Through the use of rapid prototyping it is possible to move directly from a computer design to a nal physical product without human intervention. Telemanufacturing is an extension to rapid prototyping that presents a data communications based interface to rapid prototyping. Resource negotiating agents are able to provide a completely autonomous negotiation process. By integrating resource negotiating agents into a telemanufacturing environment, an opportunity for a completely automated supply chain is presented. / Prof. E.M. Ehlers

Current syndromic surveillance systems utilize centralized databases that are neither scalable in storage space nor in computing power. Such systems are limited in the amount of syndromic data that may be collected and analyzed for the early detection of infectious disease outbreaks. However, with the increased prevalence of international travel, public health monitoring must extend beyond the borders of municipalities or states which will require the ability to store vasts amount of data and significant computing power for analyzing the data. Intelligent mobile agents may be used to create a distributed surveillance system that will utilize the hard drives and computer processing unit (CPU) power of the hosts on the agent network where the syndromic information is located. This thesis proposes the design of a mobile agent-based syndromic surveillance system and an agent decision model for outbreak detection. Simulation results indicate that mobile agents are capable of detecting an outbreak that occurs at all hosts the agent is monitoring. Further study of agent decision models is required to account for localized epidemics and variable agent movement rates.

The increasingly popular cloud-computing paradigm provides on-demand access to computing and storage with the appearance of unlimited resources. Users are given access to a variety of data and software utilities to manage their work. Users rent virtual resources and pay for only what they use. In spite of the many benefits that cloud computing promises, the lack of dependability in shared virtualized infrastructures is a major obstacle for its wider adoption, especially for mission-critical applications. Virtualization and multi-tenancy increase system complexity and dynamicity. They introduce new sources of failure degrading the dependability of cloud computing systems. To assure cloud dependability, in my dissertation research, I develop autonomic failure identification and diagnosis techniques that are crucial for understanding emergent, cloud-wide phenomena and self-managing resource burdens for cloud availability and productivity enhancement. We study the runtime cloud performance data collected from a cloud test-bed and by using traces from production cloud systems. We define cloud signatures including those metrics that are most relevant to failure instances. We exploit profiled cloud performance data in both time and frequency domain to identify anomalous cloud behaviors and leverage cloud metric subspace analysis to automate the diagnosis of observed failures. We implement a prototype of the anomaly identification system and conduct the experiments in an on-campus cloud computing test-bed and by using the Google datacenter traces. Our experimental results show that our proposed anomaly detection mechanism can achieve 93% detection sensitivity while keeping the false positive rate as low as 6.1% and outperform other tested anomaly detection schemes. In addition, the anomaly detector adapts itself by recursively learning from these newly verified detection results to refine future detection.

No description available.

