Analysis of support for modularity in object teams based on design patterns

Dissertação de Mestrado em Engenharia Informática

A qualitative assessment of modularity in CaesarJ components based on implementations of design patterns

Tese de Mestrado em Engenharia Informática

Automatic learning for the classification of chemical reactions and in statistical thermodynamics

This Thesis describes the application of automatic learning methods for a) the classification of organic and metabolic reactions, and b) the mapping of Potential Energy Surfaces(PES). The classification of reactions was approached with two distinct methodologies: a representation of chemical reactions based on NMR data, and a representation of chemical reactions from the reaction equation based on the physico-chemical and topological features of chemical bonds. NMR-based classification of photochemical and enzymatic reactions. Photochemical and metabolic reactions were classified by Kohonen Self-Organizing Maps (Kohonen SOMs) and Random Forests (RFs) taking as input the difference between the 1H NMR spectra of the products and the reactants. The development of such a representation can be applied in automatic analysis of changes in the 1H NMR spectrum of a mixture and their interpretation in terms of the chemical reactions taking place. Examples of possible applications are the monitoring of reaction processes, evaluation of the stability of chemicals, or even the interpretation of metabonomic data. A Kohonen SOM trained with a data set of metabolic reactions catalysed by transferases was able to correctly classify 75% of an independent test set in terms of the EC number subclass. Random Forests improved the correct predictions to 79%. With photochemical reactions classified into 7 groups, an independent test set was classified with 86-93% accuracy. The data set of photochemical reactions was also used to simulate mixtures with two reactions occurring simultaneously. Kohonen SOMs and Feed-Forward Neural Networks (FFNNs) were trained to classify the reactions occurring in a mixture based on the 1H NMR spectra of the products and reactants. Kohonen SOMs allowed the correct assignment of 53-63% of the mixtures (in a test set). Counter-Propagation Neural Networks (CPNNs) gave origin to similar results. The use of supervised learning techniques allowed an improvement in the results. They were improved to 77% of correct assignments when an ensemble of ten FFNNs were used and to 80% when Random Forests were used. This study was performed with NMR data simulated from the molecular structure by the SPINUS program. In the design of one test set, simulated data was combined with experimental data. The results support the proposal of linking databases of chemical reactions to experimental or simulated NMR data for automatic classification of reactions and mixtures of reactions. Genome-scale classification of enzymatic reactions from their reaction equation. The MOLMAP descriptor relies on a Kohonen SOM that defines types of bonds on the basis of their physico-chemical and topological properties. The MOLMAP descriptor of a molecule represents the types of bonds available in that molecule. The MOLMAP descriptor of a reaction is defined as the difference between the MOLMAPs of the products and the reactants, and numerically encodes the pattern of bonds that are broken, changed, and made during a chemical reaction. The automatic perception of chemical similarities between metabolic reactions is required for a variety of applications ranging from the computer validation of classification systems, genome-scale reconstruction (or comparison) of metabolic pathways, to the classification of enzymatic mechanisms. Catalytic functions of proteins are generally described by the EC numbers that are simultaneously employed as identifiers of reactions, enzymes, and enzyme genes, thus linking metabolic and genomic information. Different methods should be available to automatically compare metabolic reactions and for the automatic assignment of EC numbers to reactions still not officially classified. In this study, the genome-scale data set of enzymatic reactions available in the KEGG database was encoded by the MOLMAP descriptors, and was submitted to Kohonen SOMs to compare the resulting map with the official EC number classification, to explore the possibility of predicting EC numbers from the reaction equation, and to assess the internal consistency of the EC classification at the class level. A general agreement with the EC classification was observed, i.e. a relationship between the similarity of MOLMAPs and the similarity of EC numbers. At the same time, MOLMAPs were able to discriminate between EC sub-subclasses. EC numbers could be assigned at the