ISEP - GECAD - Grupo de Investigação em Engenharia do Conhecimento a Apoio à Decisão
URI permanente desta comunidade:
GECAD is a research unit settled in the Institute of Engineering - Polytechnic of Porto (ISEP/IPP) having as mission the promotion and development of scientific research in the Knowledge and Decision Sciences domains, having Information Technologies as support. It involves 2 research groups: Intelligent Systems and Power Energy Systems. GECAD is known worldwide in its areas of research, leading some research domains. [-]
GECAD is coordinated by Prof. Zita Vale, and recognized by FCT (Portuguese Science and Technology Foundation). 79 researchers are involved in GECAD, including 37 with PhD degree. It is the largest R&D unit from the Polytechnic sub-system of Portugal.
GECAD was involved in more than 60 R&D projects (more than 20 on-going projects now) with external funding. We are one of the Portuguese R&D units with more success at this level. Just a number, 8, is the number of projects assigned to GECAD in the last FCT Call for Projects. GECAD has a tremendous success in publications in important scientific journals; many special issues of these journals are edited by GECAD researchers.
Understanding its responsibility for the Society development, GECAD has decided to adopt a new slogan: “Intelligence for a Sustainable, Safe, and Inclusive World”. For this reason, the most recent GECAD projects are applied to areas like Energy, Transportation, Environment, Economy, Inclusion, Critical Infrastructures, Security, Information Access and new ways of Socialization.
Navegar
Percorrer ISEP - GECAD - Grupo de Investigação em Engenharia do Conhecimento a Apoio à Decisão por contribuidor "Ramos, Carlos"
A mostrar 1 - 10 de 10
Resultados por página
Opções de ordenação
- An agent-based approach to support decisions on electronic marketplacesPublication . Viamonte, Maria João; Ramos, Carlos; Rodrigues, Maria de Fátima Coutinho; Cardoso, José; Ramos, Carlos; Vale, ZitaWith the increasing importance of Electronic Commerce across the Internet the need for software agents to support both customers and suppliers in buying and selling goods/services is growing rapidly. It is becoming increasingly evident that in a few years the Internet will host a large number of interacting software agents. Most of them will be economically motivated, and will negotiate a variety of goods and services. It is therefore important to consider the economic incentives and behaviours of economic software agents, and to use all available means to anticipate their collective interactions. This paper addresses this concern by presenting a Market Simulator designed for analysing agent market strategies based on a complete understanding of buyer and seller behaviours, preference models and pricing algorithms. The system includes agents that are capable of increasing their performance with their own experience, by adapting to the market conditions. The results of the negotiations between agents will be analysed by Data mining tools in order to extract rules that will give the agents feedback to improve their strategies. We will describe the characteristics and technologies involved in the architecture we are specifying and developing.
- An architecture to integrate discovered knowledge in a rule based systemPublication . Oliveira, Paulo; Rodrigues, Maria de Fátima Coutinho; Ramos, Carlos; Vale, ZitaThe techniques and tools of Knowledge Discovery in Databases seek to transform data into knowledge in an “intelligent” and semi-automatic way. One of the possible uses to this discovered knowledge consists in its integration or fusion with the knowledge that is in the knowledge base of an Expert System. It thus complements the knowledge . initially given by the expert, which is not always complete, or the most up-to-date. Using an alternative source it is possible to discover knowledge that is implicit in data, and then proceed with its fusion with the one already in the knowledge base. However, this process can result in errors appearing (for example, inconsistencies) in the knowledge base resulting from the fusion. Thus, one of the requirements to fulfil is the consistency and correction of this new knowledge base. A generic and domain independent architecture that allows a rule based knowledge fusion, in the context above described is presented. Consistency and correction are guaranteed through the detection of errors, and by the adoption of an approach based in maximal consistent subsets of rules.
- A constraint based approach to the maintenance scheduling on electrical power distribution networksPublication . Pinheiro, Raul; Gomes, Nuno; Vale, Zita; Ramos, Carlos; Vale, ZitaPower distribution network exploration involves the scheduling of multiple maintenance and unforeseen repair tasks. The scheduling of these tasks is subject to topological, economical and electrical constraints. By is mature, problem modelling is a hard task. Traditional methods have great difficulties on dealing with such complex problems. Constraint Logic Programming (CLP) has great modelling capacities and so it seams the right tool to deal with them. On this work, we propose a new CLP method to solve the problem. This method deals with the electrical constraints on a different manner, avoiding many load flow calculations by means of performing what is known as contingency analysis on electrical networks, reducing computational complexity and speeding the calculations.
