Siga este enlace para ver otros tipos de publicaciones sobre el tema: Distributed artificial intelligence (DAI).
Tesis sobre el tema "Distributed artificial intelligence (DAI)"
Crea una cita precisa en los estilos APA, MLA, Chicago, Harvard y otros
Consulte los 50 mejores tesis para su investigación sobre el tema "Distributed artificial intelligence (DAI)".
Junto a cada fuente en la lista de referencias hay un botón "Agregar a la bibliografía". Pulsa este botón, y generaremos automáticamente la referencia bibliográfica para la obra elegida en el estilo de cita que necesites: APA, MLA, Harvard, Vancouver, Chicago, etc.
También puede descargar el texto completo de la publicación académica en formato pdf y leer en línea su resumen siempre que esté disponible en los metadatos.
Explore tesis sobre una amplia variedad de disciplinas y organice su bibliografía correctamente.
1
Adolfsson, Victor. "The State of the Art in Distributed Mobile Robotics". Thesis, Blekinge Tekniska Högskola, Institutionen för programvaruteknik och datavetenskap, 2001. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-6195.
Texto completoResumen
Distributed Mobile Robotics (DMR) is a multidisciplinary research area with many open research questions. This is a survey of the state of the art in Distributed Mobile Robotics research. DMR is sometimes referred to as cooperative robotics or multi-robotic systems. DMR is about how multiple robots can cooperate to achieve goals and complete tasks better than single robot systems. It covers architectures, communication, learning, exploration and many other areas presented in this master thesis.Uppsatsen är en brett spektrum på vilken forskning som pågår rörande distribuerad mobil robotik, dvs hur många robotar kan samverka för att lösa uppgifter.
Adress: Victor Adolfsson Folkparksvägen 12:24 372 38 Ronneby Telefon: 0457-171 42 Mobil: 0709-441389
2
Sian, Satwinder Singh. "Learning in distributed artificial intelligence systems". Thesis, Imperial College London, 1991. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.282757.
Texto completo
3
Rampal, Gaurav S. "Developing mobile distributed intelligent network services using RM-ODP". Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1998. http://www.collectionscanada.ca/obj/s4/f2/dsk2/ftp01/MQ32556.pdf.
Texto completo
4
Lucouw, Alexander. "Distributed fault detection and diagnostics using artificial intelligence techniques / A. Lucouw". Thesis, North-West University, 2009. http://hdl.handle.net/10394/4110.
Texto completoResumen
With the advancement of automated control systems in the past few years, the focus
has also been moved to safer, more reliable systems with less harmful effects on the
environment. With increased job mobility, less experienced operators could cause more
damage by incorrect identification and handling of plant faults, often causing faults to
progress to failures. The development of an automated fault detection and diagnostic
system can reduce the number of failures by assisting the operator in making correct
decisions. By providing information such as fault type, fault severity, fault location
and cause of the fault, it is possible to do scheduled maintenance of small faults rather
than unscheduled maintenance of large faults.
Different fault detection and diagnostic systems have been researched and the best
system chosen for implementation as a distributed fault detection and diagnostic
architecture. The aim of the research is to develop a distributed fault detection and
diagnostic system. Smaller building blocks are used instead of a single system that
attempts to detect and diagnose all the faults in the plant.
The phases that the research follows includes an in-depth literature study followed by
the creation of a simplified fault detection and diagnostic system. When all the aspects
concerning the simple model are identified and addressed, an advanced fault detection
and diagnostic system is created followed by an implementation of the fault detection
and diagnostic system on a physical system.Thesis (M.Ing. (Computer and Electronic Engineering))--North-West University, Potchefstroom Campus, 2009.
5
Li, Xiao-Dong Carleton University Dissertation Engineering Electrical. "DISC: a framework for coordination in a distributed artificial intelligence system". Ottawa, 1992.
Buscar texto completo
6
Wei, Jin. "Modeling and Coordination of interconnected microgrids using distributed artificial intelligence approaches". Thesis, Bourgogne Franche-Comté, 2019. http://www.theses.fr/2019UBFCA021.
Texto completoResumen
À mesure que les sources renouvelables pénètrent dans le système électrique actuel pour atténuer le réchauffement planétaire et la pénurie d’énergie, le concept de microréseau (MG) permet de réduire l’impact de la production intermittente sur le réseau de services publics. Il permet d'améliorer l’automatisation et l’intelligence du réseau électrique avec des caractéristiques plug-and-play. L’intégration d’un plus grand nombre de MG dans un réseau de distribution favorise le développement du réseau intelligent. Leur coordination pourrait conduire à une grande fiabilité du système avec un faible coût, et une forte résistance aux pannes électriques. La réalisation de ces profits repose sur des technologies développées de communication et de stratégies de contrôle.La répartition de la puissance dans les MG répartis tout en coordonnant les éléments au sein de chaque MG exige un contrôle décentralisé. L'approche multiagent permet de modéliser un réseau de MG comme un système physiquement distribué. Cette thèse étudie principalement le contrôle de coordination dans le réseau MG et sa modélisation à base d'agent.. L' objectif est de promouvoir la performance des contrôles en termes d’efficacité et de fiabilité. Deux méthodes sont envisagées pour permettre l’évolutivité du système, y compris la coordination avec les MG voisins et dans la zone de coordination étendue. Une plateforme de simulation est établie pour valider les approches proposées.Les stratégies de contrôle pour la coordination entre les MG et leurs voisins sont proposées afin de maintenir la charge complète et la sécurité tout en minimisant le coût de production. Le contrôle centralisé dans le groupe de coordination est appliqué à la gestion économique de l’énergie. Il utilise une méthode de Newton-Raphson pour répartir la puissance entre les MG voisins en simplifiant la relation entre le coût de production de MG et sa puissance de sortie. Une approche fondée sur le consensus est adoptée pour calculer le flux de puissance du réseau, et les résultats sont comparés avec la capacité maximale sur la ligne pour assurer un fonctionnement sûr. Pour améliorer encore les avantages économiques, l’approximation de la relation entre la puissance de production de MG et le coût de production est améliorée par une autre stratégie fondée sur la notion de marché. Il construit un marché pour le commerce d’électricité avec les voisins. Cette méthode préserve la vie privée de chaque MG. Le calcul du débit de puissance est simplifié pour être proportionnel à la différence d’angle entre les deux extrémités de la ligne de raccordement. Les deux stratégies sont testées sur plusieurs réseaux MG. Leur performance montre que les deux approches sont évolutives et pourraient économiquement compenser le manque d’approvisionnement en charge dans les MG défectueux.Pour la stratégie de contrôle avec une fiabilité et un profit plus élevés, une stratégie de coordination au sein d’une vaste zone sélectionnée de MG est proposée. L’élargissement de la zone de coordination en fonction des MG voisins fournit plus de sources d’énergie au MG. Il assure suffisamment de puissance pour compenser le déséquilibre et offre plus de choix pour la distribution de puissance. La sélection de la zone de coordination est réalisée par un algorithme évolutionnaire distribué. La programmation quadratique dans Gurobi est utilisée pour résoudre le problème de répartition de puissance. Un autre algorithme génétique est également adopté pour résoudre le problème de la répartition optimale de la puissance avec un coût de production quadratique pour la microturbine. La performance de cette stratégie est testée, et les résultats montrent qu’elle a des avantages en termes de fiabilité, d'évolutivité et de profit par rapport aux méthodes centraliséesAs renewable sources penetrate the current electrical system to relief global warming and energy shortage, microgrid (MG) emerges to reduce the impact of intermittent generation on the utility grid. Additionally, it improves the automation and intelligence of the power grid with plug-and-play characteristics. Inserting more MGs into a distribution network promotes the development of the smart grid. Thus MG networks existing in the power system are in prospect. Coordinating them could gain a system with high reliability, low cost, and strong resistance to electrical faults. Achieving these profits relies on developed technologies of communication, control strategy, and corresponding algorithms.Dispatching power in distributed MGs while coordinating elements within the individual MG demands a decentralized control system, in which the multi-agent system possesses advantages. It is applied to the MG network for establishing a physically distributed system. Based on the multi-agent system, this thesis mainly studies the coordination control in the MG network and its modeling. It aims at promoting control performance in terms of efficiency, reliability, economic benefit, and scalability. Two methods are considered to enable the system scalability, including the coordination with neighboring MGs and within the extensive coordinating area. A simulation platform is established to validate the proposed approaches.The control strategies for coordination between MGs and their neighbors are proposed to maintain the complete load supply and global security operation while minimizing the generation cost. Centralized control in the coordination group is applied for economic energy management. It uses a Newton-Raphson method to dispatch power among neighboring MGs by simplifying the relationship between MG generation cost and its output power. An average consensus approach is adopted to calculate the caused network power flow, and the results are compared with the maximal capacity on the line to keep safe operation. To further improve the economic benefits, the approximation of the relationship between MG output power and the caused generation cost is improved by an another strategy based on the market concept. It builds a market for neighboring power trade. This method maintains the operation privacy of individual MG. Power flow calculation is simplified to be proportional to the angle difference between the two terminates of the connecting line. Both strategies are tested on several MG network. Their performance shows that both approaches possess scalability and could economically compensate for the lack of load supply in faulted MG.For the control strategy with higher reliability and profit, a coordination strategy within a selected extensive area of MGs is proposed. Expanding the coordination area based on neighboring MGs provides more energy sources to the demanded MG. It ensures enough power to compensate imbalance and offers more choices for power dispatching. The selection of the coordination area is based on a distributed evolutionary algorithm. Quadratic programming in Gurobi is used to solve the power dispatching problem. Another genetic algorithm is also adopted to solve the problem of optimal power dispatching with a quadratic generation cost for microturbine. The performance of this strategy is tested, and the results show that it has comprehensive advantages on reliability, scalability, and profit compared with centralized methods
7
Goel, Anuj. "Symbolic model checking techniques for BDD-based planning in distributed environments". Full text (PDF) from UMI/Dissertation Abstracts International, 2002. http://wwwlib.umi.com/cr/utexas/fullcit?p3077646.
