Providing energy efficiency location-based strategies for buildings using linked open data

Dissertation submitted in partial fulfillment of the requirements for the Degree of Master of Science in Geospatial Technologies.

Probabilistic constraint reasoning

Dissertação apresentada para obtenção do Grau de Doutor em Engenharia Informática, pela Universidade Nova de Lisboa, Faculdade de Ciências e Tecnologia

Building clusters for CRM strategies by mining airlines customer data

Trabalho de Projeto apresentado como requisito parcial para obtenção do grau de Mestre em Estatística e Gestão de Informação

Detecting and evaluating land cover change in the eastern half of East Timor (1972-2011)

Dissertation submitted in partial fulfillment of the requirements for the Degree of Master of Science in Geospatial Technologies.

Metodologia da determinação de prioridades no planeamento regional de saúde : uma proposta

RESUMO - O estabelecimento de prioridades determina a sustentabilidade de qualquer sistema de saúde, pelo que urge identificar os procedimentos, metodologias e critérios de priorização. Não existem critérios nem métodos universais de os combinar, sendo que a sua seleção depende do contexto de aplicação. O presente projeto de estudo exploratório-descritivo tem por finalidade a criação de uma proposta de metodologia a adotar na determinação de prioridades do Plano Regional de Saúde de Lisboa e Vale do Tejo 2011-2016, contextualizada à região, tempo e circunstâncias. O estudo está organizado em duas etapas metodológicas: uma revisão bibliográfica, dirigida à identificação do método e dos critérios de determinação de prioridades, e a realização de um painel de Delphi, para validação do método de determinação de prioridades proposto, definição dos critérios e suas ponderações. Tendo sido encontrada evidência na literatura sobre as vantagens da utilização da Análise Multicritério da Tomada de Decisão, através da utilização do Método Aditivo Linear, na determinação de prioridades em saúde, foi selecionada esta metodologia, que obteve a concordância de 85% dos participantes para a sua utilização no contexto em estudo, na primeira ronda do painel de Delphi. Os resultados preliminares do estudo, obtidos na primeira ronda, mostram que um dos onze critérios propostos foi excluído, tendo sido sugeridos sete novos critérios pelos participantes, que serão sujeitos a análise nas rondas subsequentes. Os resultados obtidos poderão servir de base a estudos mais aprofundados nesta área e contribuir para o debate sobre os critérios subjacentes ao processo de determinação de prioridades em saúde.

Geospatial technologies for public participation: better decisions for smarter cities?

Dissertation submitted in partial fulfillment of the requirements for the Degree of Master of Science in Geospatial Technologies.

Politicization of non-political events

Spatial analysis and social network analysis typically take into consideration social processes in specific contexts of geographical or network space. The research in political science increasingly strives to model heterogeneity and spatial dependence. To better understand and geographically model the relationship between “non-political” events, streaming data from social networks, and political climate was the primary objective of the current study. Geographic information systems (GIS) are useful tools in the organization and analysis of streaming data from social networks. In this study, geographical and statistical analysis were combined in order to define the temporal and spatial nature of the data eminating from the popular social network Twitter during the 2014 FIFA World Cup. The study spans the entire globe because Twitter’s geotagging function, the fundamental data that makes this study possible, is not limited to a geographic area. By examining the public reactions to an inherenlty non-political event, this study serves to illuminate broader questions about social behavior and spatial dependence. From a practical perspective, the analyses demonstrate how the discussion of political topics fluсtuate according to football matches. Tableau and Rapidminer, in addition to a set basic statistical methods, were applied to find patterns in the social behavior in space and time in different geographic regions. It was found some insight into the relationship between an ostensibly non-political event – the World Cup - and public opinion transmitted by social media. The methodology could serve as a prototype for future studies and guide policy makers in governmental and non-governmental organizations in gauging the public opinion in certain geographic locations.

O processo de dádiva de sangue do dador de primeira vez no Hospital do Espírito Santo - Évora, EPE : satisfação e retorno para a dádiva seguinte

RESUMO - Introdução: Com este trabalho, pretendeu-se averiguar em que medida a satisfação no processo de dádiva de sangue afeta o regresso dos dadores que doam pela primeira vez na vida, ou que se apresentaram pela primeira vez no Serviço de sangue do HESE. Material e métodos: Estudo observacional transversal descritivo. Dos dadores com uma única inscrição no período de 2011 a 2012 inclusive, (531+541 dadores) foram retirados os que entretanto completaram 66 anos (idade limite para a dádiva); os que não tinham contacto telefónico válido; e os que tinham morada fora do Distrito de Évora. Os dadores restantes (327 + 330 dadores), foram então inquiridos através de um questionário efetuado telefonicamente para determinar as causas de não regresso. Resultados: Obtiveram-se 360 respostas válidas ao questionário, correspondentes a 50% da amostra com um IC de 95%. Apesar de estar amplamente demonstrado que a satisfação na dádiva contribui decisivamente para o retorno à dádiva seguinte, apenas 12% da amostra referiu não regressar por algum motivo de insatisfação decorrente do processo de dádiva. Evidentemente, o mérito destes resultados é devido à equipa do Serviço de Imunohemoterapia do HESE. Porém uma outra realidade fica aqui patente, os dadores de primeira vez estão a decrescer há vários anos, e destes, os que regressam são cada vez menos. A manter-se esta tendência, a taxa de renovação da bolsa de dadores poderá tornar-se insuficiente para a manutenção da atual bolsa de dadores. Se o HESE conseguisse recuperar para a dádiva metade da amostra de dadores de primeira vez que não regressam, a sua autonomia em termos de consumo de sangue sairia reforçada, com o incremento de proveitos financeiros consequente. Conclusão: Este trabalho concretiza os objetivos a que se propôs, nomeadamente o de produzir conhecimento útil e de suporte à decisão no âmbito da administração hospitalar. O HESE tem agora ao seu dispor, a caraterização dos dadores de primeira vez e a descrição de como se está a processar a renovação da sua bolsa de dadores.

