ISEP - Departamento de Engenharia Informática
URI permanente desta comunidade:
Navegar
Percorrer ISEP - Departamento de Engenharia Informática por título
A mostrar 1 - 10 de 64
Resultados por página
Opções de ordenação
- Abordagens ao Problema de Escalonamento em Ambientes Reais de ProduçãoPublication . Madureira, Ana Maria; Almeida, Ana[Resumo] Num sistema de fabrico do tipo Job-Shop podem ser identificados alguns factores que contribuem para a dificuldade do processo de escalonamento, nomeadamente, a complexidade, as restrições e a incerteza. Os ambientes industriais reais são sujeitos a várias fontes de mudança, as quais são tratadas como ocorrências aleatórias, tais como, lançamento de novas ordens de fabrico, avarias, alterações de prioridades, atrasos nas operações, etc. Por escalonamento dinâmico consideramos a situação na qual um plano flexível é executado, isto é, o plano inicial é dinamicamente ajustado (re-escalonado) sempre que eventos inesperados ocorrem no sistema. Esta comunicação tem por objectivo principal efectuar uma sistematização de conceitos e classificações de problemas e tipos de escalonamento, bem como das abordagens usadas na sua resolução. Inicialmente, é apresentado o problema de escalonamento, através da caracterização dos seus elementos e da referência a algumas definições encontradas na literatura, A seguir descrevem-se algumas classificações para os problemas de escalonamento e os tipos de abordagens de resolução a adoptar. Finalmente, são propostas duas arquitecturas para a resolução do problema de escalonamento em ambientes reais de produção caracterizados por um elevado grau de dinamismo. À primeira baseada em Sistemas de Apoio à Decisão e a segunda em Algoritmos Genéticos.
- Advancing recruitment: fair and efficient resume screening with LLMsPublication . Novais, Liliana; Rocio, Vitor; Oliveira, Paulo Moura; Santos, ArnaldoTraditional talent acquisition encounters significant sustainability problems marked by increasing application quantities and the intrinsic dangers of subjective human bias. This article, which is still being worked on, uses the Design Science Research (DSR) technique to create CurAIEval, a new IT tool for automated, fairness-aware resume screening. Based on a rigorous examination of the literature, the study finds a fundamental gap between technical optimization and ethical governance. To close this gap, the suggested architecture combines Large Language Models (LLMs) for semantic analysis with a required "Fairness-by-Design" auditing engine. The system uses a Human-in-the-Loop (HITL) protocol to automate parsing of large amounts of data while still letting people make the ultimate judgments. Expected outcomes encompass the creation of a workable prototype that substantially alleviates administrative burdens and the validation of a Balanced KPI Framework. This approach is meant to quantify both operational efficiency (like time-to-hire) and algorithmic fairness (like disparate impact) at the same time. It gives a validated technique to automate hiring in a responsible and fair way.
- Automated extraction of insurance product characteristicsPublication . Oliveira, Francisco; Sousa, Paulo Gandra de; Faria, Luiz; Faria, Luiz; Cardoso, Duarte; Teixeira, JoãoThe increasing complexity and diversity of insurance products have highlighted the need for efficient methods to interpret and manage the detailed information present in regulatory documents. This project explores the application of Natural Language Processing (NLP) and Large Language Models (LLMs) in the automatic extraction of relevant characteristics of these products, addressing challenges such as structuring technical texts and accurately identifying rules, conditions, and variations. The research focuses on analyzing the state of the art in technologies such as vector databases, LLMs, knowledge graphs, and agentic workflows, as well as evaluating NLP tools and methodologies. The text goes on to explore the primary challenges encountered during the interpretation of insurance documentation, as well as the transformation of unstructured data into organized formats that are compatible with modelling systems. The solution developed responded satisfactorily to the objectives established, enabling the structured and consistent extraction of product characteristics from regulatory documents. To this end, AI agent-based workflows were used, supported by LLMs and validation schemes, ensuring the quality and consistency of the results.