Texto completo
8
Ling, Nai Man. "The application of artificial intelligence and distributed control to a robotic workcell /". Thesis, McGill University, 1989. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=55617.
Texto completo
9
Wallace, Andrew Alexander. "Application of distributed artificial intelligence to the flow control of mobile robots". Thesis, Open University, 2002. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.395248.
Texto completo
10
Khoui, Hooman. "Investigations into distributed artificial intelligence techniques for design with applications to instruments". Thesis, City University London, 1995. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.283157.
Texto completo
11
Wagy, Mark David. "Enabling Machine Science through Distributed Human Computing". ScholarWorks @ UVM, 2016. http://scholarworks.uvm.edu/graddis/618.
Texto completoResumen
Distributed human computing techniques have been shown to be effective ways of accessing the problem-solving capabilities of a large group of anonymous individuals over the World Wide Web. They have been successfully applied to such diverse domains as computer security, biology and astronomy. The success of distributed human computing in various domains suggests that it can be utilized for complex collaborative problem solving. Thus it could be used for "machine science": utilizing machines to facilitate the vetting of disparate human hypotheses for solving scientific and engineering problems.
In this thesis, we show that machine science is possible through distributed human computing methods for some tasks. By enabling anonymous individuals to collaborate in a way that parallels the scientific method -- suggesting hypotheses, testing and then communicating them for vetting by other participants -- we demonstrate that a crowd can together define robot control strategies, design robot morphologies capable of fast-forward locomotion and contribute features to machine learning models for residential electric energy usage. We also introduce a new methodology for empowering a fully automated robot design system by seeding it with intuitions distilled from the crowd.
Our findings suggest that increasingly large, diverse and complex collaborations that combine people and machines in the right way may enable problem solving in a wide range of fields.
12
Shi, Shaohuai. "Communication optimizations for distributed deep learning". HKBU Institutional Repository, 2020. https://repository.hkbu.edu.hk/etd_oa/813.
Texto completoResumen
With the increasing amount of data and the growing computing power, deep learning techniques using deep neural networks (DNNs) have been successfully applied in many practical artificial intelligence applications. The mini-batch stochastic gradient descent (SGD) algorithm and its variants are the most widely used algorithms in training deep models. The SGD algorithm is an iterative algorithm that needs to update the model parameters many times by traversing the training data, which is very time-consuming even using the single powerful GPU or TPU. Therefore, it becomes a common practice to exploit multiple processors (e.g., GPUs or TPUs) to accelerate the training process using distributed SGD. However, the iterative nature of distributed SGD requires multiple processors to iteratively communicate with each other to collaboratively update the model parameters. The intensive communication cost easily becomes the system bottleneck and limits the system scalability. In this thesis, we study the communication-efficient techniques for distributed SGD to improve the system scalability and thus accelerate the training process. We identify the performance issues in distributed SGD through benchmarking and modeling and then propose several communication optimization algorithms to address the communication issues. First, we build a performance model with a directed acyclic graph (DAG) to modeling the training process of distributed SGD and verify the model with extensive benchmarks on existing state-of-the-art deep learning frameworks including Caffe, MXNet, TensorFlow, and CNTK. Our benchmarking and modeling point out that existing optimizations for the communication problems are sub-optimal, which we need to address in this thesis. Second, to address the startup problem (due to the high latency of each communication) of layer-wise communications with wait-free backpropagation (WFBP), we propose an optimal gradient merging solution for WFBP, named MG-WFBP, that exploits the layer-wise property to well overlap the communication tasks with the computing tasks and can be adaptive to the training environments. Experiments are conducted on dense-GPU clusters with Ethernet and InfiniBand, and the results show that MG-WFBP can well address the startup problem in distributed training of layer-wise structured DNNs. Third, to make the high computing-intensive training tasks be possible in GPU clusters with low- bandwidth interconnect, we investigate the gradient compression techniques in distributed training. The top-{dollar}k{dollar} sparsification can well compress the communication traffic with little impact on the model convergence, but it suffers from a linear communication complexity to the number of workers so that top-{dollar}k{dollar} sparsification cannot scale well in large-scale clusters. To address the problem, we propose a global top-{dollar}k{dollar} (gTop-{dollar}k{dollar}) sparsification algorithm that reduces the communication complexity to be logarithmic to the number of workers. We also provide detailed theoretical analysis for the gTop-{dollar}k{dollar} SGD training algorithm, and the theoretical results show that our gTop-{dollar}k{dollar} SGD has the same order of convergence rate with SGD. Experiments are conducted on up to 64-GPU cluster to verify that gTop-{dollar}k{dollar} SGD significantly improves the system scalability with only a slight impact on the model convergence. Lastly, to enjoy the both benefits of the pipelining technique and the gradient sparsification algorithm, we propose a new distributed training algorithm, layer-wise adaptive gradient sparsification SGD (LAGS-SGD), which supports layer-wise sparsification and communication, and we theoretically and empirically prove that the LAGS-SGD preserves the convergence properties. To further alliterate the impact of the startup problem of layer-wise communications in LAGS-SGD, we also propose the optimal gradient merging solution for LAGS-SGD, named OMGS-SGD, and theoretical prove its optimality. The experimental results on a 16-node GPU cluster connected 1Gbps Ethernet show that OMGS-SGD can always improve the system scalability while the model convergence properties are not affected
13
Kassabalidis, Ioannis N. "Applications of biologically inspired algorithms to complex systems /". Thesis, Connect to this title online; UW restricted, 2002. http://hdl.handle.net/1773/5915.
Texto completo
14
Bianchi, Reinaldo Augusto da Costa. "Uma arquitetura de controle distribuída para um sistema de visão computacional propositada". Universidade de São Paulo, 1998. http://www.teses.usp.br/teses/disponiveis/3/3142/tde-10122004-222058/.
Texto completoResumen
Esta dissertação apresenta uma arquitetura de controle distribuída para um sistema de visão computacional propositada, modelada segundo uma abordagem de Inteligência Artificial Distribuída com ênfase em Sistemas Multi-Agentes. O principal problema abordado é o da integração de diversos módulos com tarefas e comportamentos diferentes em um sistema robótico, que utiliza visão computacional para perceber o mundo. Esta integração surge da organização de diversas soluções dedicadas a diferentes tarefas visuais, resultando na proposta de uma arquitetura constituída por uma sociedade de Agentes Autônomos (AAs), que comunicam entre si através de uma rede de comunicação descentralizada e totalmente conectada, sendo cada AA responsável por um comportamento independente, organizados segundo regras de comportamento e uma estrutura de autoridade. Essa arquitetura integra diversos módulos da cognição, como percepção visual, planejamento, controle e atuação. Como tentativa de validação experimental da proposta, essa arquitetura foi implementada em um sistema dotado de um manipulador robótico e uma câmera, trabalhando em um domínio de montagem. A estrutura básica da arquitetura foi desenvolvida segundo uma metodologia de projeto orientada a objetos e consiste em uma biblioteca de classes que definem o modelo dos agentes e as estruturas para as interações entre esses em uma sociedade. O sistema robótico proposto foi implementado na Célula Flexível de Montagem da Escola Politécnica da USP, tendo por objetivo realizar tarefas de montagens simples e visualmente guiadas. O sistema foi testado exaustivamente e os resultados experimentais indicaram algumas vantagens e desvantagens da metodologia empregada, possibilitando a definição de algumas diretrizes importantes para o projeto e implementação de sistemas robóticos inteligentes atuando no mundo real.This dissertation presents a distributed control architecture for a purposive computer vision system, modeled according to a Distributed Artificial Intelligence approach, with emphasis in Multi-Agents Systems. The main problem addressed is the integration of several modules with different purposes and behaviors in a robotic system, which uses computer vision to perceive the world. This integration arises from the organization of several dedicated solutions to different visual tasks, resulting in the proposal of one architecture that consists of a society of Autonomous Agents, communicating with each other through a decentralized and fully connected network, where each AA is responsible for an independent behavior. This society is organized according to behavior rules and an authority structure. Furthermore, this architecture integrates several cognitive modules, like visual perception, planning, control and action. As an attempt of an experimental validation of the proposal, this architecture was implemented in a system composed of a robotic manipulator and one camera, working in an assembly domain. The basic structure of the architecture was developed according to an object oriented methodology and consists of a library of classes which defines the agents\' model and the structures needed for the interactions among these agents in a society. The proposed robotic system was implemented in the Flexible Assembly Cell of the Escola Politécnica da USP, with the objective of accomplishing simple and visually guided assembly tasks. The system was thoroughly tested and the experimental results indicated some advantages and inconveniences of the methodology, allowing the definition of some important guidelines for the design and implementation of intelligent robotic systems acting in the real world.
