Integra����o de reac����o e delibera����o em agentes inteligentes

Trabalho Final de Mestrado para obten����o do grau de Mestre em Engenharia de Redes de Comunica����o e Multim��dia

Relat��rio de est��gio na Empresa Biodroid Entertainment

Trabalho Final de Mestrado para obten����o do grau de Mestre em Engenharia de Redes de Comunica����o e Multim��dia

An��lise do sistema de tratamento de efluentes gasosos de uma central de valoriza����o energ��tica de res��duos s��lidos urbanos

Trabalho Final de Mestrado para obten����o do grau de Mestre Em Engenharia Qu��mica e Biol��gica Ramo de processos Qu��micos

A hybrid genetic algorithm for the multi-mode resource-constrained project scheduling

A construction project is a group of discernible tasks or activities that are conduct-ed in a coordinated effort to accomplish one or more objectives. Construction projects re-quire varying levels of cost, time and other resources. To plan and schedule a construction project, activities must be defined sufficiently. The level of detail determines the number of activities contained within the project plan and schedule. So, finding feasible schedules which efficiently use scarce resources is a challenging task within project management. In this context, the well-known Resource Constrained Project Scheduling Problem (RCPSP) has been studied during the last decades. In the RCPSP the activities of a project have to be scheduled such that the makespan of the project is minimized. So, the technological precedence constraints have to be observed as well as limitations of the renewable resources required to accomplish the activities. Once started, an activity may not be interrupted. This problem has been extended to a more realistic model, the multi-mode resource con-strained project scheduling problem (MRCPSP), where each activity can be performed in one out of several modes. Each mode of an activity represents an alternative way of combining different levels of resource requirements with a related duration. Each renewable resource has a limited availability for the entire project such as manpower and machines. This paper presents a hybrid genetic algorithm for the multi-mode resource-constrained pro-ject scheduling problem, in which multiple execution modes are available for each of the ac-tivities of the project. The objective function is the minimization of the construction project completion time. To solve the problem, is applied a two-level genetic algorithm, which makes use of two separate levels and extend the parameterized schedule generation scheme. It is evaluated the quality of the schedules and presents detailed comparative computational re-sults for the MRCPSP, which reveal that this approach is a competitive algorithm.

Meta-heuristics self-parameterization in a multi-agent scheduling system using case-based reasoning

This paper proposes a novel agent-based approach to Meta-Heuristics self-configuration. Meta-heuristics are algorithms with parameters which need to be set up as efficient as possible in order to unsure its performance. A learning module for self-parameterization of Meta-heuristics (MH) in a Multi-Agent System (MAS) for resolution of scheduling problems is proposed in this work. The learning module is based on Case-based Reasoning (CBR) and two different integration approaches are proposed. A computational study is made for comparing the two CBR integration perspectives. Finally, some conclusions are reached and future work outlined.

Optimal offering strategies for wind power producers considering uncertainty and risk

This paper provides a two-stage stochastic programming approach for the development of optimal offering strategies for wind power producers. Uncertainty is related to electricity market prices and wind power production. A hybrid intelligent approach, combining wavelet transform, particle swarm optimization and adaptive-network-based fuzzy inference system, is used in this paper to generate plausible scenarios. Also, risk aversion is explicitly modeled using the conditional value-at-risk methodology. Results from a realistic case study, based on a wind farm in Portugal, are provided and analyzed. Finally, conclusions are duly drawn.

Integrating protein structural information

Disserta����o apresentada para obten����o de Grau de Doutor em Bioqu��mica,Bioqu��mica Estrutural, pela Universidade Nova de Lisboa, Faculdade de Ci��ncias e Tecnologia