Thesis (MScEng)--Stellenbosch University, 2013. / ENGLISH ABSTRACT: The thesis evaluates control strategies for reconfigurable manufacturing systems by using a welding assembly cell as a case study. The cell consists of a pallet magazine, conveyor, feeder subsystem (comprising an articulated robot and singulation unit), welder subsystem (which uses a modular Cartesian robot), and inspection and removal subsystems. The research focuses on control strategies that enhance reconfigurability in terms of structure, hardware and software using agent-based control and the IEC 61499 standard, based on PC control. Reconfiguration may occur when a new product is introduced, as well as when a new subsystem is introduced or removed from the production cell. The overall control architecture is that the subsystems retain no knowledge of the product, but product information resides in the cell controller, while services offered by the subsystems are registered with the directory facilitator of the Java agent platform. The control strategies are implemented on the modular Cartesian weld robot and the cell controller for assembly cell. A layered architecture with low-level control and high-level control is used to allow separation of concerns and rapid changes in both hardware and software components. The low-level control responds in hard real-time to internal and external events, while the high-level control handles soft real-time actions involving coordination of control related issues. The results showed IEC 61499 function blocks to be better suited to low-level control application in distributed systems, while agents are more suited for high-level control. Modularity in software components enhances hardware and software scalability. Additionally, agents can support online reconfiguration of reconfigurable machines. / AFRIKAANSE OPSOMMING: Die tesis evalueer beheerstrategieë vir herkonfigureerbare vervaardigingstelsels deur gebruik te maak van ’n sweismonteersel as ’n gevallestudie. Die sel bestaan uit ’n palletmagasyn, vervoerbande, voersubstelsel (bestaande uit ’n geartikuleerde robot en singulasie-eenheid), sweissubstelsel (wat gebruik maak van ’n modulêre Cartesiese robot), en inspeksie- en verwyderingsubstelsels. Die navorsing fokus op beheerstrategieë wat herkonfigureerbaarheid verhoog in terme van struktuur, hardeware en sagteware met behulp van agent-gebaseerde beheer en die IEC 61499 standaard, wat gebaseer is op PC-beheer. Herkonfigurasie mag voorkom wanneer ’n nuwe produk in-gestel word, sowel as wanneeer ’n nuwe substelsel bygevoeg of verwyder word van die produksiesel. Die oorhoofse beheerargitektuur is dat die substelsels geen kennis van die produk hou nie, maar die produkinligting in die selbeheerder geberg, terwyl dienste wat aangebied word deur die substelsels wat geregistreer is by die gidsfasiliteerder van die Java agent platform. Die beheerstrategië is geïmplementeer op die modulere Cartesiese sweisrobot en die selbeheerder vir die monteersel. ’n Gelaagde argitektuur met ’n lae-vlak beheer en hoë-vlak beheer word gebruik om skeiding van oorwegings en vinnige veranderinge in beide hardeware en sagteware komponente toe te laat. Die lae-vlak beheer reageer hard intyds op interne en eksterne gebeure, terwyl die hoë-vlak beheer sag intyds die koördinering van beheerverwante kwessies hanteer. Die resultate het getoon dat IEC 61499 funksie-blokke beter geskik is vir lae-vlak beheer toepassing in verspreide stelsels, terwyl agente meer geskik is vir hoë-vlak beheer. Modulariteit in sagteware komponente verhoog hardeware en sagteware skaleerbaarheid. Boonop kan agente ook aanlyn herkonfigurasie van herkonfigureerbare masjiene ondersteun.

Esta tese propõe o desenvolvimento de SMAs centrados em organizações de forma disciplinada, mesmo nos casos em que os modelos organizacionais de agentes utilizados não estejam incorporados aos métodos oferecidos pela Engenharia de Software Orientada a Agentes (AOSE). A fim de atingir tal objetivo, esta tese adota os princípios da Engenharia de Método Situational e propõe o Ateliê Medee, que permite a composição de métodos situacionais para SMAs usando fragmentos de método adequados à situação de cada projeto. Este ateliê oferece um repositório de fragmentos de método que contempla distintas fases de desenvolvimento de um projeto, tais como elucidação de requisitos, análise, design, e implementação, envolvendo os principais componentes de um SMA, como agentes, ambientes, interações e organizações. Tal repositório contém fragmentos extraídos de diversas abordagens para o desenvolvimento de SMAs, entre elas os métodos Gaia, Tropos, Ingenias, PASSI, e os modelos organizacionais MOISE+ e OperA. Além disso, esta tese mostra como tais métodos situationais podem contribuir no estabelecimento de um ciclo de melhoria do método de desenvolvimento para SMAs. Este ciclo aplica os princípios da Engenharia de Software a fim de prover um procedimento empírico para a adaptação, avaliação e melhoria de métodos situacionais para o desenvolvimento de SMAs centrados em organizações. Dessa forma, este ciclo contribui para uma utilização mais ampla de aplicações orientadas a agentes pela indústria.de software. Finalmente, esta tese apresenta um estudo de caso conduzido para investigar o uso do Ateliê Medee na composição de métodos situacionais para SMAs. Este estudo de caso envolveu o desenvolvimento de SMAs centrados em organizações para resolver o problema proposto pelo Torneio de Programação Multiagentes usando dois métodos situacionais distintos, compostos a partir de fragmentos de método extraídos de Tropos, Gaia e MOISE+. / This thesis proposes the development of organization centered MAS in a disciplined way, even though some agent organizational models are not currently incorporated into AOSE methods. In order to do that, this thesis proposes the Medee Framework for composing MAS situational methods out of method fragments according to a given project situation, by applying the principles proposed by Situational Method Engineering. Thus, it offers a method fragment repository that covers different development phases, like requirements, analysis, design, implementation, as well as the main components of a MAS application, such as agents, environments, interactions, and organizations. Such a repository has been sourced from several MAS development approaches, as such Gaia, Tropos, Ingenias, PASSI, MOISE, and OperA. Furthermore, this doctoral dissertation shows how such MAS situational methods could contribute to establish a method improvement cycle. Such a cycle applies principles of the Software Engineering discipline to provide an empirical procedure for tailoring, evaluating, and enhancing MAS situational methods. In this way, this cycle allows the continuous improvement of the Medee Method Repository, towards a steady and well founded path for MAS method maturation and, consequently, for a broader utilization of agent-oriented software development in the software industry. Finally, this dissertation presents a case study conducted to investigate the use of the Medee Framework for composing MAS situational methods, sourced mainly from Tropos, Gaia, and MOISE+. Moreover, these situational methods were used within an improvement cycle for MAS development methods. This case study, called the USP Farmer project, involved the development of organization centered MAS to solve the problem proposed by the Multiagent Programming Contest.