15
Wong, Wing-ki Vicky. "An immunity-based distributed multiagent control framework". Click to view the E-thesis via HKUTO, 2006. http://sunzi.lib.hku.hk/hkuto/record/B37314348.
Texto completo
16
Zelek, John S. "SPOTT : a real-time, distributed and scalable architecture for autonomous mobile robot control". Thesis, McGill University, 1996. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=34493.
Texto completoResumen
A mobile robot control architecture called SPOTT$ sp1$ is proposed and implemented as a real-time system of concurrently executing and co-operating modules. What distinguishes SPOTT from other behavioral architectures is that it is able to guarantee task completion for navigational tasks under many different scenarios. SPOTT provides a bridge for linking behavioral (i.e., reactive) and symbolic control and has actually been interfaced with the logical reasoning system called COCOLOG. One of the roles of the symbolic reasoner is to help guarantee task completion in the situations where SPOTT is not able to solely do so. In essence, SPOTT is a real-time AI system which is responsible for dynamically adapting to changing environmental circumstances in order to successfully execute and complete a set of navigational tasks for an autonomous mobile robot.SPOTT consists of a behavioral controller, a local dynamic path planner, and a global path planner, as well as a map database and a graphical user interface. The behavioral control formalism is called TR+ and is based on an adaptation and extension of the Teleo-Reactive (TR) formalism. TR+ rules make decisions which affect actuator control and map database maintenance. A dynamic local path planner continually polls the map database in order to navigate around newly encountered obstacles. The local dynamic path planner is based on a potential field method using harmonic functions, which are guaranteed to have no spurious local minima. The global planning module advises the local planning module in order to position and project the global goal onto the local border. A real-time and parallel implementation of SPOTT using a message passing software package called PVM has been developed and tested across a collection of ten to fifteen heterogeneous workstations. Navigational experiments have consisted of moving the robot in an office and laboratory environment to known spatial locations with no or a partial a priori map. ftn$ sp1$A System which integrates Potential fields for planning On-line with TR+ program control in order to successfully execute a general suite of Task commands.
17
Padilla-Franco, Javitt Higmar Nahitt. "Secure framework for implementing distributed networked control systems with mobile observers using heterogeneous controllers". Thesis, New Mexico State University, 2018. http://pqdtopen.proquest.com/#viewpdf?dispub=10759028.
Texto completoResumen
In this dissertation, a framework for the development and analysis of low-cost monitoring and control systems for a set of distributed nodes comprising of dissimilar controllers is presented. The ability to connect multiple disparate processors, is possible due to the use of a secure minimalistic custom communication protocol. This architecture allows the use of mobile devices to interact with the main features of the system for monitoring and control. The server is at the core the overall framework, which enables the transparent development of data acquisition, processing and control models using a software interface. These models automatically translate to functional systems executed by all microprocessors available to the system. The framework contains software libraries that allows the integration of neural networks and fuzzy logic that permit the implementation of intelligent data acquisition and control systems.
The random behavior of the underlying communication network is modeled in real-time to automatically compensate for the delays and lost packages in the execution of control actions.
The framework enables a mapping of system inputs and outputs to state variables. These variables can then be used to form a system model to enable classical control theory analysis, such as controllability, observability and stability test.
18
Gao, Zhenning. "Parallel and Distributed Implementation of A Multilayer Perceptron Neural Network on A Wireless Sensor Network". University of Toledo / OhioLINK, 2014. http://rave.ohiolink.edu/etdc/view?acc_num=toledo1383764269.
Texto completo
19
Bieszczad, Andrzej Carleton University Dissertation Engineering Systems and Computer. "Neuromorphic distributed general problem solvers". Ottawa, 1996.
Buscar texto completo
20
Balamuru, Vinay Gopal. "The Role of Intelligent Mobile Agents in Network Management and Routing". Thesis, University of North Texas, 2000. https://digital.library.unt.edu/ark:/67531/metadc2736/.
Texto completoResumen
In this research, the application of intelligent mobile agents to the management of distributed network environments is investigated. Intelligent mobile agents are programs which can move about network systems in a deterministic manner in carrying their execution state. These agents can be considered an application of distributed artificial intelligence where the (usually small) agent code is moved to the data and executed locally. The mobile agent paradigm offers potential advantages over many conventional mechanisms which move (often large) data to the code, thereby wasting available network bandwidth. The performance of agents in network routing and knowledge acquisition has been investigated and simulated. A working mobile agent system has also been designed and implemented in JDK 1.2.
21
Boone, Gary Noel. "Extreme dimensionality reduction for text learning : cluster-generated feature spaces". Diss., Georgia Institute of Technology, 2000. http://hdl.handle.net/1853/8139.
Texto completo
22
Lu, Yapeng. "An integrated algorithm for distributed optimization in networked systems". Click to view the E-thesis via HKUTO, 2009. http://sunzi.lib.hku.hk/hkuto/record/B43224234.
Texto completo
23
Malheiro, Maria Benedita Campos Neves. "Methodologies for Belief Revision in Multi-agent Systems". Phd thesis, Instituições portuguesas -- UP-Universidade do Porto -- -Faculdade de Engenharia -- -Departamento de Engenharia Electrotécnica e de Computadores, 1999. http://dited.bn.pt:80/29534.
Texto completoResumen
The goal of this thesis is twofold: first, we want to present the distributed belief accommodation and revision model for multi-agent systems that has been developed and, second, we wish to show its applicability to an appropriate domain. The Distributed Belief Accommodation & Revision model, called DeBAteR model, was developed for co-operative heterogeneous multi-agent systems used to model inherently dynamic distributed problems. In these systems, although the agents are able to detect changes both in the environment and in the problem specifications, each agent has only a partial view of the global picture. As a result the information that represents the current state of affairs is dynamic, incomplete and sometimes uncertain. This non-monotonic kind of data is called beliefs ? a belief is a piece of data that is held as correct as long as no contradicting evidence is found or presented. Each agent is expected to include an assumption based truth maintenance module for representing properly this type of data.
Our main effort was concentrated on the task of maintaining the system's information, which consists of updating, revising and accommodating the represented beliefs. Belief updating is necessary for including the changes detected by the agents both in the environment and/or in the problem specifications. Belief revision is essential for solving the inconsistencies detected among the represented beliefs. Belief accommodation and revision is crucial for integrating the multiple disparate perspectives regarding the same data items, which may occur whenever there is overlap of expertise domains between the agents.
In order to solve the information conflicts that result from the detection of inconsistencies between distinct beliefs or within multi-perspective beliefs we conceived the DeBATeR model. The DeBAteR is fully distributed, provides individual belief autonomy and is made of two methodologies: the pro-active belief accommodation and revision methodology and the delayed belief revision methodology. Whilst the first methodology is used to solve domain independent conflicts, the second methodology was devised for solving domain dependent conflicts. Both methodologies use argumentation for, in the case of the domain independent conflicts, choosing the most credible perspective between the existing multiple perspectives of a belief, and, in the case of the domain dependent conflicts, finding the best alternative belief support set for the affected concepts. These methodologies are distributed and their scope may be internal or collective. The DeBAteR model main contributions are: (i) the pro-active methodology conceived for solving domain independent conflicts and (ii) the capability, not only to represent and maintain individual beliefs and joint beliefs, but also to accommodate, rationally maintain and make use of multi-perspective beliefs.
