigured on demand, posing strict management challenges to networked systems. The selection of the most appropriate VNFs to achieve a particular objective, the decision on where to deploy these VNFs and through which paths they will communicate are the responsibilities of an NFV orchestrator. In this dissertation, we propose to orchestrate VNFs using interacting cognitive components structured with the belief-desire-intention (BDI) architecture, leading to emergent solutions to address network challenges. The BDI architecture includes a reasoning cycle, which provides agents with rational behaviour, allowing agents to deal with different scenarios in which flexible and intelligent behaviour is needed. We extend the NFV architecture, replacing its centralised orchestrator with BDI agents. Our proposal includes a reverse auction protocol and a novel bidding heuristic that allow agents to make decisions regarding the orchestration tasks. Finally, we provide a testbed that integrates a platform for developing BDI agents with a network emulator, allowing agents to control VNFs and perceive the network. This testbed is used to implement VNFs and empirically evaluate our theoretical model in a distributed denial-of-service (DDoS) attack. The evaluation results show that a solution to the DDoS attack emerges through the negotiation of agents, successfully mitigating the attack.

Made available in DSpace on 2016-03-22T17:26:24Z (GMT). No. of bitstreams: 1 Dissertacao II Fernanda.pdf: 5870886 bytes, checksum: 38e862a3e70d2150160467fa6341965c (MD5) Previous issue date: 2009-12-22 / Simulações sociais em sistemas de agentes têm sido um tema presente na comunidade de Inteligência Artificial. O presente trabalho aborda estudos de conceitos relativos a um sistema microeconômico para modelagem de agentes econômicos cognitivos, com comportamento de consumidor e de produtor, com base no conceito do modelo de agentes BDI. A fim de destacar a importância desta modelagem, trabalhos relacionados à área de pesquisa são examinados, enfatizando a originalidade deste modelo de agente econômico cognitivo. Também são apresentados conceitos básicos inerentes a esta modelagem, tais como: trocas sociais e econômicas, e as interações entre os agentes. O conteúdo de microeconomia apresentado aborda os conceitos básicos de mercado e dos modelos de consumidor e de produtor utilizados na modelagem. Do mesmo modo, é apresentado um estudo do modelo de agentes BDI para a modelagem de agentes reativos e cognitivos. Estudos sobre um modelo básico de comportamento do consumidor, o processo de tomada de decisão e formação de comportamento e sobre Teoria da Firma são apresentados para embasar o comportamento dos agentes. Por fim, o modelo de um agente econômico cognitivo, com comportamento de consumidor e de produtor, é apresentado, bem como os resultados da simulação de um mercado com quatro agentes econômicos cognitivos

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.

