[pt] O uso de sistemas baseados em agentes é adequado à construção de software complexo. Para garantir uma ordem social desejável é preciso lidar com a autonomia e a diversidade de interesses dos agentes e as normas são mecanismos eficientes de controle usados para regular o comportamento dos agentes. O teste de software continua sendo amplamente aplicado para garantir a qualidade do software. No contexto de sistemas multiagentes normativos, os testes devem lidar com a necessidade dos agentes atuarem de forma robusta sob condições normativas dinâmicas as quais os desenvolvedores não consideraram. Neste contexto, propomos uma abordagem para testar agentes normativos que seguem o modelo belief-desire-intention. Como contribuições, esta tese apresenta: um framework para desenvolvimento de agentes BDI normativos, o NBDI4JADE; um modelo modelo de faltas para apoiar a identificação dos diferentes tipos de falhas em agentes normativos; um framework para testar agentes BDI normativos, o N-JAT4BDI e, um método para geração de casos de teste a partir de modelos ANA-ML dos agentes. Avaliamos o framework de teste através de um estudo experimental no qual discutimos a eficiência e a eficácia do framework. Avaliamos, também, a eficácia do método de geração de casos de teste,aplicando-o a dois cenários de uso: (i) um sistema para gerenciar a submissão e o processo de revisão de artigos em conferências, e (ii) um sistema de venda de pacotes turísticos de uma agência de viagens. Os resultados obtidos nas avaliações de ambos os frameworks apresentam indícios positivos da eficiência e eficácia na detecção e identificação de falhas em agentes normativos e eficiência na geração dos casos de teste. / [en] The use of agent-based systems is suitable for the construction of complex software. To guarantee a desirable social order one we must deal with the autonomy and diversity of interests of the agents and norms are efficient mechanisms of control used to regulate the behavior of the agents. Software testing still have been widely applied to ensure the software quality. In the context of normative multiagent systems, the test must deal with the need for the agents to act robustly under dynamic normative conditions in which the developers did not consider. In this context, we propose an approach to test normative agents that follow the belief-desire-intention model. Among the contributions, this thesis presents: a framework for development of normative BDI agents, the NBDI4JADE; a fault model to support the identification of different types of failures in normative agents; a framework for testing normative BDI agents, the N-JAT4BDI, and a method for generating test cases from ANA-ML models.We evaluated the test framework through an experimental study in which we discussed the efficiency and effectiveness of the framework. We also evaluate the effectiveness of the test case generation method, applying it to two usage scenarios: (i) a system to the manage submission and the review process of articles in conferences, and (ii) a system of sale of tour packages from a travel agency. The results obtained in the evaluations of both frameworks presented positive indications of efficiency and effectiveness in the detection and identification of failures in normative agents and efficiency in the generation of test cases.

<p dir="ltr">We present a framework for Trustworthy Artificial Intelligence (TAI) that dynamically assesses trust and scrutinizes past decision-making, aiming to identify both individual and community behavior. The modeling of behavior incorporates proposed concepts, namely trust pressure and trust sensitivity, laying the foundation for predicting future decision-making regarding community behavior, consensus level, and decision-making duration. Our framework involves the development and mathematical modeling of trust pressure and trust sensitivity, drawing on social validation theory within the context of environmental decision-making. To substantiate our approach, we conduct experiments encompassing (i) dynamic trust sensitivity to reveal the impact of learning actors between decision-making, (ii) multi-level trust measurements to capture disruptive ratings, and (iii) different distributions of trust sensitivity to emphasize the significance of individual progress as well as overall progress.</p><p dir="ltr">Additionally, we introduce TAI metrics, trustworthy acceptance, and trustworthy fairness, designed to evaluate the acceptance of decisions proposed by AI or humans and the fairness of such proposed decisions. The dynamic trust management within the framework allows these TAI metrics to discern support for decisions among individuals with varying levels of trust. We propose both the metrics and their measurement methodology as contributions to the standardization of trustworthy AI.</p><p dir="ltr">Furthermore, our trustability metric incorporates reliability, resilience, and trust to evaluate systems with multiple components. We illustrate experiments showcasing the effects of different trust declines on the overall trustability of the system. Notably, we depict the trade-off between trustability and cost, resulting in net utility, which facilitates decision-making in systems and cloud security. This represents a pivotal step toward an artificial control model involving multiple agents engaged in negotiation.</p><p dir="ltr">Lastly, the dynamic management of trust and trustworthy acceptance, particularly in varying criteria, serves as a foundation for causal AI by providing inference methods. We outline a mechanism and present an experiment on human-driven causal inference, where participant discussions act as interventions, enabling counterfactual evaluations once actor and community behavior are modeled.</p>