Finally, we describe the developed decision support multi-agent system for choosing adequate project locations, called DIPLOMAT ? Dynamic and Interactive Project Location Test bed, which has the ability of accommodating and revising the represented beliefs according to the DeBAteR model methodologies.O objectivo desta dissertação é duplo: por um lado, pretendemos dar a conhecer o modelo de revisão e acomodação de crenças para sistemas multi-agente por nós desenvolvido e, por outro, procuramos ilustrar a sua validade descrevendo a aplicação que realizámos. O modelo, designado DeBAteR ? Distributed Belief Accommodation & Revision, destina-se a sistemas multi-agente cooperativos e heterogéneos que modelam problemas inerentemente distribuídos e dinâmicos. Neste tipo de sistemas, a informação que representa o ambiente é dinâmica (os agentes possuem a capacidade de constatar alterações no ambiente e/ou nas condições do problema) e, muitas vezes, incompleta (os agentes possuem visões parcelares da realidade) e/ou incerta. Este tipo de informação, de carácter não definitivo, designa-se por crenças ? uma crença é uma convicção tida como correcta enquanto não for posta em causa por alguma evidência. Cada agente, a fim de representar e manipular crenças, foi enriquecido com um módulo específico de manutenção de consistência baseado em suposições. O nosso esforço concentrou-se na tarefa de manutenção (actualização, revisão e acomodação) da informação do sistema. A actualização de crenças é essencial para incorporar as alterações que os agentes detectam no ambiente e/ou nas condições do problema. A revisão de crenças é indispensável para resolver inconsistências (conflitos) entre as crenças representadas. A acomodação e revisão simultânea de crenças é imprescindível para a integração das múltiplas perspectivas díspares que surgem em relação a um mesmo item de informação (crenças pluri-perspectiva) quando existe sobreposição de domínios de especialidade entre os agentes. Para tentar solucionar estes conflitos entre crenças concebemos um modelo distribuído que assegura autonomia individual de crença. O modelo de acomodação e revisão de crenças DeBAteR é composto por duas metodologias: a metodologia pró-activa de acomodação e revisão de crenças pluri-perspectiva e a metodologia retardada de revisão de crenças. A primeira, destina-se a resolver conflitos independentes do domínio e a segunda destina-se à resolução de conflitos dependentes do domínio. Estas metodologias são suportadas quase integralmente por um sistema de argumentação que procura, no caso dos conflitos independentes do domínio, escolher a perspectiva mais credível e, no caso dos conflitos dependentes do domínio, encontrar o melhor conjunto alternativo de suporte para os conceitos afectados. Esta actividade é descentralizada e pode decorrer quer no âmbito intra-agente, quer no âmbito inter-agente. É ainda de realçar: (i) o carácter pró-activo da resolução dos conflitos independentes do domínio (crenças pluri-perspectiva) e (ii) a capacidade de, não só, representar e manter crenças de âmbito individual (crenças suportadas por apenas um agente) e crenças conjuntas (crenças suportadas por vários agentes), mas também, de sintetizar, manter racionalmente e utilizar crenças pluri-perspectiva. Por último, descrevemos o sistema multi-agente de apoio à decisão no domínio da localização de empreendimentos desenvolvido, denominado DIPLOMAT ? Dynamic and Interactive Project Location Test bed, o qual possui a capacidade de acomodar e rever crenças de acordo com as metodologias concebidas no âmbito do modelo DeBAteR.
24
Prueller, Hans. "Distributed online machine learning for mobile care systems". Thesis, De Montfort University, 2014. http://hdl.handle.net/2086/10875.
Texto completoResumen
Telecare and especially Mobile Care Systems are getting more and more popular. They have two major benefits: first, they drastically improve the living standards and even health outcomes for patients. In addition, they allow significant cost savings for adult care by reducing the needs for medical staff. A common drawback of current Mobile Care Systems is that they are rather stationary in most cases and firmly installed in patients’ houses or flats, which makes them stay very near to or even in their homes. There is also an upcoming second category of Mobile Care Systems which are portable without restricting the moving space of the patients, but with the major drawback that they have either very limited computational abilities and only a rather low classification quality or, which is most frequently, they only have a very short runtime on battery and therefore indirectly restrict the freedom of moving of the patients once again. These drawbacks are inherently caused by the restricted computational resources and mainly the limitations of battery based power supply of mobile computer systems. This research investigates the application of novel Artificial Intelligence (AI) and Machine Learning (ML) techniques to improve the operation of 2 Mobile Care Systems. As a result, based on the Evolving Connectionist Systems (ECoS) paradigm, an innovative approach for a highly efficient and self-optimising distributed online machine learning algorithm called MECoS - Moving ECoS - is presented. It balances the conflicting needs of providing a highly responsive complex and distributed online learning classification algorithm by requiring only limited resources in the form of computational power and energy. This approach overcomes the drawbacks of current mobile systems and combines them with the advantages of powerful stationary approaches. The research concludes that the practical application of the presented MECoS algorithm offers substantial improvements to the problems as highlighted within this thesis.
25
Wong, Wing-ki Vicky y 黃穎琪. "An immunity-based distributed multiagent control framework". Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 2006. http://hub.hku.hk/bib/B37314348.
Texto completo
26
Gandon, Fabien. "Distributed artificial intelligence and knowledge management : ontologies and multi-agent systems for a corporate semantic web". Nice, 2002. http://www.theses.fr/2002NICE5773.
Texto completoResumen
This work concerns multi-agents systems for the management of a corporate semantic web based on an ontology. It was carried out in the context of the European project CoMMA focusing on two application scenarios: support technology monitoring activities and assist the integration of a new employee to the organisation. Three aspects were essentially developed in this work: the design of a multi-agents architecture supporting both scenarios, and the organisational top-down approach followed to identify the societies, the roles and the interactions of agents. The construction of the ontology O'CoMMA and the structuring of a corporate memory exploiting semantic Web technologies. The design and implementation of the sub-societies of agents dedicated to the management of the annotations and the ontology and of the protocols underlying these groups of agents, in particular techniques for distributing annotations and queries between the agentsCe travail concerne les systèmes multi-agents pour la gestion d'un web sémantique d'entreprise basé sur une ontologie. Il a été effectué dans le cadre du projet Européen CoMMA se focalisant sur deux scénarios d'application: l'assistance aux activités de veille technologique et l'aide à l'insertion d'un nouvel employé dans une organisation. Trois aspects ont essentiellement été développés dans ce travail: la conception d'une architecture multi-agents assistant les deux scénarios, et l'approche organisationnelle descendante adoptée pour identifier les sociétés, les rôles et les interactions des agents. La construction de l'ontologie O'CoMMA et la structuration de la mémoire organisationnelle en exploitant les technologies du Web sémantique. La conception et l'implantation (a) des sous-sociétés d'agents chargées de la maintenance des annotations et de l'ontologie et (b) des protocoles supportant ces deux groupes d'agents, en particulier des techniques pour la distribution des annotations et des requêtes entre les agents
27
Hu, Yuebing y 胡跃冰. "Consensus control of multi-agent systems". Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 2011. http://hub.hku.hk/bib/B4658657X.
Texto completo
28
Wahbi, Mohamed. "Algorithms and Ordering Heuristics for Distributed Constraint Satisfaction Problems". Phd thesis, Université Montpellier II - Sciences et Techniques du Languedoc, 2012. http://tel.archives-ouvertes.fr/tel-00718537.
Texto completoResumen
Les problèmes de satisfaction de contraintes distribués (DisCSP) permettent de formaliser divers problèmes qui se situent dans l'intelligence artificielle distribuée. Ces problèmes consistent à trouver une combinaison cohérente des actions de plusieurs agents. Durant cette thèse nous avons apporté plusieurs contributions dans le cadre des DisCSPs. Premièrement, nous avons proposé le Nogood-Based Asynchronous Forward-Checking (AFC-ng). Dans AFC-ng, les agents utilisent les nogoods pour justifier chaque suppression d'une valeur du domaine de chaque variable. Outre l'utilisation des nogoods, plusieurs backtracks simultanés venant de différents agents vers différentes destinations sont autorisés. En deuxième lieu, nous exploitons les caractéristiques intrinsèques du réseau de contraintes pour exécuter plusieurs processus de recherche AFC-ng d'une manière asynchrone à travers chaque branche du pseudo-arborescence obtenu à partir du graphe de contraintes dans l'algorithme Asynchronous Forward-Checking Tree (AFC-tree). Puis, nous proposons deux nouveaux algorithmes de recherche synchrones basés sur le même mécanisme que notre AFC-ng. Cependant, au lieu de maintenir le forward checking sur les agents non encore instanciés, nous proposons de maintenir la consistance d'arc. Ensuite, nous proposons Agile Asynchronous Backtracking (Agile-ABT), un algorithme de changement d'ordre asynchrone qui s'affranchit des restrictions habituelles des algorithmes de backtracking asynchrone. Puis, nous avons proposé une nouvelle méthode correcte pour comparer les ordres dans ABT_DO-Retro. Cette méthode détermine l'ordre le plus pertinent en comparant les indices des agents dès que les compteurs d'une position donnée dans le timestamp sont égaux. Finalement, nous présentons une nouvelle version entièrement restructurée de la plateforme DisChoco pour résoudre les problèmes de satisfaction et d'optimisation de contraintes distribués.
29
Zhou, Lingzhong y n/a. "Agent Ordering and Nogood Repairs in Distributed Constraint Solving". Griffith University. School of Information and Communication Technology, 2006. http://www4.gu.edu.au:8080/adt-root/public/adt-QGU20070713.162515.