Questionário de satisfação do utente e do profissional : impacto num laboratório de análises clínicas

RESUMO: Temos assistido a uma evolução impressionante nos laboratórios de análises clínicas, os quais precisam de prestar um serviço de excelência a custos cada vez mais competitivos. Nos laboratórios os sistemas de gestão da qualidade têm uma importância significativa nesta evolução, fundamentalmente pela procura da melhoria continua, que ocorre não só ao nível de processos e técnicas, mas também na qualificação dos diferentes intervenientes. Um dos problemas fundamentais da gestão e um laboratório é a eliminação de desperdícios e erros criando benefícios, conceito base na filosofia LeanThinking isto é “pensamento magro”, pelo que é essencial conseguir monitorizar funções críticas sistematicamente. Esta monitorização, num laboratório cada vez mais focalizado no utente, pode ser efetuada através de sistemas e tecnologias de informação, sendo possível contabilizar número de utentes, horas de maior afluência, tempo médio de permanência na sala de espera, tempo médio para entrega de análises, resultados entregues fora da data prevista, entre outros dados de apoio à decisão. Devem igualmente ser analisadas as reclamações, bem como a satisfação dos utentes quer através do feedback que é transmitido aos funcionários, quer através de questionários de satisfação. Usou-se principalmente dois modelos: um proposto pelo Índice Europeu de Satisfação do Consumidor (ECSI) e o outro de Estrutura Comum de Avaliação (CAF). Introduziram-se igualmente dois questionários: um apresentado em formato digital num posto de colheitas, através de um quiosque eletrónico, e um outro na página da internet do laboratório, ambos como alternativa ao questionário em papel já existente, tendo-se analisado os dados, e retirado as devidas conclusões. Propôs-se e desenvolveu-se um questionário para colaboradores cuja intenção foi a de fornecer dados úteis de apoio à decisão, face à importância dos funcionários na interação com os clientes e na garantia da qualidade ao longo de todo o processo. Avaliaram-se globalmente os resultados sem que tenha sido possível apresentá-los por política interna da empresa, bem como se comentou de forma empírica alguns benefícios deste questionário. Os principais objetivos deste trabalho foram, implementar questionários de satisfação eletrónicos e analisar os resultados obtidos, comparando-os com o estudo ECSI, de forma a acentuar a importância da análise em simultâneo de dois fatores: a motivação profissional e a satisfação do cliente, com o intuito de melhorar os sistemas de apoio à decisão. ------------------------ ABSTRACT: We have witnessed an impressive development in clinical analysis laboratories, which have to provide excellent service at increasingly competitive costs, quality management systems have a significant importance in this evolution, mainly by demanding continuous improvement, which does not occur only in terms of processes and techniques, but also in the qualification of the various stakeholders. One key problem of managing a laboratory is the elimination of waste and errors, creating benefits, concept based on Lean Thinking philosophy, therefore it is essential be able to monitor critical tasks systematically. This monitoring, in an increasingly focused on the user laboratory can be accomplished through information systems and technologies, through which it is possible to account the number of clients, peak times, average length of waiting room stay, average time for delivery analysis, delivered results out of the expected date, among other data that contribute to support decisions, however it is also decisive to analyzed complaint sand satisfaction of users through employees feedback but mainly through satisfaction questionnaires that provides accurate results. We use mainly two models one proposed by the European Index of Consumer Satisfaction (ECSI), directed to the client, and the Common Assessment Framework (CAF), used both in the client as the employees surveys. Introduced two questionnaires in a digital format, one in the central laboratory collect center, through an electronic kiosk and another on the laboratory web page, both as an alternative to survey paper currently used, we analyzed the results, and withdrew the conclusions. It was proposed and developed a questionnaire for employees whose intention would be to provide useful data to decision support, given the importance of employees in customer interaction and quality assurance throughout the whole clinical process, it was evaluated in a general way because it was not possible to show the results, however commented an empirical way some benefits of this questionnaire. The main goals of this study were to implement electronic questionnaires and analyze the results, comparing them with the ECSI, in order to emphasize the importance of analyzing simultaneously professional motivation with customer satisfaction, in order to improve decision support systems.