Made available in DSpace on 2016-04-29T14:23:42Z (GMT). No. of bitstreams: 1 Daniel Henrique da Silva.pdf: 3074984 bytes, checksum: 8157750ada0d1efd84ba9e3c3b73b64a (MD5) Previous issue date: 2015-12-11 / This research proposes a software architecture to the development of a tool for narrative scripts generation that follows the OCC-RDD technique. It is supposing that the choice of intelligent agents is adequate for this purpose, because of the diversity of inputs that make up a narrative script is propitious for artificial intelligence. In order to support the selection of the proposed architecture, a detailed study about OCC-RDD technique was made, followed by the use of a specific methodology for intelligent agents named TROPOS, in the analysis and solution design. There was also studies about theories and architectural styles suitable for software agents, as well as foundations and practices of software systems in general. The details of software architecture were designed with a prototype able to generate simple scripts which served to demonstrate the feasibility of the implementation. Some aspects of the text generation have been achieved by using a markup language built especially for this architecture. This language played the role of defining static text template in which intelligent agents consume to assemble the narrative script / A pesquisa propõe uma arquitetura de software para desenvolver uma ferramenta de geração de roteiros narrativos orientados a técnica OCC-RDD. Agentes inteligentes fo- ram escolhidos pela proximidade da área de estudo denomidada inteligência artificial que engloba a geração de roteiros narrativos. Para fundamentar a escolha da arquitetura pro- posta, foram feitos estudos detalhados sobre a técnica OCC-RDD, juntamente com o uso de uma metodologia específica para agentes inteligentes denominada TROPOS nas eta- pas de análise e de desenho da solução. Houve também estudos de teorias e de estilos arquiteturais apropriados para agentes, além de fundamentos e práticas de sistemas de software em geral. O detalhamento da arquitetura de software foi concebido junto com um protótipo capaz de gerar roteiros simples e que serviu para demonstrar a viabilidade da implementação. Alguns aspectos de geração de textos foram alcançados utilizando uma linguagem de marcação construída especialmente para esta arquitetura. Tal linguagem teve o papel importante de servir como uma definição de templates de texto estáticos no qual os agentes inteligentes a utilizam para montar o roteiro narrativo