Texto completoResumen
The distributed constraint satisfaction problem is a general formalization used to represent problems in distributed multi-agent systems. A large body of problems in artificial intelligence and computer science can be easily formulated as distributed constraint satisfaction problems. In this thesis we study agent ordering, effects of no-goods, search efficiency and threshold repairing in distributed constraint satisfaction problems and its variants. A summary of contributions is as follows: 1. We present a new algorithm, Dynamic Agent Ordering. A distinctive feature of this algorithm is that it uses the degree of unsatisfiability as a guiding parameter to dynamically determine agent ordering during the search. We show through an empirical study that our algorithm performs better than the existing approaches. In our approach, the independence of agents is guaranteed and agents without neighbouring relationships can run concurrently and asynchronously. (Part of this work was published in the Australian Al Conference (80)). 2. We extend the Dynamic Agent Ordering algorithm by incorporating a novel technique called nogood repairing. This results in a dramatic reduction in the nogoods being stored, and communication costs. In an empirical study, we11 show that this approach outperforms an equivalent static ordering algorithm and a current state-of-the-art technique in terms of execution time, memory usage and communication cost. (Part of this work was published at FLAIRS Conference (81)). Further, we introduce a new algorithm, Over-constrained Dynamic Agent Ordering, that breaks new ground in handling multiple variables per agent in distributed over-constrained satisfaction problems. The algorithm also uses the degree of unsatisfiability as a measure for relaxing constraints, and hence as a way to guide the search toward the best optimal solution(s). By applying our Threshold Repair method, we can solve a distributed constraint satisfaction problem without knowing whether the problem is under- or over-constrained. In an experimental study, we show that the new algorithm compares favourably to an implementation of asynchronous weak commitment search adapted to handle over-constrained problems. (Part of this work was published at the Canadian AI conference (79)).
30
Lu, Yapeng y 呂亞鵬. "An integrated algorithm for distributed optimization in networked systems". Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 2009. http://hub.hku.hk/bib/B43224234.
Texto completo
31
Gaff, Douglas G. "Architecture design and simulation for distributed learning classifier systems". Thesis, This resource online, 1995. http://scholar.lib.vt.edu/theses/available/etd-02132009-172649/.
Texto completo
32
Challita, Ursula. "Distributed algorithms for optimized resource management of LTE in unlicensed spectrum and UAV-enabled wireless networks". Thesis, University of Edinburgh, 2018. http://hdl.handle.net/1842/33099.
Texto completoResumen
Next-generation wireless cellular networks are morphing into a massive Internet of Things (IoT) environment that integrates a heterogeneous mix of wireless-enabled devices such as unmanned aerial vehicles (UAVs) and connected vehicles. This unprecedented transformation will not only drive an exponential growth in wireless traffic, but it will also lead to the emergence of new wireless service applications that substantially differ from conventional multimedia services. To realize the fifth generation (5G) mobile networks vision, a new wireless radio technology paradigm shift is required in order to meet the quality of service requirements of these new emerging use cases. In this respect, one of the major components of 5G is self-organized networks. In essence, future cellular networks will have to rely on an autonomous and self-organized behavior in order to manage the large scale of wireless-enabled devices. Such an autonomous capability can be realized by integrating fundamental notions of artificial intelligence (AI) across various network devices. In this regard, the main objective of this thesis is to propose novel self-organizing and AI-inspired algorithms for optimizing the available radio resources in next-generation wireless cellular networks. First, heterogeneous networks that encompass licensed and unlicensed spectrum are studied. In this context, a deep reinforcement learning (RL) framework based on long short-term memory cells is introduced. The proposed scheme aims at proactively allocating the licensed assisted access LTE (LTE-LAA) radio resources over the unlicensed spectrum while ensuring an efficient coexistence with WiFi. The proposed deep learning algorithm is shown to reach a mixed-strategy Nash equilibrium, when it converges. Simulation results using real data traces show that the proposed scheme can yield up to 28% and 11% gains over a conventional reactive approach and a proportional fair coexistence mechanism, respectively. In terms of priority fairness, results show that an efficient utilization of the unlicensed spectrum is guaranteed when both technologies, LTE-LAA and WiFi, are given equal weighted priorities for transmission on the unlicensed spectrum. Furthermore, an optimization formulation for LTE-LAA holistic traffic balancing across the licensed and the unlicensed bands is proposed. A closed form solution for the aforementioned optimization problem is derived. An attractive aspect of the derived solution is that it can be applied online by each LTE-LAA small base station (SBS), adapting its transmission behavior in each of the bands, and without explicit communication with WiFi nodes. Simulation results show that the proposed traffic balancing scheme provides a better tradeoff between maximizing the total network throughput and achieving fairness among all network ows compared to alternative approaches from the literature. Second, UAV-enabled wireless networks are investigated. In particular, the problems of interference management for cellular-connected UAVs and the use of UAVs for providing backhaul connectivity to SBSs are studied. Speci cally, a deep RL framework based on echo state network cells is proposed for optimizing the trajectories of multiple cellular-connected UAVs while minimizing the interference level caused on the ground network. The proposed algorithm is shown to reach a subgame perfect Nash equilibrium upon convergence. Moreover, an upper and lower bound for the altitude of the UAVs is derived thus reducing the computational complexity of the proposed algorithm. Simulation results show that the proposed path planning scheme allows each UAV to achieve a tradeoff between minimizing energy efficiency, wireless latency, and the interference level caused on the ground network along its path. Moreover, in the context of UAV-enabled wireless networks, a UAV-based on-demand aerial backhaul network is proposed. For this framework, a network formation algorithm, which is guaranteed to reach a pairwise stable network upon convergence, is presented. Simulation results show that the proposed scheme achieves substantial performance gains in terms of both rate and delay reaching, respectively, up to 3.8 and 4-fold increase compared to the formation of direct communication links with the gateway node. Overall, the results of the different proposed schemes show that these schemes yield significant improvements in the total network performance as compared to current existing literature. In essence, the proposed algorithms can also provide self-organizing solutions for several resource management problems in the context of new emerging use cases in 5G networks, such as connected autonomous vehicles and virtual reality headsets.
33
Dai, Hanping. "Distributed control system architecture and smart sensing for intelligent semi-autonomous vehicles". Thesis, De Montfort University, 2002. http://hdl.handle.net/2086/4784.
Texto completo
34
Qi, Dehu. "Multi-agent systems : integrating reinforcement learning, bidding and genetic algorithms /". free to MU campus, to others for purchase, 2002. http://wwwlib.umi.com/cr/mo/fullcit?p3060133.
Texto completo
35
Santos, Daniela Scherer dos. "Bee clustering : um algoritmo para agrupamento de dados inspirado em inteligência de enxames". reponame:Biblioteca Digital de Teses e Dissertações da UFRGS, 2009. http://hdl.handle.net/10183/18249.
Texto completoResumen
Agrupamento de dados é o processo que consiste em dividir um conjunto de dados em grupos de forma que dados semelhantes entre si permaneçam no mesmo grupo enquanto que dados dissimilares sejam alocados em grupos diferentes. Técnicas tradicionais de agrupamento de dados têm sido usualmente desenvolvidas de maneira centralizada dependendo assim de estruturas que devem ser acessadas e modificadas a cada passo do processo de agrupamento. Além disso, os resultados gerados por tais métodos são dependentes de informações que devem ser fornecidas a priori como por exemplo número de grupos, tamanho do grupo ou densidade mínima/máxima permitida para o grupo. O presente trabalho visa propor o bee clustering, um algoritmo distribuído inspirado principalmente em técnicas de inteligência de enxames como organização de colônias de abelhas e alocação de tarefas em insetos sociais, desenvolvido com o objetivo de resolver o problema de agrupamento de dados sem a necessidade de pistas sobre o resultado desejado ou inicialização de parâmetros complexos. O bee clustering é capaz de formar grupos de agentes de maneira distribuída, uma necessidade típica em cenários de sistemas multiagente que exijam capacidade de auto-organização sem controle centralizado. Os resultados obtidos mostram que é possível atingir resultados comparáveis as abordagens centralizadas.Clustering can be defined as a set of techniques that separate a data set into groups of similar objects. Data items within the same group are more similar than objects of different groups. Traditional clustering methods have been usually developed in a centralized fashion. One reason for this is that this form of clustering relies on data structures that must be accessed and modified at each step of the clustering process. Another issue with classical clustering methods is that they need some hints about the target clustering. These hints include for example the number of clusters, the expected cluster size, or the minimum density of clusters. In this work we propose a clustering algorithm that is inspired by swarm intelligence techniques such as the organization of bee colonies and task allocation among social insects. Our proposed algorithm is developed in a decentralized fashion without any initial information about number of classes, number of partitions, and size of partition, and without the need of complex parameters. The bee clustering algorithm is able to form groups of agents in a distributed way, a typical necessity in multiagent scenarios that require self-organization without central control. The performance of our algorithm shows that it is possible to achieve results that are comparable to those from centralized approaches.