<p dir="ltr">Learning, planning, and representing knowledge at multiple levels of temporal abstractions provide an agent with the ability to predict consequences of different courses of actions, which is essential for improving the performance of sequential decision making. However, discovering effective temporal abstractions, which the agent can use as skills, and adopting the constructed temporal abstractions for efficient policy learning can be challenging. Despite significant advancements in single-agent settings, temporal abstractions in multi-agent systems remains underexplored. This thesis addresses this research gap by introducing novel algorithms for discovering and employing temporal abstractions in both cooperative and competitive multi-agent environments. We first develop an unsupervised spectral-analysis-based discovery algorithm, aiming at finding temporal abstractions that can enhance the joint exploration of agents in complex, unknown environments for goal-achieving tasks. Subsequently, we propose a variational method that is applicable for a broader range of collaborative multi-agent tasks. This method unifies dynamic grouping and automatic multi-agent temporal abstraction discovery, and can be seamlessly integrated into the commonly-used multi-agent reinforcement learning algorithms. Further, for competitive multi-agent zero-sum games, we develop an algorithm based on Counterfactual Regret Minimization, which enables agents to form and utilize strategic abstractions akin to routine moves in chess during strategy learning, supported by solid theoretical and empirical analyses. Collectively, these contributions not only advance the understanding of multi-agent temporal abstractions but also present practical algorithms for intricate multi-agent challenges, including control, planning, and decision-making in complex scenarios.</p>

Thesis (M. Tech.) -- Central University of Technology, Free State, 2010 / Traditional corrective maintenance is both costly and ineffective. In some situations it is more cost effective to replace a device than to maintain it; however it is far more likely that the cost of the device far outweighs the cost of performing routine maintenance. These device related costs coupled with the profit loss due to reduced production levels, makes this reactive maintenance approach unacceptably inefficient in many situations. Blind predictive maintenance without considering the actual physical state of the hardware is an improvement, but is still far from ideal. Simply maintaining devices on a schedule without taking into account the operational hours and workload can be a costly mistake. The inefficiencies associated with these approaches have contributed to the development of proactive maintenance strategies. These approaches take the device health state into account. For this reason, proactive maintenance strategies are inherently more efficient compared to the aforementioned traditional approaches. Predicting the health degradation of devices allows for easier anticipation of the required maintenance resources and costs. Maintenance can also be scheduled to accommodate production needs. This work represents the design and simulation of an intelligent maintenance management system that incorporates device health prognosis with maintenance schedule generation. The simulation scenario provided prognostic data to be used to schedule devices for maintenance. A production rule engine was provided with a feasible starting schedule. This schedule was then improved and the process was determined by adhering to a set of criteria. Benchmarks were conducted to show the benefit of optimising the starting schedule and the results were presented as proof. Improving on existing maintenance approaches will result in several benefits for an organisation. Eliminating the need to address unexpected failures or perform maintenance prematurely will ensure that the relevant resources are available when they are required. This will in turn reduce the expenditure related to wasted maintenance resources without compromising the health of devices or systems in the organisation.