One of the hardest challenges in the field of machine learning is to build agents, such as robotic assistants in homes and hospitals, that can autonomously learn new tasks that they were not pre-programmed to tackle, without the intervention of an engineer. Reinforcement learning (RL) and learning from demonstration (LfD) are popular approaches for task learning, but they are often ineffective in high-dimensional domains unless provided with either a great deal of problem-specific domain information or a carefully crafted representation of the state and dynamics of the world. Unfortunately, autonomous agents trying to learn new tasks usually do not have access to such domain information nor to an appropriate representation. We demonstrate that algorithms that focus, at each moment, on the relevant features of the state space can achieve significant speed-ups over previous reinforcement learning algorithms with respect to the number of state features in complex domains. To do so, we introduce and evaluate a family of attention focus algorithms. We show that these algorithms can reduce the dimensionality of complex domains, creating a compact representation of the state space with which satisficing policies can be learned efficiently. Our approach obtains exponential speed-ups with respect to the number of features considered when compared with table-based learning algorithms and polynomial speed-ups when compared with state-of-the-art function approximation RL algorithms such as LSPI or fitted Q-learning. Our attention focus algorithms are divided in two classes, depending on the source of the focus information they require. Attention focus from human demonstrations infers the features to focus on from a set of demonstrations from human teachers performing the task the agent must learn. We introduce two algorithms within this class. The first one, abstraction from demonstration (AfD), identifies features that can be safely ignored in the whole state space and builds a state-space abstraction where a satisficing policy can be learned efficiently. The second, automatic decomposition and abstraction from demonstration, goes one step further, using the demonstrations to identify a set of subtasks and to find an appropriate abstraction for each subtask found. The other class of algorithms we present, attention focus with a world model, does not require a set of human demonstrations. Instead, it extracts the attention focus information from an object-based model of the world together with the agent experience in performing the task. Within this class, we introduce object-focused Q-learning (OF-Q), at first with an assumption of object independence that is later removed to support domains where objects interact with each other. Finally, we show that both sources of focus information can be combined for further speed-ups.

Changes in work, along with improvements in techniques to statistically model uncertainty, have resulted in a class of groupware tools able to forecast the activities and/or attentional state of their users. This thesis represents an exploration into the design, development, and use of one such system. I describe the design and development of a groupware calendar system called Augur that is augmented with the ability to predict the attendance of its users. Using Bayesian networks, Augur models the uncertain problem of event attendance, drawing inferences based on the attributes of calendar events as well as a history of attendance provided by each user. This system was deployed to an academic workgroup and studied over the course of a semester. To more deeply explore the social implications of Augur and systems like it, I conducted a structured privacy analysis of Augur to examine the vulnerabilities inherent in this type of forecasting groupware system. I present an architecture, user interface, and probabilistic model for Augur. This work also addresses the feasibility of such a system and the challenges faced when deploying it to an academic workgroup. I also report on an exploration of the systems use by individuals, its effects on communication within working relationships, and its effectiveness with respect to the presence of domestic calendars. Finally, I present a set of implications for the workplace social environment with the introduction of Augur. Specifically, I show how the integrity of predictions generated by Augur can have consequences for the privacy of users and their representations through the shared calendar. Overall, this thesis is presented as an early exploration into the potential for a new class of forecasting groupware applications. It offers guidance and lessons learned for both designers and researchers seeking to work in this area. It also presents a complete calendar application as an example for building and studying such systems.

As the amount of accessible and shareable knowledge increases, it is figured out that learning platforms offering the same context and learning path to all users can not meet the demands of learners. This issue brings out the necessity of designing and developing adaptive hypermedia systems. This study describes an agent-based adaptive learning framework whose goal is to implement effective tutoring system with the help of Artificial Intelligence (AI) techniques and cognitive didactic methods into Adaptive Educational Hypermedia Systems (AEHS) in the domain of Unified Modeling Language (UML). There are three main goals of this study. First goal is to explore how supportive agents affect student&rsquo / s learning achievement in distance learning. Second goal is to examine the interaction between supportive agents and learners with the help of experiments in Human Computer Interaction laboratories and system analysis. The effects of the methodology that agents give misleading hints which are common mistakes of other learners are also investigated. Last goal is to deliver effective feedback to students both from IAs and tutors. In order to assess that UML-ALF has accomplished its objectives, we followed an experimental procedure. Experimental groups have taken the advantage of adaptive and intelligent techniques of the UML-ALF and control groups have used the traditional learning techniques. The results show that there is a positive correlation between variables practice score and number of agent suggestion which means, as the participants benefit from supportive agents, they get higher scores.