36
Gonzalez, Lopez Jorge. "Distributed multi-label learning on Apache Spark". VCU Scholars Compass, 2019. https://scholarscompass.vcu.edu/etd/5775.
Texto completoResumen
This thesis proposes a series of multi-label learning algorithms for classification and feature selection implemented on the Apache Spark distributed computing model. Five approaches for determining the optimal architecture to speed up multi-label learning methods are presented. These approaches range from local parallelization using threads to distributed computing using independent or shared memory spaces. It is shown that the optimal approach performs hundreds of times faster than the baseline method. Three distributed multi-label k nearest neighbors methods built on top of the Spark architecture are proposed: an exact iterative method that computes pair-wise distances, an approximate tree-based method that indexes the instances across multiple nodes, and an approximate local sensitive hashing method that builds multiple hash tables to index the data. The results indicated that the predictions of the tree-based method are on par with those of an exact method while reducing the execution times in all the scenarios. The aforementioned method is then used to evaluate the quality of a selected feature subset. The optimal adaptation for a multi-label feature selection criterion is discussed and two distributed feature selection methods for multi-label problems are proposed: a method that selects the feature subset that maximizes the Euclidean norm of individual information measures, and a method that selects the subset of features maximizing the geometric mean. The results indicate that each method excels in different scenarios depending on type of features and the number of labels. Rigorous experimental studies and statistical analyses over many multi-label metrics and datasets confirm that the proposals achieve better performances and provide better scalability to bigger data than the methods compared in the state of the art.
37
Huhtinen, J. (Jouni). "Utilization of neural network and agent technology combination for distributed intelligent applications and services". Doctoral thesis, University of Oulu, 2005. http://urn.fi/urn:isbn:9514278550.
Texto completoResumen
Abstract
The use of agent systems has increased enormously, especially in the field of mobile services. Intelligent services have also increased rapidly in the web. In this thesis, the utilization of software agent technology in mobile services and decentralized intelligent services in the multimedia business is introduced and described. Both Genie Agent Architecture (GAA) and Decentralized International and Intelligent Software Architecture (DIISA) are described.
The common problems in decentralized software systems are lack of intelligence, communication of software modules and system learning. Another problem is the personalization of users and services. A third problem is the matching of users and service characteristics in web application level in a non-linear way. In this case it means that web services follow human steps and are capable of learning from human inputs and their characteristics in an intelligent way. This third problem is addressed in this thesis and solutions are presented with two intelligent software architectures and services.
The solutions of the thesis are based on a combination of neural network and agent technology. To be more specific, solutions are based on an intelligent agent which uses certain black box information like Self-Organized Map (SOM). This process is as follows; information agents collect information from different sources like the web, databases, users, other software agents and the environment. Information is filtered and adapted for input vectors. Maps are created from a data entry of an SOM. Using maps is very simple, input forms are completed by users (automatically or manually) or user agents. Input vectors are formed again and sent to a certain map. The map gives several outputs which are passed through specific algorithms. This information is passed to an intelligent agent.
The needs for web intelligence and knowledge representation serving users is a current issue in many business solutions. The main goal is to enable this by means of autonomous agents which communicate with each other using an agent communication language and with users using their native languages via several communication channels.
38
Cheng, Yongqiang. "Wireless mosaic eyes based robot path planning and control : autonomous robot navigation using environment intelligence with distributed vision sensors". Thesis, University of Bradford, 2010. http://hdl.handle.net/10454/4421.
Texto completoResumen
As an attempt to steer away from developing an autonomous robot with complex centralised intelligence, this thesis proposes an intelligent environment infrastructure where intelligences are distributed in the environment through collaborative vision sensors mounted in a physical architecture, forming a wireless sensor network, to enable the navigation of unintelligent robots within that physical architecture. The aim is to avoid the bottleneck of centralised robot intelligence that hinders the application and exploitation of autonomous robot. A bio-mimetic snake algorithm is proposed to coordinate the distributed vision sensors for the generation of a collision free Reference-snake (R-snake) path during the path planning process. By following the R-snake path, a novel Accompanied snake (A-snake) method that complies with the robot's nonholonomic constraints for trajectory generation and motion control is introduced to generate real time robot motion commands to navigate the robot from its current position to the target position. A rolling window optimisation mechanism subject to control input saturation constraints is carried out for time-optimal control along the A-snake. A comprehensive simulation software and a practical distributed intelligent environment with vision sensors mounted on a building ceiling are developed. All the algorithms proposed in this thesis are first verified by the simulation and then implemented in the practical intelligent environment. A model car with less on-board intelligence is successfully controlled by the distributed vision sensors and demonstrated superior mobility.
39
Chapman, Kevin L. "A Distributed Q-learning Classifier System for task decomposition in real robot learning problems". Thesis, This resource online, 1996. http://scholar.lib.vt.edu/theses/available/etd-03042009-041449/.
Texto completo
40
McCallum, Simon y n/a. "Catastrophic forgetting and the pseudorehearsal solution in Hopfield networks". University of Otago. Department of Computer Sciences, 2007. http://adt.otago.ac.nz./public/adt-NZDU20080130.105101.
Texto completoResumen
Most artificial neural networks suffer from the problem of catastrophic forgetting, where previously learnt information is suddenly and completely lost when new information is learnt. Memory in real neural systems does not appear to suffer from this unusual behaviour. In this thesis we discuss the problem of catastrophic forgetting in Hopfield networks, and investigate various potential solutions. We extend the pseudorehearsal solution of Robins (1995) enabling it to work in this attractor network, and compare the results with the unlearning procedure proposed by Crick and Mitchison (1983). We then explore a familiarity measure based on the energy profile of the learnt patterns. By using the ratio of high energy to low energy parts of the network we can robustly distinguish the learnt patterns from the large number of spurious "fantasy" patterns that are common in these networks. This energy ratio measure is then used to improve the pseudorehearsal solution so that it can store 0.3N patterns in the Hopfield network, significantly more than previous proposed solutions to catastrophic forgetting. Finally, we explore links between the mechanisms investigated in this thesis and the consolidation of newly learnt material during sleep.
41
Xu, Duo. "An agent-based tool for China's express delivery SMEs". Click to view the E-thesis via HKUTO, 2008. http://sunzi.lib.hku.hk/hkuto/record/B40987784.
Texto completo
42
Wang, Tingting. "Multi-agent team competitions and the implementation of a team-strategy". HKBU Institutional Repository, 2006. http://repository.hkbu.edu.hk/etd_ra/772.
Texto completo
43
Case, Denise Marie. "Engineering complex systems with multigroup agents". Diss., Kansas State University, 2015. http://hdl.handle.net/2097/19045.
Texto completoResumen
Doctor of PhilosophyComputing and Information Sciences
Scott A. DeLoach
As sensor prices drop and computing devices continue to become more compact and powerful, computing capabilities are being embedded throughout our physical environment. Connecting these devices in cyber-physical systems (CPS) enables applications with significant societal impact and economic benefit. However, engineering CPS poses modeling, architecture, and engineering challenges and, to fully realize the desired benefits, many outstanding challenges must be addressed. For the cyber parts of CPS, two decades of work in the design of autonomous agents and multiagent systems (MAS) offers design principles for distributed intelligent systems and formalizations for agent-oriented software engineering (AOSE). MAS foundations offer a natural fit for enabling distributed interacting devices. In some cases, complex control structures such as holarchies can be advantageous. These can motivate complex organizational strategies when implementing such systems with a MAS, and some designs may require agents to act in multiple groups simultaneously. Such agents must be able to manage their multiple associations and assignments in a consistent and unambiguous way. This thesis shows how designing agents as systems of intelligent subagents offers a reusable and practical approach to designing complex systems. It presents a set of flexible, reusable components developed for OBAA++, an organization-based architecture for single-group MAS, and shows how these components were used to develop the Adaptive Architecture for Systems of Intelligent Systems (AASIS) to enable multigroup agents suitable for complex, multigroup MAS. This work illustrates the reusability and flexibility of the approach by using AASIS to simulate a CPS for an intelligent power distribution system (IPDS) operating two multigroup MAS concurrently: one providing continuous voltage control and a second conducting discrete power auctions near sources of distributed generation.
44
Cazella, Silvio Cesar. "Uma arquitetura para coordenar a interação de agentes na internet". reponame:Biblioteca Digital de Teses e Dissertações da UFRGS, 1997. http://hdl.handle.net/10183/17973.