- Decision support for power system control centers – a model based reasoning componentPublication . Malheiro, Nuno; Vale, Zita; Ramos, Carlos; Cordeiro, Manuel; Marques, Albino; Couto, Vieira; Ramos, Carlos; Vale, ZitaThe increasing demand on Power System Control Centers (PSCC) for optimization of the use of the Electrical Network implies, as one of its key focuses, the fastest possible restoration of service. Human PSCC operators (PSCCO) control the Electrical Network aided by a distributed system of sensors and actuators, which produce temporal information about the networks’ state. These distributed systems are known as Supervisory Control and Data acquisition or SCADA systems. In incident situations, in which SCADA systems can produce huge amounts of information, PSCCOs can become very stressed and loose the necessary focus to perform an accurate diagnosis and hence proper power restoration. Several approaches have been made to develop systems which can cope with the particularly hard features of this problem in real-time. This paper presents a model based teasoning component which is integrated in a multicomponent system with the task of Electrical Network diagnosis and restoration. This particular component adds adaptability to the system ensuring correct behaviour on any topological variation of the part of the electrical network in service or its protection schemes. The whole system is fully functional and operating in the Portuguese Electrical Network Dispatch Center.
- Fabricare: an agent-based system for manufacturingPublication . Sousa, Paulo; Neves, José; Ramos, Carlos; Ramos, Carlos; Vale, ZitaDue to current and future trends in manufacturing, computer-supported manufacturing systems are now more distributed than the traditional CIM approach. This paper presents a prototype system for the problem of scheduling of manufacturing orders, focusing on the internal implementation of each type of agent in the system.
- Hybrid methods for the maintenance scheduling of generating units problemPublication . Gomes, Nuno; Cordeiro, Manuel; Vale, Zita; Ramos, Carlos; Ramos, Carlos; Vale, ZitaReal world search and optimization problems are usually characterized by having large search spaces, being difficult to model and being constantly changing. Constraint Logic Programming (CLP) has proved to be a good tool to model and solve this type of problems despite some efficiency problems. It seams that the problem is related to some lack of a “global perspective” of the constraints in the search process, One way of overcoming this problem is to hybridize Constraint Logic Programming with Linear Programming (LP) in order to enhance the solving process by finding feasible solutions early in the search by “global reasoning”. In this work we propose 4 hybrid methods for solving a Maintenance Scheduling of Generating Units problem. The main idea is to take the advantages of both CLP and LP avoiding their problems. Some initial tests show that for some conditions all the hybrid methods can perform better than CLP alone.
- Proposal for the combination of ontology assemble and ontology mapping processesPublication . Silva, Nuno; Santos, Jorge; Rocha, João; Ramos, Carlos; Vale, ZitaOntology mapping is dependent on the matching algorithms, which in turn depends on the semantics of the ontologies. This proposal grounds on two distinct technologies: ontology mapping and ontology assemble. The ontology mapping system is a service-oriented system in which autonomous plug-able services capture and represent the ontology mapping domain’s expertise. Automatic ontology mapping systems perform poorly due to the lack of ontologies’ semantics to reason upon. The assemble process aims to integrate well-founded, proofed knowledge into the domain ontologies, providing extra semantics. Exploiting such semantics indistinct phases of the ontology mapping process, we envisage that such semantics would be very useful in the improvement of the automatic mapping results. Conversely, the ontology mapping experiences would provide feed-back to the assemble process, suggesting its improvement too. The cyclic improvement would run indefinitely. This paper suggests therefore the combination of efforts from both the assemble and mapping processes towards a better semantic relations and assembled ontologies.
- Service-oriented semi-automatic ontology bridgingPublication . Silva, Nuno; Rocha, João; Ramos, Carlos; Vale, ZitaWith the advent of Semantic Web, knowledge-based interoperability faces a new technological shift, in which ontologies and semantic web technologies play a major role. Exploiting the explicit semantic description of the domain of discourse allows reasoning and automatically acquiring semantic relations between two different domains of discourses. Such semantic relations would be further applied in converting data or documents between such domains. This process is named Ontology Mapping. This paper proposes a semi-automatic bridging process, based in the idea that while automatic matching algorithms do not provide enough information to overcome semantic heterogeneity, they represent valuable sources of similarities measurements between ontologies’ entities, which can be combined into an overall similarity measure according to each service specific requirements.
- Software configuration management: orthogonal dimensions for systems evolutionPublication . Novais, Paulo; Oliveira Lima, Luís Carlos; Ramos, Carlos; Ramos, Carlos; Vale, ZitaThis paper presents an overview of the tasks and limitations of traditional Software Configuration Management systems. In addition to the familiar check-in/check-out model, a brief characterization of another three configuration management models found in SCM tools is presented. Three dimensions for software systems evolution are considered: time, space and team cooperation. A case study is presented to exemplify the three dimensions of evolution. Reasoning for the need of a new data model representation supporting the three dimensions, viewed as orthogonal to each other, is also presented.
- Strategic coalition impact on transmission costsPublication . Ferreira, Judite; Gonçalves, Manuel João D.; Vale, Zita; Ramos, Carlos; Vale, ZitaIn a liberalized electric power market one of the main goals is equal opportunity of market and network access for each participant. However, the possibility of agents (sellers) strategic coalition actions can limit the accessibility of some participants to the market. This kind of actions can affect the transmission network use allocated costs for each transaction. These costs are divided in a different way that can penalize the sellers outside the strategic coalition. In this paper we present a comparative study of transmission costs allocated to each seller in a scenario with and without transmission congestion effects due to coalitions of two sellers. The paper includes a case study considering coalition scenarios selected after a power market evaluation.