Submitted by Cristiane Chim (cristiane.chim@ucpel.edu.br) on 2017-04-24T14:36:33Z No. of bitstreams: 1 Clarissa Martins.pdf: 1616707 bytes, checksum: 7d6ba6c5f2c247d0a5ccd351abde1ebe (MD5) / Made available in DSpace on 2017-04-24T14:36:33Z (GMT). No. of bitstreams: 1 Clarissa Martins.pdf: 1616707 bytes, checksum: 7d6ba6c5f2c247d0a5ccd351abde1ebe (MD5) Previous issue date: 2014-10-28 / This dissertation refers to an epidemiological study of screening scales for depression in pregnant adolescents. The main objective of the research was to adjust the cutoff scales for screening for depression, Edinburgh Postnatal Depression Scale (EPDS) and Beck Depression Inventory (BDI), for pregnant teenagers. It is a cross-sectional, population-based study carried out with pregnant adolescents (10-19 years old), which consulted the service prenatal Unified Health System (SUS) of Pelotas. Was carried out from October 2009 to March 2011. The sample was composed based on the SIS-Prenatal program records along the municipal health department and the Basic Health Units, and specialized clinics in the urban area of Pelotas / RS. The women answered a questionnaire with socio demographic and obstetric data, besides the two scales for screening for depression during pregnancy. Also participated in a structured clinical interview Mini International Neuropsychiatric Interview 5.0 (MINI) for the clinical diagnosis of depression. Demographic, obstetric and psychiatric social variables were assessed according to the WHO questionnaire. The accuracy of the scales was calculated by their Area under the curve (AUC) of ROC, as well as their respective sensitivity, specificity and predictive values. The best cutoff (PC) found for this sample was ≥10 EPDS scale, with sensitivity 81.1% and specificity 82.7% and AUC of 0.899. BDI for the best cutoff point was ≥11, sensitivity 81.1%, sensitivity 76.8% and an AUC of 0.869. Since the difference between the two AUC were statistically significant (p = 0, 0215). Based on the results, it is concluded that the EPDS scale has become more predictive and sensitive in screening for depression in pregnant adolescents, with respect to BDI. / A presente dissertação refere-se a um estudo epidemiológico sobre escalas de rastreamento para depressão em gestantes adolescentes. O objetivo principal da pesquisa foi verificar os pontos de corte das escalas para rastreamento da depressão Edinburgh Postnatal Depression Scale (EPDS) e Beck Depression Inventory (BDI), em gestantes adolescentes. Trata-se de um estudo transversal, de base populacional, realizado com gestantes adolescentes (10 a 19 anos de idade), as quais consultaram o serviço de pré-natal do Sistema Único de Saúde (SUS) de Pelotas-RS. Desenvolvido no período de outubro de 2009 a março de 2011. A amostra foi composta com base nos registros do programa SIS-Pré-Natal, junto a secretaria municipal de saúde e nas Unidades Básicas de Saúde, além de ambulatórios especializados na zona urbana de Pelotas/RS. As gestantes responderam a um questionário com dados sócio demográfico e obstétricos, além das duas escalas para o rastreamento da depressão durante a gestação. Também participaram de uma entrevista clínica estruturada Mini Internacional Neuropsychiatric Interview 5.0 (MINI) para o diagnóstico clínico da depressão. As variáveis sócio demográficas, obstétricas e psiquiátricas foram avaliadas nos domínios do questionário da OMS. A precisão das escalas foi calculada através de suas Áreas sob a curva (AUC) de ROC, assim como suas respectivas sensibilidade, especificidade e valores preditivos. O melhor ponto de corte (PC) encontrado para esta amostra na escala EPDS foi ≥10, com sensibilidade 81,1% e especificidade 82,7% e AUC de 0,899. Para a escala BDI o melhor ponto de corte foi ≥11, sensibilidade 81,1%, sensibilidade 76,8% e uma AUC de 0,869. Sendo que a diferença entre as duas AUC mostraram-se estatisticamente significativas (p=0,0215). Com base nos resultados, conclui-se que a escala EPDS apresenta-se mais preditiva e sensível no rastreamento para depressão em gestantes adolescentes, quando contrastada com a escala BDI.

On the basis of extensive practical experience in the development of agent-based systems for manufacturing execution and agent-based systems in general, a reference model for holonic execution known as HERA (Holonic Execution Reference Architecture) is developed. The model is characterised by a focus on holarchy - Koestler's Janus Effect (Koestler, 1967) is explicitly captured. However, the Holonic Manufacturing Systems (HMS) Consortium's view of a holon having an information processing part and a physical part (Brennan and Norrie, 2003) is also present. We refer to these parts as the behaviour and the embodiment respectively.

Personal assistants need to allow the user to interact with the system in a flexible and adaptive way such as through spoken language dialogue. This research is aimed at achieving robust and effective dialogue management in such applications. We focus on an application, the Smart Personal Assistant (SPA), in which the user can use a variety of devices to interact with a collection of personal assistants, each specializing in a task domain. The current implementation of the SPA contains an e-mail management agent and a calendar agent that the user can interact with through a spoken dialogue and a graphical interface on PDAs. The user-system interaction is handled by a Dialogue Manager agent. We propose an agent-based approach that makes use of a BDI agent architecture for dialogue modelling and control. The Dialogue Manager agent of the SPA acts as the central point for maintaining coherent user-system interaction and coordinating the activities of the assistants. The dialogue model consists of a set of complex but modular plans for handling communicative goals. The dialogue control flow emerges automatically as the result of the agent???s plan selection by the BDI interpreter. In addition the Dialogue Manager maintains the conversational context, the domainspecific knowledge and the user model in its internal beliefs. We also consider the problem of dialogue adaptation in such agent-based dialogue systems. We present a novel way of integrating learning into a BDI architecture so that the agent can learn to select the most suitable plan among those applicable in the current context. This enables the Dialogue Manager agent to tailor its responses according to the conversational context and the user???s physical context, devices and preferences. Finally, we report the evaluation results, which indicate the robustness and effectiveness of the dialogue model in handling a range of users.