Texto completoResumen
O grande salto tecnológico ocorrido nos últimos decênios em áreas como a informática e as telecomunicações já começa a causar uma verdadeira revolução social. Com o advento da Internet, a possibilidade de substituir a presença física de pessoas por assistentes inteligentes ou agentes é uma realidade que começa a tomar forma. O objetivo principal deste trabalho é definir como deve ser feita a interação entre agentes, nas sociedades de agentes dentro da Internet. Para tanto, é apresentada uma proposta de arquitetura geral para coordenar a interação de agentes na Internet, de forma a possibilitar, entre outros, a localização de agentes, a conexão entre os agentes, a identificação de agentes (nomes de agentes, função e endereços destes na rede) sem que ocorra a repetição de nomes na sociedade, a entrada e saída de agentes da sociedade, a troca de mensagens entre os agentes e a procura de agentes com determinadas características. Inicialmente, é apresentada uma visão geral sobre Inteligência Artificial Distribuída, área em que o trabalho se insere, e alguns exemplos de aplicações agentes. A seguir, as principais características da linguagem Java são introduzidas, por ser a linguagem utilizada nas implementações realizadas. Estas implementações foram feitas, a nível de protótipos, para permitir a obtenção de experiência no trabalho com agentes. Toda a programação destes agentes foi feita utilizando a linguagem Java, e a sua escolha como linguagem para estas implementações, foi feita devido a características próprias. Por exemplo. a linguagem Java é independente da plataforma de trabalho, o que no caso de programação para Internet, torna-se um característica muito desejável. Após, dois sistemas para o desenvolvimento de agentes na Internet são: apresentados em suas principais características do ponto de vista da arquitetura geral. Estes sistemas são o SodaBot e o sistema Java Agent Template. Este último totalmente implementado com a utilização da linguagem Java. Finalmente, apresenta-se em detalhes a arquitetura proposta, com um exemplo de utilização e perspectivas para a continuação do trabalho. O resultado obtido com todos os estudos realizados diz respeito a proposta de uma arquitetura que tem por objetivo permitir coordenar a interação entre os agentes que vierem a ser implementados na Internet. Toda a proposta foi acompanhada por estudos reais da viabilidade da implementação futura da arquitetura.Technological breakthroughs which occurred in the last decades in areas such as Computer Science and Telecommunications have started to cause an undeniable social revolution. With the Internet, the possibility of replacing the physical presence of people by intelligent assistants or agents is now becoming a reality. This thesis aims at defining how the interaction among agents in the Internet should be achieved. An architecture to coordinate the interaction of agents in the Internet is presented, so as to make it possible, among other things, the localization of agents, the connection among agents, the identification of agents (their names, function, and addresses in the net), the way in and the way out of a gents of the society, the exchange of messages among agents and the search for agents with specific characteristics. First, a general view on Distributed Artificial Intelligence, the area in which this work is inserted, and some examples of agents are given. Next, the main characteristics of the Java language are introduced, since it is the language used in the implementations carried out. These implementations accomplished were prototypes which aim at gaining experience in the work with agents. All the programming of these a gents was carried out using the Java language, which was chosen for these implementations due to its characteristics. For example, the Java lan guage is Architecture Neutral, which in the case of programming for the Internet, becomes very desirable. After that, the main characteristics of two systems for the development of agents in the Internet, concerning their general architecture, were presented. These systems are SodaBot and Java Agent Template, the latter being totally implemented in the Java language. Finally, the architecture which was proposed is described in detail with an example of utilization and perspectives for a continuation of the work. The result obtained from this work is related to the proposal of an architecture which aims at making it possible to coordinate the interaction among agents which will be implemented in the Internet. The entire proposal was accompanied by studies of the feasibility of a future implementation of this architecture.
45
Diop, Codé. "An autonomic service bus for service-based distributed systems". Thesis, Toulouse, INSA, 2015. http://www.theses.fr/2015ISAT0011/document.
Texto completoResumen
Avec l’évolution des technologies de l’internet, les applications et plus généralement lessystèmes distribués sont de plus en plus conçus en composant et interconnectant un ensemblede services distribués. Ces services pouvant être très hétérogènes, plusieurs approches etsolutions pour la gestion de l’intégration et l’interopérabilité ont été proposées. De toutes cespropositions, les bus de services (ESB – Enterprise Service Bus) ont été désignés commeétant la solution la plus adaptée. Toutefois, le problème avec les ESB est qu’ils sont déployésdans un contexte très évolutif et très dynamique; un contexte dans lequel un grand nombre deservices peuvent être fournis et utilisés de façon concurrente à travers le bus. L’utilisationconcurrente de ces services mais aussi des ressources sous-jacentes allouées au bus (mémoire,processeur, etc.) peut conduire à des événements imprévisibles tels qu’une surcharge du bus,une indisponibilité des services, des temps de réponse élevés, une diminution de la fiabilité,etc. Dans ce contexte, des solutions efficaces permettant de garantir ou d'améliorer à la fois laqualité de service et l'évolutivité offertes par les ESB sont nécessaires. Le but de cette thèse est de proposer les principes architecturaux pour la mise en place un busde service autonome (ASB) qui offre une solution de communication scalable guidée par lestransactions des systèmes interconnectés, mais aussi par les ressources disponibles. L’ASBoffre aussi un service d’intégration différentiée en fonction des exigences en termes de qualitéde service spécifiques aux systèmes interconnectésWith the accelerated evolution of Internet, distributed systems are more and more designed asa composition of distributed services that need to be composed to implement complexbusiness processes. Diversity and heterogeneity of these services raise important integrabilityand interoperability requirements. To meet these needs, the Enterprise Service Bus (ESB) hasbeen proposed as a mediator based on open and standard interfaces facilitating theintegrability and interoperability of services. However, in very active and dynamic contextswhere a large number of concurrent services can be provided and consumed via the ESB, thecompetition for using shared services, but also the underlying computing resources allocatedto the ESB (memory, processor, etc.) can lead to unpredictable events such as serviceunavailability, high response time, decrease of reliability, etc. Such anomalies need to beaddressed by proposing efficient strategies able to guarantee or to improve both the QoS andscalability offered by the ESB. The aim of this thesis is to propose an architectural framework for a QoS-aware AutonomicService Bus (ASB) able to offer in an autonomic way a scalable communication solutionguided by distributed systems transactions and the state of the underlying computingresources. The ASB offers also a differentiated integration service based on the QoSrequirements of interconnected systems
46
Mattos, Ekler Paulino de. "Analise de uso de sociedade de tutores inteligentes com aplicação em sistemas de e-Gov". [s.n.], 2007. http://repositorio.unicamp.br/jspui/handle/REPOSIP/259463.
Texto completoResumen
Orientador: Leonardo de Souza MendesDissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Eletrica e de Computação
Made available in DSpace on 2018-08-10T16:36:33Z (GMT). No. of bitstreams: 1 Mattos_EklerPaulinode_M.pdf: 2049372 bytes, checksum: d292b2d52c2a0c0bf5326e8f7e533665 (MD5) Previous issue date: 2007
Resumo: O Sistema Tutor Inteligente (STI) pertence a uma categoria de sistemas de natureza educacional, utilizado como ferramenta de suporte ao ensino-aprendizagem. Possui uma estrutura modular que tem por finalidade auxiliar o aprendiz na realização de atividades educacionais, bem como a capacidade de adaptar-se de acordo com as necessidades de um aprendiz, o que faz do STI uma arquitetura interessante na construção de softwares educacionais. O trabalho proposto tem por objetivo utilizar a arquitetura de STI, aplicada à área de sistemas de e-Gov como proposta de solução de problemas de natureza distribuída. Como estudo de caso, foi escolhida a área Gestão de Materiais e Medicamentos, justamente por apresentar problema pertinente à distribuição de materiais e medicamentos, nas unidades básicas de saúde (UBS). Cada STI funciona como representante de uma UBS, que tem por função realizar o papel de um agente gestor de estoque (Agente Gestor Tutor - AGT), cargo pouco comum na rede municipal de saúde, auxiliando o administrador de cada setor (visto como o aprendiz) a realizar tarefas complexas de gestão de materiais e medicamentos. Foi realizada uma série de simulações usando o protótipo desenvolvido para testar a sua viabilidade de aplicação com relação ao tratamento do estoque distribuído de uma arquitetura de rede municipal de saúde
Abstract: The Intelligent Tutor Systems (ITS) belong to a category of educational nature systems, used as a tool to support the teaching and learning. It has a modular structure, which aim to help the apprentice in the execution of educational activities, as well as in adapting itself according to the apprentice¿s necessities, what makes the ITS, an interesting architecture in the construction of educational softwares. The proposed work aim to use the ITS architecture in the management of materials, as a solution for the problem of medicine distribution in the health basic units (HBU). Each ITS works as a HBU representative, whose function is to play the role of a managing agent of supply (Tutorial Managing Agent - TMA), a post job not so common in the municipal health¿s network. The TMA assists the administrator of each sector (seen as the apprentice) in executing complex tasks of management of materials and medicines.In this way, many simulations were carried out, using the developed prototype to test its feasibility of application, in relation to the management of the distributed materials of architecture of a municipal health¿s network
Mestrado
Telecomunicações e Telemática
Mestre em Engenharia Elétrica
47
Epstein, Daniel. "Um algoritmo distribuído para resolução do problema de geração de estruturas de coalizão com presença de externalidades". reponame:Biblioteca Digital de Teses e Dissertações da UFRGS, 2013. http://hdl.handle.net/10183/103391.