- Braço ótico com controle Arduíno para medição do índice de refraçãoPublication . Moreira, Ana Rita; Ramos, Carlos; Oliveira Vilão de Ramos, Gina MariaA automação em contexto laboratorial tem reforçado a precisão e a reprodutibilidade das medições no domínio biomédico. Neste trabalho descreve-se um sistema robótico automatizado para determinar o índice de refração de tecidos biológicos através do ângulo de Brewster, integrando controlo motorizado, aquisição sensorial e análise computacional. O protótipo, composto por motores de passo controlados por Arduino e por um fotodetetor com processamento em tempo real numa interface Python, realiza varrimentos angulares sincronizados e identifica autonomamente o ponto mínimo de refletância, completando todo o ciclo de medição. Em material de referência obteve-se um ângulo de Brewster de 56,2° e um índice de 1,495 com erro inferior a 0,5%, enquanto nos ensaios com tecido muscular os valores variaram entre 1,375 e 1,393, refletindo a influência da orientação das fibras. Os resultados confirmam a precisão e a repetibilidade do sistema, demonstrando o seu potencial como solução acessível para caracterização ótica de tecidos biológicos.
- C Tutor usage in relation to student achievement and progress: A study of introductory programming courses in Portugal and SerbiaPublication . Alves, Luís; Gajić, Dušan; Henriques, Pedro Rangel; Ivančević, Vladimir; Ivković, Vladimir; Lalić, Maksim; Luković, Ivan; Pereira, Maria João Varanda; Popov, Srđan; Tavares, Paula CorreiaPrevious research studies on introductory programming courses in engineering education in Portugal and Serbia have indicated that although high motivation and high expectations seem to be reported by students, many students may fail the course. This prompted a further inquiry into student attitudes, behavior, and achievement, and it also led to the introduction of C Tutor, a widely known program visualization tool, into courses in both countries. As a result, in the present study, self-reported student achievement (grades), self-reported student progress (knowledge improvement and confidence), and self-reported usage and helpfulness of C Tutor were investigated. Anonymous data about students and their experience in the course, which also included the usage of C Tutor, were collected in a survey in Portugal and Serbia. Quantitative methods, including descriptive statistics, clustering, statistical testing of independence, and partial correlation analysis, were applied in analyses of survey data. The distribution of grades differed between the two countries, but overall attitudes were similar. Various uncovered patterns involving student attitudes and usage of C Tutor may serve as a starting point for new research studies.
- CEPP: Conversion and execution of process plansPublication . Ramos, Carlos; Figueiredo, LinoThis paper deals with a method to produce a program in numerical control (NC) language from a part drawing in a CAD system. This method is applied to any piece with revolution axis that can be machined in a CNC lathe. The method was developed with the goal of being integrated in the control software of the flexible manufacturing system existent in the CIM center of ISEP. The proposed method involves three phases, which are presented and explained.
- Characterization of mv consumers using hierarchical clusteringPublication . Figueiredo, V.; Pinheiro, R.; Carvalho Ramos, Sérgio Filipe; Rodrigues, Maria de Fátima Coutinho; Vale, Zita; Ramos, Carlos; Vale, ZitaWith the electricity market liberalization, distribution and retail companies are looking for better market strategies based on adequate information upon the consumption patterns of its electricity customers. A fair insight on the customers’ behaviour will permit the definition of specific contract aspects based on the different, consumption patterns. In this paper, we propose a Knowledge Discovery in Databases project applied to electricity consumption data from a utility client’s database. To form the different customers’ classes, and find a set of representative consumption patterns, we have used the Two-Step algorithm which is a hierarchical clustering algorithm. Each consumer class will be represented by its load profile resulting from the clustering operation. Next, to characterize each consumer class a classification model will be constructed with the C5.0 classification algorithm.