Recomenda����o de conte��dos multim��dia

A quantidade e variedade de conte��dos multim��dia actualmente dispon��veis cons- tituem um desafio para os utilizadores dado que o espa��o de procura e escolha de fontes e conte��dos excede o tempo e a capacidade de processamento dos utilizado- res. Este problema da selec����o, em fun����o do perfil do utilizador, de informa����o em grandes conjuntos heterog��neos de dados �� complexo e requer ferramentas espec��ficas. Os Sistemas de Recomenda����o surgem neste contexto e s��o capazes de sugerir ao utilizador itens que se coadunam com os seus gostos, interesses ou necessidades, i.e., o seu perfil, recorrendo a metodologias de intelig��ncia artificial. O principal objectivo desta tese �� demonstrar que �� poss��vel recomendar em tempo ��til conte��dos multim��dia a partir do perfil pessoal e social do utilizador, recorrendo exclusivamente a fontes p��blicas e heterog��neas de dados. Neste sen- tido, concebeu-se e desenvolveu-se um Sistema de Recomenda����o de conte��dos multim��dia baseado no conte��do, i.e., nas caracter��sticas dos itens, no historial e prefer��ncias pessoais e nas interac����es sociais do utilizador. Os conte��dos mul- tim��dia recomendados, i.e., os itens sugeridos ao utilizador, s��o provenientes da esta����o televisiva brit��nica, British Broadcasting Corporation (BBC), e est��o classificados de acordo com as categorias dos programas da BBC. O perfil do utilizador �� constru��do levando em conta o historial, o contexto, as prefer��ncias pessoais e as actividades sociais. O YouTube �� a fonte do histo- rial pessoal utilizada, permitindo simular a principal fonte deste tipo de dados - a Set-Top Box (STB). O historial do utilizador �� constitu��do pelo conjunto de v��deos YouTube e programas da BBC vistos pelo utilizador. O conte��do dos v��deos do YouTube est�� classificado segundo as categorias de v��deo do pr��prio YouTube, sendo efectuado o mapeamento para as categorias dos programas da BBC. A informa����o social, que �� proveniente das redes sociais Facebook e Twit- ter, �� recolhida atrav��s da plataforma Beancounter. As actividades sociais do utilizador obtidas s��o filtradas para extrair os filmes e s��ries que s��o, por sua vez, enriquecidos semanticamente atrav��s do recurso a reposit��rios abertos de dados interligados. Neste caso, os filmes e s��ries s��o classificados atrav��s dos g��neros da IMDb e, posteriormente, mapeados para as categorias de programas da BBC. Por ��ltimo, a informa����o do contexto e das prefer��ncias expl��citas, atrav��s da classifica����o dos itens recomendados, do utilizador s��o tamb��m contempladas. O sistema desenvolvido efectua recomenda����es em tempo real baseado nas actividades das redes sociais Facebook e Twitter, no historial de v��deos Youtube e de programas da BBC vistos e prefer��ncias expl��citas. Foram realizados testes com cinco utilizadores e o tempo m��dio de resposta do sistema para criar o conjunto inicial de recomenda����es foi 30 s. As recomenda����es personalizadas s��o geradas e actualizadas mediante pedido expresso do utilizador.

Uso de Interfaces C��rebro-computador na comunica����o de pessoas com S��ndrome de Encarceramento

Os avan��os nas Interfaces C��rebro-m��quina, resultantes dos avan��os no tratamento de sinal e da intelig��ncia artificial, est��o a permitir-nos aceder �� atividade cerebral, descodific��-la, e us��la para comandar dispositivos, sejam eles bra��os artificiais ou computadores. Isto �� muito mais importante quando os utilizadores s��o pessoas que perderam a capacidade de comunicar, embora mantenham as suas capacidades cognitivas intactas. O caso mais extremo desta situa����o �� o das pessoas afetadas pela S��ndrome de Encarceramento. Este trabalho pretende contribuir para a melhoria da qualidade de vida das pessoas afetadas por esta s��ndrome, disponibilizando-lhes um meio de comunica����o adaptado ��s suas limita����es. �� essencialmente um estudo de usabilidade aplicada a um tipo de utilizador extremamente diminu��do na sua capacidade de intera����o. Nesta investiga����o come��amos por compreender a S��ndrome de Encarceramento e as limita����es e capacidades das pessoas afetadas por ela. Abordamos a neuroplasticidade, o que ��, e em que medida �� importante para a utiliza����o das Interfaces C��rebro-m��quina. Analisamos o funcionamento destas interfaces, e os fundamentos cient��ficos que o suportam. Finalmente, com todo este conhecimento em m��os, investigamos e desenvolvemos m��todos que nos permitissem otimizar as limitadas capacidades do utilizador na sua intera����o com o sistema, minimizando o esfor��o e maximizando o desempenho. Foi para o efeito desenhado e implementado um prot��tipo que nos permitisse validar as solu����es encontradas.

Share GFS ��� Games, Films & Series: sistema de recomenda����o

Esta disserta����o incide sobre o estudo e an��lise de uma solu����o para a cria����o de um sistema de recomenda����o para uma comunidade de consumidores de media e no consequente desenvolvimento da mesma cujo ��mbito inicial engloba consumidores de jogos, filmes e/ou s��ries, com o intuito de lhes proporcionar a oportunidade de partilharem experi��ncias, bem como manterem um registo das mesmas. Com a informa����o adquirida, o sistema re��ne condi����es para proceder a sugest��es direcionadas a cada membro da comunidade. O sistema atualiza a sua informa����o mediante as a����es e os dados fornecidos pelos membros, bem como pelo seu feedback ��s sugest��es. Esta aprendizagem ao longo do tempo permite que as sugest��es do sistema evoluam juntamente com a mudan��a de prefer��ncia dos membros ou se autocorrijam. O sistema toma iniciativa de sugerir mediante determinadas a����es, mas tamb��m pode ser invocada uma sugest��o diretamente pelo utilizador, na medida em que este n��o precisa de esperar por sugest��es, podendo pedir ao sistema que as forne��a num determinado momento. Nos testes realizados foi poss��vel apurar que o sistema de recomenda����o desenvolvido forneceu sugest��es adequadas a cada utilizador espec��fico, tomando em linha de conta as suas a����es pr��vias. Para al��m deste facto, o sistema n��o forneceu qualquer sugest��o quando o hist��rico destas tinha provado incomodar o utilizador.