Thesis (M. Tech. (Engineering: Electrical)) -- Central University of technology, Free State, 2013 / The South African (SA) manufacturing industry requires developing similar levels of sophistication and expertise in automation as its international rivals to compete for global markets. To achieve this, manufacturing plants need to be managed extremely efficiently to ensure the quality of manufactured products and these plants must also have the relevant infrastructure. Furthermore, this industry must also compensate for rapid product introduction, product changes and short product lifespan. To support this need, this industry must engage in the current trend in automation known as reconfigurable manufacturing. The aim of the study is to develop a reconfigurable assembly system with enhanced control capabilities by utilizing virtual commissioning. In addition, this system must be capable of assembling multiple different products of a product range; reconfigure to accommodate the requirements of these products; autonomously reroute the product flow and distribute workload among assembly cells; handle erroneous products; and implement enhanced control methods. To achieve this, a literature study was done to confirm the type of components to be used, reveal design issues and what characteristics such a system must adhere to. Software named DELMIA was used to create a virtual simulation environment to verify the system and simultaneously scrutinize the methods of verification. On completion, simulations were conducted to verify software functions, device movements and operations, and the control software of the system. Based on simulation results, the physical system was built, and then verified with a multi agent system as overhead control to validate the entire system. The final results showed that the project objectives are achievable and it was also found that DELMIA is an excellent tool for system verification and will expedite the design of a system. By obtaining these results it is indicated that companies can design and verify their systems earlier through virtual commissioning. In addition, their systems will be more flexible, new products or product changes can be introduced more frequently, with minimum cost and downtime. This will enable SA manufacturing companies to be more competitive, ensure increased productivity, save time and so ensure them an advantage over their international competition.

Common control channels in cognitive radio (CR) ad hoc networks are spectrum resources temporarily allocated and commonly available to CR users for control message exchange. With no presumably available network infrastructure, CR users rely on cooperation to perform spectrum management functions. One the one hand, CR users need to cooperate to establish common control channels, but on the other hand, they need to have common control channels to facilitate such cooperation. This control channel problem is further complicated by primary user (PU) activities, channel impairments, and intelligent attackers. Therefore, how to reliably and securely establish control links in CR ad hoc networks is a challenging problem. In this work, a framework for control channel design and analysis is proposed to address control channel reliability and security challenges for seamless communication and spectral efficiency in CR ad hoc networks. The framework tackles the problem from three perspectives: (i) responsiveness to PU activities: an efficient recovery control channel method is devised to efficiently establish control links and extend control channel coverage upon PU's return while mitigating the interference with PUs, (ii) robustness to channel impairments: a reinforcement learning-based cooperative sensing method is introduced to improve cooperative gain and mitigate cooperation overhead, and (iii) resilience to jamming attacks: a jamming-resilient control channel method is developed to combat jamming under the impacts of PU activities and spectrum sensing errors by leveraging intrusion defense strategies. This research is particularly attractive to emergency relief, public safety, military, and commercial applications where CR users are highly likely to operate in spectrum-scarce or hostile environment.

La modélisation de la dynamique des piétons, des cyclistes et des conducteurs de véhicules est d'un grand intérêt théorique et pratique. Au cours des deux dernières décennies, la Recherche dans un large éventail de domaines tels que l'infographie, la physique, la robotique, les sciences sociales, la sécurité et les systèmes de formation a créé des simulations impliquant des individus de type hétérogènes. Deux grands types de simulation d'individus dans un univers virtuel peuvent généralement être distingués selon qu'elles cherchent à atteindre : un haut niveau de réalisme de comportement (simulation pour la sécurité ou les sciences sociales) ou une visualisation de haute qualité (productions de films, de jeux vidéos, d'outils de réalité virtuelle). Dans la première catégorie, les résultats de simulation sont généralement cohérents avec les observations réalisées sur la population réelle et peuvent servir de base à des études théoriques pour l'évaluation et la prévision du comportement des individus. Dans la seconde catégorie, les modèles de comportement ne sont pas la priorité et ne correspondent pas quantitativement au monde réel. Cependant, les individus sont des personnages en 3D entièrement animés et les utilisateurs de l'application peuvent avoir un degré élevé d'interaction avec les éléments de la simulation. Les recherches et les applications récentes tendent à unifier ces deux domaines, en particulier dans le domaine des systèmes de formation où les deux aspects sont nécessaires pour une formation efficace. Dans ce cadre, les systèmes multiagents sont utilisés pour modéliser les populations d'individus. Ils forment un paradigme prometteur pour la conception de logiciels complexes. En effet, ce paradigme propose de nouvelles stratégies pour analyser, concevoir et implémenter de tels systèmes. Les systèmes multiagents sont considérés comme des sociétés composées d'entités autonomes et indépendantes, appelées agents, qui interagissent en vue de résoudre un problème ou de réaliser collectivement une tâche. Les systèmes multiagents peuvent être considérés comme un outil viable pour la modélisation et la simulation de systèmes complexes, et notamment les systèmes de simulation d'individus dans un univers virtuel. Nous proposons un métamodèle organisationnel et holonique permettant de modéliser ces systèmes multiagents. L'approche organisationnelle permet de décomposer le système en unités comportementales appelées rôles. L'approche holonique permet de composer le système en un ensemble d'agents, eux-mêmes, pouvant être décomposés en un ensemble d'agents, et ainsi de suite. Ce métamodèle est utilisé comme la base de notre processus méthodologique, appelé ASPECS, qui guide les scientifiques et les experts d'un domaine dans la modélisation et la construction d'un modèle d'un SMA représentant un système complexe. Sur la base du métamodèle organisationnel et holonique, nous proposons des modèles d'environnement et de groupes d'individus constituant un système de grande échelle spatiale et avec une large population d'individus. Ces modèles sont utilisés pour la simulation d'individus et de foules dans des univers virtuels. L'une des particularités intéressantes de nos modèles est leur conception multiniveau. Nous proposons des modèles de décomposition hiérarchique dynamique pour l'environnement et pour la population. Durant le processus de simulation, il devient alors possible de sélectionner les niveaux permettant d'atteindre le meilleur compromis entre la qualité des résultats produits par la simulation et les performances de calculs pour obtenir ces résultats. Les modèles présentés dans ce mémoire ont été appliqués à la simulation de foule et de trafic dans le cadre de contrats de recherche dont certains sont abordés dans ce document : simulation du réseau urbain de bus de Belfort, simulation de foules dans un centre ville de Belfort, simulation du covoiturage dans les Flandres.