- Cliente mobile e desktop de comunicações unificadas para IPBrick OSPublication . Paiva, Diogo; Ramalhão, Miguel; Campos, Carlos José; Lima, Veríssimo; Reis, Pedro; Cardoso, Vitor; Aires, Sandra; Pinto, Carla; Carvalho, Fernando; Sousa, AntónioO IPBRICK OS é um sistema operativo baseado em Linux Debian, concebido para suportar as soluções empresariais da IPBRICK no domínio das Comunicações Unificadas sobre IP (UCoIP) e Ferramentas Colaborativas para Gestão de Documentos e Processos. Entre os serviços UCoIP integrados pelo módulo IPBRICK.PBX (baseado em Asterisk), destaca-se o Voice Over Internet Protocol (VoIP), por norma, suportado por um conjunto distribuído de servidores que executam, entre outros, os protocolos Session Initiation Protocol (SIP), responsável pela sinalização e gestão de chamadas, e o Real-Time Transport Protocol (RTP), que assegura a transmissão de áudio em tempo real. A versão 8.0 exigiu a implementação e integração de uma aplicação cliente Mobile e Desktop de Comunicações Unificadas (softphone VoIP) que privilegia a simplicidade de configuração, a eficiência de utilização e a estética do IPBRICK OS. Nesse sentido, este trabalho apresenta uma aplicação softphone VoIP responsiva, implementada em Dart através da framework Flutter. É baseada numa arquitetura cliente-servidor, em que a comunicação é realizada via HTTP, recorrendo a APIs PHP que estabelecem a interface com o servidor SIP. Deste modo, descrevem-se os principais aspetos técnicos e arquiteturais da solução proposta, incluindo a modelação dos fluxos de comunicação, a estrutura das APIs e os layouts funcionais da interface gráfica. Apresentam-se ainda diagramas de fluxo e os protótipos de ecrã das principais componentes da aplicação – autenticação Lightweight Directory Access Protocol (LDAP), interface principal, teclado de marcação, lista de contactos, registo de histórico e de chamadas.
- Computational Intelligence and Decision Making: Trends and ApplicationsPublication . Madureira, Ana Maria; Reis, Cecília; Marques, ViriatoAdvances in Computational Intelligence and Decision Making: Trends and Applications provides an overview and original analysis of new developments and applications in several areas of Computational Intelligence and Information Systems, in general. Computational Intelligence became the roadmap for engineers to develop and analyze novel techniques to solve problems in basic sciences such as physics, chemistry, biology, engineering, environment and social sciences. The material contained in this book addresses the foundations and applications of Artificial Intelligence and Decision Support Systems, Complex and Biological Inspired Systems, Simulation and Evolution of real and artificial life forms, Intelligent Models and Control Systems, Knowledge and Learning Technologies, Web Semantics and Ontologies, Intelligent Tutoring Systems, Intelligent Power Systems, Self-Organized and Distributed Systems, Intelligent Manufacturing Systems and Affective Computing. The contributions are written by international experts, who provide up-to-date aspects of the topics discussed and present recent, original insights of their own experience in these fields. Its aim is the presentation of state-of-the-art technologies in the field of Computational Intelligence as well as the discussion of new research findings in this field. The book is suitable for scientists, engineers, educators and students, as it addresses a large diversity of subjects presented in a broad band of complexity, ranging from simple natural language, found in some state-of-the-art articles, to some more complex mathematical issues, found in control applications, robotics and power systems, such as fractional calculus, fuzzy systems and rough-sets theory. Data Mining techniques, such as Support-Vector Machines and Neural Networks, are presented in application of the Biomedical and Bioinformatics fields, among others. Briefly, we believe that this book provides a good window on most of the subjects that directly or indirectly make use of Computational Intelligence, also showing the contributions that it is already giving, or can be given in a near future, for solving some of the more pressing problems of today’s world, such as energy and environment, society and economy.
- Conceitos básicos para o desenvolvimento de cursos multimédiaPublication . Vaz de Carvalho, Carlos[Excerto] Este módulo pretende descrever, de forma necessariamente sintética, as etapas associadas à criação de cursos de e-learning multimédia. No final, o leitor deverá compreender os conceitos básicos da concepção e desenvolvimento de cursos multimédia e ajustá-los de acordo com as matérias a ensinar e com o perfil dos formandos (utilizadores). Deverá ainda dominar as principais fases do desenvolvimento de cursos multimédia - análise e especificação, concepção, desenvolvimento e integração, avaliação e manutenção - incluindo a compreensão da importância de cada etapa, as ferramentas a utilizar e as competências necessárias.