Desenvolvimento de Ontologia para Apoio ao Diagn��stico de Dist��rbios do Humor

Mestrado em Computa����o e Instrumenta����o M��dica

Towards Active Course Marks for Autonomous Sailing Competitions

This paper describes the environmental monitoring / regatta beacon buoy under development at the Laboratory of Autonomous Systems (LSA) of the Polytechnic Institute of Porto. On the one hand, environmentalmonitoring of open water bodies in real or deferred time is essential to assess and make sensible decisions and, on the other hand, the broadcast in real time of position, water and wind related parameters allows autonomous boats to optimise their regatta performance. This proposal, rather than restraining the boats autonomy, fosters the development of intelligent behaviour by allowing the boats to focus on regatta strategy and tactics. The Nautical and Telemetric Application (NAUTA) buoy is a dual mode reconfigurable system that includes communications, control, data logging, sensing, storage and power subsystems. In environmental monitoring mode, the buoy gathers and stores data from several underwater and above water sensors and, in regatta mode, the buoy becomes an active course mark for the autonomous sailing boats in the vicinity. During a race, the buoy broadcasts its position, together with the wind and the water current local conditions, allowing autonomous boats to navigate towards and round the mark successfully. This project started with the specification of the requirements of the dual mode operation, followed by the design and building of the buoy structure. The research is currently focussed on the development of the modular, reconfigurable, open source-based control system. The NAUTA buoy is innovative, extensible and optimises the on board platform resources.

Personalised Advertising Supported by Agents

This paper reports the development of a B2B platform for the personalization of the publicity transmitted during the program intervals. The platform as a whole must ensure that the intervals are filled with ads compatible with the profile, context and expressed interests of the viewers. The platform acts as an electronic marketplace for advertising agencies (content producer companies) and multimedia content providers (content distribution companies). The companies, once registered at the platform, are represented by agents who negotiate automatically the price of the interval timeslots according to the specified price range and adaptation behaviour. The candidate ads for a given viewer interval are selected through a matching mechanism between ad, viewer and the current context (program being watched) profiles. The overall architecture of the platform consists of a multiagent system organized into three layers consisting of: (i) interface agents that interact with companies; (ii) enterprise agents that model the companies, and (iii) delegate agents that negotiate a specific ad or interval. The negotiation follows a variant of the Iterated Contract Net Interaction Protocol (ICNIP) and is based on the price/s offered by the advertising agencies to occupy the viewer���s interval.

Argumentation as Distributed Belief Revision: Conflict Resolution in Decentralised Multi-agent Systems

Decentralised co-operative multi-agent systems are computational systems where conflicts are frequent due to the nature of the represented knowledge. Negotiation methodologies, in this case argumentation based negotiation methodologies, were developed and applied to solve unforeseeable and, therefore, unavoidable conflicts. The supporting computational model is a distributed belief revision system where argumentation plays the decisive role of revision. The distributed belief revision system detects, isolates and solves, whenever possible, the identified conflicts. The detection and isolation of the conflicts is automatically performed by the distributed consistency mechanism and the resolution of the conflict, or belief revision, is achieved via argumentation. We propose and describe two argumentation protocols intended to solve different types of identified information conflicts: context dependent and context independent conflicts. While the protocol for context dependent conflicts generates new consensual alternatives, the latter chooses to adopt the soundest, strongest argument presented. The paper shows the suitability of using argumentation as a distributed decentralised belief revision protocol to solve unavoidable conflicts.

Solving Conflicting Beliefs with a Distributed Belief Revision Approach

The ability to solve conflicting beliefs is crucial for multi- agent systems where the information is dynamic, incomplete and dis- tributed over a group of autonomous agents. The proposed distributed belief revision approach consists of a distributed truth maintenance sy- stem and a set of autonomous belief revision methodologies. The agents have partial views and, frequently, hold disparate beliefs which are au- tomatically detected by system���s reason maintenance mechanism. The nature of these conflicts is dynamic and requires adequate methodolo- gies for conflict resolution. The two types of conflicting beliefs addressed in this paper are Context Dependent and Context Independent Conflicts which result, in the first case, from the assignment, by different agents, of opposite belief statuses to the same belief, and, in the latter case, from holding contradictory distinct beliefs. The belief revision methodology for solving Context Independent Con- flicts is, basically, a selection process based on the assessment of the cre- dibility of the opposing belief statuses. The belief revision methodology for solving Context Dependent Conflicts is, essentially, a search process for a consensual alternative based on a ���next best��� relaxation strategy.