Notre travail a porté sur le développement d'un instrument pour l'aide à la négociation des acteurs impliqués dans la gestion de l'eau, ressource posant actuellement de façon accrue le problème de la durabilité. Pour cette ressource des directives générales ont été édictées au niveau national et européen. La mise en œuvre concrète de ces réglementations passe au niveau régional et au niveau local par la création de règles résultant de négociations entre les différents acteurs concernés. Toutefois, l'émergence de ces règles de gestion et d'allocation de la ressource se fait bien souvent sans vision des conséquences résultant de l'adoption de celles-ci tant au niveau global qu'au niveau individuel. Le but de notre travail est de fournir méthodes et instruments pour faciliter une négociation dont l'enjeu est de déterminer les règles d'accès à cette ressource pour les différents utilisateurs. Nous avons, d'une part, mis à l'épreuve la conception agent BDI (Beliefs, Desires and Intentions) à un problème relevant des sciences sociales et de grande taille. D'autre part, nous avons conçu une architecture multi-agent appropriée au problème posé intégrant la dimension négociation. Enfin, nous avons initié une méthodologie de conception interactive avec les acteurs de terrain. La construction de l'instrument de simulation s'est faite en deux phases : Une première maquette (Manga) concerne une situation simple de gestion (type nappe). Manga a permis d'explorer différents corps de règles d'attribution de l'eau et attitudes des agriculteurs face au risque climatique. Toutefois passer à des situations de gestion plus réalistes mais plus complexes, nous a conduit à enrichir fortement la représentation des acteurs et à concevoir une deuxième maquette (MangaLère). En nous appuyant sur le cas concret de la gestion de la Lère, nous avons testé l'adéquation du formalisme BDI à la représentation des acteurs concernés et commencé à développer une ontologie propre au problème posé.

Modeling comprehensive human decision behaviors in a unified and extensible framework is quite challenging. In this research, an integrated Belief-Desire-Intention (BDI) modeling framework is proposed to represent the human decision behavior, whose submodules (Belief, Desire, Decision-Making, and Emotion modules) are based on a Bayesian belief network (BBN), Decision-Field-Theory (DFT), a probabilistic depth first search (PDFS) technique, and a BBN-reinforcement (Q-Learning) hybrid learning algorithm. A key novelty of the proposed model is its ability to represent various human decision behaviors such as decision-making, decision-planning, and learning in a unified framework.To this end, first, we extend DFT (a widely known psychological model for preference evolution) to cope with dynamic environments. The extended DFT (EDFT) updates the subjective evaluation for the alternatives and the attention weights on the attributes via BBN under the dynamic environment. To illustrate and validate the proposed EDFT, a human-in-the-loop experiment is conducted for a virtual stock market. Second, a new approach to represent learning (a dynamic evolution process of underlying modules) in the human decision behavior is proposed under the context of the BDI framework. Our research focuses on how a human adjusts his perception process (involving BBN) dynamically against his performance (depicted via a confidence index) in predicting the environment as part of his decision-planning. To this end, Q-learning is employed and further developed.To mimic realistic human behaviors, attributes of the BDI framework are reverse-engineered from human-in-the-loop experiments conducted in the Cave Automatic Virtual Environment (CAVE). The proposed modeling framework is demonstrated for a human's evacuation behaviors in response to a terrorist bomb attack. The constructed simulation has been used to test the impact of several factors (e.g., demographics, number of police officers, information sharing via speakers) on evacuation performance (e.g., average evacuation time, percentage of casualties).In addition, the proposed human decision behavior model is extended for decisions of many stakeholders that form a complex social network in the community-based development of software systems.To the best of our knowledge, the proposed human decision behavior modeling framework is one of the first efforts to represent various human decision behaviors (e.g., decision-making, decision-planning, dynamic learning) in a unified BDI framework.