This thesis addresses the problem of positional consensus of multi-agent systems. A positional consensus is achieved when the agents converge to a point. Some applications of this class of problem is in mid-air refueling of the aircraft or UAVs, targeting a geographical location, etc. In this research work some positional consensus algorithms have been developed. They can be categorized in two part (i) Broadcast control based algorithm (ii) Distributed control based algorithm. In case of broadcast based algorithm control strategies for a group of agents is developed to achieve positional consensus. The problem is constrained by the requirement that every agent must be given the same control input through a broadcast communication mechanism. Although the control command is computed using state information in a global framework, the control input is implemented by the agents in a local coordinate frame. The mathematical formulation has been done in a linear programming framework that is computationally less intensive than earlier proposed methods. Moreover, a random perturbation input in the control command, that helps to achieve reasonable proximity among agents even for a large number of agents, which was not possible with the existing strategy in the literature, is introduced. This method is extended to achieve positional consensus at a pre-specified location. A comparison between the LP approach and the existing SOCP based approach is also presented. Some of the algorithm has been demonstrated successfully on a robotic platform made from LEGO Mindstorms NXT Robots. In the second case of broadcast based algorithm, a decentralized algorithm for a group of multiple autonomous agents to achieve positional consensus has been developed using the broadcast concept. Even here, the mathematical formulation has done using a linear programming framework. Each agent has some sensing radius and it is capable of sensing position and orientation with other agents within their sensing region. The method is computationally feasible and easy to implement. In case of distributed algorithms, a computationally efficient distributed rendezvous algorithm for a group of autonomous agents has been developed. The algorithm uses a rectilinear decision domain (RDD), as against the circular decision domain assumed in earlier work available in the literature. This helps in reducing its computational complexity considerably. An extensive mathematical analysis has been carried out to prove the convergence of the algorithm. The algorithm has also been demonstrated successfully on a robotic platform made from LEGO Mindstorms NXT Robots.