Texto completoResumen
Uma importante parte de um sistema multiagente é o seu mecanismo de coordenação que permite que os agentes possam agir de maneira coesa em direção aos seus objetivos, sejam eles individuais ou coletivos. Um agente pode optar por cooperar para atingir um determinado objetivo que seria inalcançável através de ações individuais, para realizar uma tarefa de maneira mais eficiente ou simplesmente porque ele foi projetado para tal. Em todos os casos, a formação de coalizões (grupos de agentes que concordam em coordenar suas ações em torno de um objetivo comum) é uma questão fundamental. O problema de geração de estruturas de coalizão entre agentes (conjunto de todas as combinações de coalizões) é um tópico de pesquisa que recebeu muita atenção principalmente na resolução do problema quando considerado como um jogo de função característica, onde o valor das coalizões independe dos agentes que não estão presentes nela. Essa abordagem, apesar de ser indicada para muitos tipos de problema, não cobre toda a área de pesquisa do assunto, visto que em muitos casos a criação de uma coalizão irá afetar os demais agentes do sistema. Quando o sistema possui agentes com objetivos sobrepostos ou contrários, uma coalizão cujos recursos são destinados a completar tais objetivos irá influenciar as demais coalizões desse sistema. Essa influência se chama externalidade e, nesses casos, o problema de formação de estruturas de coalizão deve ser tratado como um jogo de partição. Apesar das pesquisas na área de jogos de partição serem recentes, elas trazem resultados promissores e há alguns poucos algoritmos já desenvolvidos para buscar soluções a esse problema. A busca pela melhor estrutura de coalizão geralmente demanda que seja calculado o valor de todas possíveis coalizões, a fim de se encontrar aquele conjunto cuja soma dos valores das coalizões forneça o melhor resultado. Esse processo requer um alto número de computações e de memória, devido à natureza exponencial do problema. Assim, ao invés de apenas um agente central realizar todas as operações, é mais eficiente do ponto de vista do uso de recursos computacionais distribuir essas operações entres os diversos agentes presentes no sistema. Além dos benefícios computacionais, distribuir o processo de busca pela melhor estrutura de coalizão permitiria trabalhar com questões como privacidade e tolerância a falhas, tendo em vista que as informações não estão concentradas em um único agente. Apesar disso, não há na literatura qualquer algoritmo capaz de solucionar o problema de geração de estrutura de coalizão em ambientes distribuídos e que sejam modelados como jogos de partição. A proposta desse trabalho é utilizar a fundamentação teórica existente acerca do problema de formação de estruturas de coalizão (modelados tanto como jogos de função característica quanto como jogos de partição) para criar um algoritmo distribuído capaz de encontrar a estrutura de coalizão ótima em ambientes que possuam externalidade. Esse algoritmo utiliza como base a ordenação das coalizões e dos agentes para permitir a distribuição do cálculo dos limites superiores e inferiores de cada coalizão. Após, esses valores são utilizados para se encontrar o subespaço mais provável de conter a estrutura de coalizão ótima. Com base nos experimentos, percebe-se que o algoritmo encontrou a estrutura de coalizão ótima buscando em apenas uma pequena parte do espaço de busca. Para os experimentos com 16 agentes, o algoritmo foi capaz de encontrar a solução ótima procurando em apenas 0,01% do espaço de busca. Também, é demonstrado que em cenários com externalidade negativa os agentes necessitaram investigar um espaço de busca menor para encontrar a estrutura de coalizão ótima que em cenários com externalidade positiva. Experimentos também demonstram que o algoritmo não consegue encontrar a estrutura de coalizão ótima quando há falhas na comunicação entre os agentes.An important part of a multi-agent system is its coordination mechanism that allows the agents to act cohesively towards their goals, whether individual or collective. An agent can choose to cooperate to achieve a certain goal that would be unattainable through individual actions, to perform a task more efficiently or simply because it was designed to do so. In all cases, the formation of coalitions (group of agents that agree to coordinate their actions around a common goal) is a key issue. The problem of generating coalition structures between agents (set of all combinations of coalitions) is a research topic that has received much attention mostly on solving the problem when considered as a characteristic function game, where the value of coalitions is independent of agents that are not part of it. This approach, although suitable for many types of problem, does not cover the whole area of research on the subject, since in many cases the creation of a coalition will affect the other agents of the system. When the system has agents with overlapping goals or opposing goals, a coalition whose resources are devoted to completing these objectives will influence the other coalitions of that system. This influence is called externality, and in these cases, the problem of formation of coalition structures should be treated as a partition function game. Although research in the area of partition games is recent, it brings promising results and there are few algorithms already developed to find solutions to this problem. The search for the best coalition structure generally requires computation of the value of all possible coalitions in order to find the set that the sum of the values of the coalitions provides the best result. This process requires a large number of computations and memory due to the exponential nature of the problem. Hence, instead of just one central agent performing all operations, it is more efficient to distribute those operations among several agents. Besides the computational benefits, distributing the search process for the best coalition structure would address issues such as privacy and fault tolerance, given that the information is not concentrated in a single agent. Nevertheless, in the literature there is not algorithm capable of solving the problem of coalition structure generation in decentralized environments and modeled as partition function game. The purpose of this work is to use the existing theoretical foundations for solving the coalition structure generation problem (modeled both as a characteristic function game and as a partition function game) to create a distributed algorithm capable of finding the optimal coalition structure in environments that have externality. This algorithm uses as a base the ordering of coalitions and agents to distribute the calculation of the upper and lower limits for each coalition. Afterwards, these values are used to find the subspace more likely to contain the optimal coalition structure. Based on experiments, the algorithm found the optimal coalition structure searching only a small part of the search space. For the experiments with 16 agents, the algorithm was able to find the solution looking at just 0.0001%of the search space. Also, it is shown that in scenarios with negative externality agents need to investigate a smaller search space to find the optimal coalition structure than in scenarios with positive externality. Experiments also show that the algorithm can not find the optimal coalition structure when there are failures in the communication among the agents.
48
Xu, Duo y 徐鐸. "An agent-based tool for China's express delivery SMEs". Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 2008. http://hub.hku.hk/bib/B40987784.
Texto completo
49
Capanni, Niccolo Francesco. "The functionality of spatial and time domain artificial neural models". Thesis, Robert Gordon University, 2006. http://hdl.handle.net/10059/241.
Texto completoResumen
This thesis investigates the functionality of the units used in connectionist Artificial Intelligence systems. Artificial Neural Networks form the foundation of the research and their units, Artificial Neurons, are first compared with alternative models. This initial work is mainly in the spatial-domain and introduces a new neural model, termed a Taylor Series neuron. This is designed to be flexible enough to assume most mathematical functions. The unit is based on Power Series theory and a specifically implemented Taylor Series neuron is demonstrated. These neurons are of particular usefulness in evolutionary networks as they allow the complexity to increase without adding units. Training is achieved via various traditiona and derived methods based on the Delta Rule, Backpropagation, Genetic Algorithms and associated evolutionary techniques. This new neural unit has been presented as a controllable and more highly functional alternative to previous models. The work on the Taylor Series neuron moved into time-domain behaviour and through the investigation of neural oscillators led to an examination of single-celled intelligence from which the later work developed. Connectionist approaches to Artificial Intelligence are almost always based on Artificial Neural Networks. However, another route towards Parallel Distributed Processing was introduced. This was inspired by the intelligence displayed by single-celled creatures called Protoctists (Protists). A new system based on networks of interacting proteins was introduced. These networks were tested in pattern-recognition and control tasks in the time-domain and proved more flexible than most neuron models. They were trained using a Genetic Algorithm and a derived Backpropagation Algorithm. Termed "Artificial BioChemical Networks" (ABN) they have been presented as an alternative approach to connectionist systems.
50
Parker, Christopher Alonzo. "K x N Trust-Based Agent Reputation". VCU Scholars Compass, 2006. http://scholarscompass.vcu.edu/etd/702.
Texto completoResumen
In this research, a multi-agent system called KMAS is presented that models an environment of intelligent, autonomous, rational, and adaptive agents that reason about trust, and adapt trust based on experience. Agents reason and adapt using a modification of the k-Nearest Neighbor algorithm called (k X n) Nearest Neighbor where k neighbors recommend reputation values for trust during each of n interactions. Reputation allows a single agent to receive recommendations about the trustworthiness of others. One goal is to present a recommendation model of trust that outperforms MAS architectures relying solely on direct agent interaction. A second goal is to converge KMAS to an emergent system state where only successful cooperation is allowed. Three experiments are chosen to compare KMAS against a non-(k X n) MAS, and between different variations of KMAS execution. Research results show KMAS converges to the desired state, and in the context of this research, KMAS outperforms a direct interaction-based system.