An essay on agile project management practices

The main goals for the current dissertation is to research on how practices and concepts from Agile Project Management can be applied in a non-IT context and to discover which aspects should be considered when deciding if whether an Agile approach should be implemented or not. Previous studies reflect on the adoption for the identified context. However, the recognition of these practices and concepts by the Project Management field of studies still remains unresolved. The adoption of Agile Project Management emerges as a manifestation against traditional approaches, mainly due to their inability of accepting requirements’ changes. Therefore, these practices and concepts can be considered in order to reduce the risks concerning the increase of competition and innovation – which does not apply to the IT sector solely. The current study reviews the literature on Agile Project Management and its adoption across different sectors in order to assess which practices and concepts can be applied on a non-IT context. Nine different methods are reviewed, where two of these show a higher relevance – Scrum and Extreme Programming. The identified practices and concepts can be separated into four different groups: Cultural and Organizational Structures, Process, Practices, and Artefacts. A framework based on the work by Boehm & Turner in 2004 is developed in order to support the decision of adopting agile methods. A survey intended for project managers was carried in order to assess the implementation of the identified practices and concepts and to evaluate which variables have the highest importance on the developed decision support framework. It is concluded that New Product Development is the project type with the highest potential to implement an agile approach and that the Project Final Product’s Innovativeness, Competitiveness, and the Project Member’s Experience and Autonomy are the most important aspects to consider an implementation of an Agile approach.

Semantic architecture for sensors

Based on the report for the unit “Sociology of New Information Technologies” of the Master on Computer Sciences at FCT/University Nova Lisbon in 2015-16. The responsible of this curricular unit is Prof. António Moniz

Business intelligence in banking: A literature analysis from 2002 to 2013 using Text Mining and latent Dirichlet allocation

telligence applications for the banking industry. Searches were performed in relevant journals resulting in 219 articles published between 2002 and 2013. To analyze such a large number of manuscripts, text mining techniques were used in pursuit for relevant terms on both business intelligence and banking domains. Moreover, the latent Dirichlet allocation modeling was used in or- der to group articles in several relevant topics. The analysis was conducted using a dictionary of terms belonging to both banking and business intelli- gence domains. Such procedure allowed for the identification of relationships between terms and topics grouping articles, enabling to emerge hypotheses regarding research directions. To confirm such hypotheses, relevant articles were collected and scrutinized, allowing to validate the text mining proce- dure. The results show that credit in banking is clearly the main application trend, particularly predicting risk and thus supporting credit approval or de- nial. There is also a relevant interest in bankruptcy and fraud prediction. Customer retention seems to be associated, although weakly, with targeting, justifying bank offers to reduce churn. In addition, a large number of ar- ticles focused more on business intelligence techniques and its applications, using the banking industry just for evaluation, thus, not clearly acclaiming for benefits in the banking business. By identifying these current research topics, this study also highlights opportunities for future research.

Clustering-based approach for categorizing pregnant women in obstetrics and maternity care

When a pregnant woman is guided to a hospital for obstetrics purposes, many outcomes are possible, depending on her current conditions. An improved understanding of these conditions could provide a more direct medical approach by categorizing the different types of patients, enabling a faster response to risk situations, and therefore increasing the quality of services. In this case study, the characteristics of the patients admitted in the maternity care unit of Centro Hospitalar of Porto are acknowledged, allowing categorizing the patient women through clustering techniques. The main goal is to predict the patients’ route through the maternity care, adapting the services according to their conditions, providing the best clinical decisions and a cost-effective treatment to patients. The models developed presented very interesting results, being the best clustering evaluation index: 0.65. The evaluation of the clustering algorithms proved the viability of using clustering based data mining models to characterize pregnant patients, identifying which conditions can be used as an alert to prevent the occurrence of medical complications.

Plataforma para suporte ao ciclo de vida de organizações virtuais e seleção dinâmica de parceiros e fornecedores

Tese de Doutoramento em Engenharia Industrial e de Sistemas

Abstract computation in schizophrenia detection through artificial neural network based systems

Schizophrenia stands for a long-lasting state of mental uncertainty that may bring to an end the relation among behavior, thought, and emotion; that is, it may lead to unreliable perception, not suitable actions and feelings, and a sense of mental fragmentation. Indeed, its diagnosis is done over a large period of time; continuos signs of the disturbance persist for at least 6 (six) months. Once detected, the psychiatrist diagnosis is made through the clinical interview and a series of psychic tests, addressed mainly to avoid the diagnosis of other mental states or diseases. Undeniably, the main problem with identifying schizophrenia is the difficulty to distinguish its symptoms from those associated to different untidiness or roles. Therefore, this work will focus on the development of a diagnostic support system, in terms of its knowledge representation and reasoning procedures, based on a blended of Logic Programming and Artificial Neural Networks approaches to computing, taking advantage of a novel approach to knowledge representation and reasoning, which aims to solve the problems associated in the handling (i.e., to stand for and reason) of defective information.