Este trabalho apresenta um modelo de acompanhamento e atendimento de pacientes crônicos baseado nos conceitos de relacionamento de clientes utilizados nas empresas, mais especificamente aqueles presentes na tecnologia CRM (Customer Relationship Management). A esse modelo denominou-se Gestão do Relacionamento com o Paciente Crônico (GRPC). A tecnologia CRM é uma estratégia com ferramentas para implementar um programa de relacionamento e fidelidade entre o cliente/consumidor e o fornecedor. O modelo GRPC, ao utilizar o conceito de CRM no atendimento ao paciente, apresenta uma estratégia de acompanhamento e monitoramento de pacientes crônicos diferente da abordagem tradicional, muitas vezes baseada somente no tratamento da doença. Da mesma forma que o CRM consegue atingir os clientes dos mais variados níveis através dos seus canais de comunicação, neste modelo propõe-se utilizar a mesma tecnologia a fim de garantir um acompanhamento efetivo e adequado a todas as camadas populacionais. Para implementar o modelo GRPC propõe-se a criação de centrais de relacionamento de pacientes crônicos, que compõem a infra-estrutura do modelo ao combinar, de maneira adequada, a troca de informações, as campanhas, a transmissão e o processamento de dados, com a finalidade de melhorar o relacionamento com o paciente, através da tecnologia de telefonia e computação. Para uma avaliação preliminar do modelo, elaborou-se uma central de monitoração de pacientes diabéticos e desenvolveu-se um sistema de monitoração para diabéticos. A modelagem da central de monitoração foi feita utilizando-se a extensão da UML para a modelagem de negócio, o que permitiu analisar a abrangência do modelo. O sistema de monitoração, denominado TeleDM, foi desenvolvido visando a realizar as simulações necessárias para os estudos desse trabalho. A partir da modelagem de negócio elaboraram-se os modelos para o desenvolvimento do sistema. Após a avaliação de suas características optou-se por implementá-lo utilizando a tecnologia de orientação a agentes e objetos, o que permitiu verificar que tal combinação é adequada na solução de sistemas complexos com as características do sistema TeleDM. / This paper shows a chronic patient follow-up and attendance model based on the concepts of customers’ relationship used in the companies, mainly those existent in CRM technology (Customer Relationship Management). The model was designated as Chronic Patient Relationship Management (CPRM). The CRM technology is a strategy with tools to implement a relationship and fidelity program between the client / customer and the supplier. The CPRM model, by using the CRM concept on patient attendance, presents a strategy to follow-up and monitoring the chronic patient different from the usual traditional approach, which many times only consists in illness treatment. In the same way as the CRM, this model is able to reach clients of every condition through its communication channels; and suggests the use of the same technology in order to guarantee an effective and suitable follow-up for all social layers. To implement the CPRM model, the creation of relationship centers for chronic patients, thus building the model’s infrastructure when properly connecting the information exchange, campaigns, and data processing and transmitting, for the purpose of improving the relationship with the patient through telephone and computing technology. For a preliminary assessment of the model, a monitoring center was elaborated for diabetic patients, as well as a system for diabetes monitoring. The modeling of the center was done using the UML extension for business modeling, which allowed analyzing the model’s coverage. The monitoring system known, as TeleDM was developed to execute the simulations needed for this work’s studies. The models for the system’s development were elaborated from the business modeling. After evaluating its features, the choice was implementing it with agent and object-oriented technology, thus allowing checking this combination suitability for complex systems solution with the TeleDM system features.

Submitted by Maicon Juliano Schmidt (maicons) on 2015-07-09T14:56:04Z No. of bitstreams: 1 Luiz Rodrigo Jardim da Silva.pdf: 2565431 bytes, checksum: 6a2df89b794e9afe09546769e43ef4e9 (MD5) / Made available in DSpace on 2015-07-09T14:56:04Z (GMT). No. of bitstreams: 1 Luiz Rodrigo Jardim da Silva.pdf: 2565431 bytes, checksum: 6a2df89b794e9afe09546769e43ef4e9 (MD5) Previous issue date: 2013-01-31 / CAPES - Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / Problemas relacionados à heterogeneidade semântica vêm se mostrando atualmente como um importante campo de pesquisa. Dentro do contexto educacional, pesquisadores têm se dedicado ao desenvolvimento de novas tecnologias que visam melhorar os processos de localização, recuperação, catalogação, e reutilização de objetos de aprendizagem. Baseado neste cenário, destaca-se o uso de técnicas de alinhamento de ontologias para prover integração entre ontologias distintas. Assim, o objetivo deste trabalho é desenvolver uma ferramenta que forneça mecanismos de busca semântica de objetos de aprendizagem com suporte a alinhamento automático de ontologias. / Semantics heterogeneity problems are becoming an important field of research. Within the educational context, researchers have focused on developing new technologies to improve the processes of localization, retrieval, cataloging, and reuse of learning objects. This scenario highlights the use of ontology alignment techniques to provide integration between different ontologies. Therefore, the goal of the present work is to develop a tool that provides mechanisms for semantic search of learning objects, with support for automatic aligning ontologies.