class, subclass, and sub-subclass levels with accuracies up to 92%, 80%, and 70% for independent test sets. The correspondence between chemical similarity of metabolic reactions and their MOLMAP descriptors was applied to the identification of a number of reactions mapped into the same neuron but belonging to different EC classes, which demonstrated the ability of the MOLMAP/SOM approach to verify the internal consistency of classifications in databases of metabolic reactions. RFs were also used to assign the four levels of the EC hierarchy from the reaction equation. EC numbers were correctly assigned in 95%, 90%, 85% and 86% of the cases (for independent test sets) at the class, subclass, sub-subclass and full EC number level,respectively. Experiments for the classification of reactions from the main reactants and products were performed with RFs - EC numbers were assigned at the class, subclass and sub-subclass level with accuracies of 78%, 74% and 63%, respectively. In the course of the experiments with metabolic reactions we suggested that the MOLMAP / SOM concept could be extended to the representation of other levels of metabolic information such as metabolic pathways. Following the MOLMAP idea, the pattern of neurons activated by the reactions of a metabolic pathway is a representation of the reactions involved in that pathway - a descriptor of the metabolic pathway. This reasoning enabled the comparison of different pathways, the automatic classification of pathways, and a classification of organisms based on their biochemical machinery. The three levels of classification (from bonds to metabolic pathways) allowed to map and perceive chemical similarities between metabolic pathways even for pathways of different types of metabolism and pathways that do not share similarities in terms of EC numbers. Mapping of PES by neural networks (NNs). In a first series of experiments, ensembles of Feed-Forward NNs (EnsFFNNs) and Associative Neural Networks (ASNNs) were trained to reproduce PES represented by the Lennard-Jones (LJ) analytical potential function. The accuracy of the method was assessed by comparing the results of molecular dynamics simulations (thermal, structural, and dynamic properties) obtained from the NNs-PES and from the LJ function. The results indicated that for LJ-type potentials, NNs can be trained to generate accurate PES to be used in molecular simulations. EnsFFNNs and ASNNs gave better results than single FFNNs. A remarkable ability of the NNs models to interpolate between distant curves and accurately reproduce potentials to be used in molecular simulations is shown. The purpose of the first study was to systematically analyse the accuracy of different NNs. Our main motivation, however, is reflected in the next study: the mapping of multidimensional PES by NNs to simulate, by Molecular Dynamics or Monte Carlo, the adsorption and self-assembly of solvated organic molecules on noble-metal electrodes. Indeed, for such complex and heterogeneous systems the development of suitable analytical functions that fit quantum mechanical interaction energies is a non-trivial or even impossible task. The data consisted of energy values, from Density Functional Theory (DFT) calculations, at different distances, for several molecular orientations and three electrode adsorption sites. The results indicate that NNs require a data set large enough to cover well the diversity of possible interaction sites, distances, and orientations. NNs trained with such data sets can perform equally well or even better than analytical functions. Therefore, they can be used in molecular simulations, particularly for the ethanol/Au (111) interface which is the case studied in the present Thesis. Once properly trained, the networks are able to produce, as output, any required number of energy points for accurate interpolations.

Alternativas de design no moodle

Este guião de apoio à formação tem como objectivo apoiar docentes em (1) aprender boas práticas no design de páginas web, (2) conhecer aspectos de versatilidade do moodle e (3) configurar o bloco "course menu".

Learning with tangible interfaces

Trabalho apresentado no âmbito do Mestrado em Engenharia Informática, como requisito parcial para obtenção do grau de Mestre em Engenharia Informática

Designing market-based instruments for biodiversity conservation: learning with the Australian experience and evaluating Portugal's potential

Dissertação apresentada na Faculdade de Ciências e Tecnologia da Universidade Nova de Lisboa para a obtenção do grau de Mestre em Engenharia do Ambiente, perfil Gestão de Sistemas Ambientais

Design and implementation of an autonomous, proactive, and reactive software infrastructure to help improving the management level of projects

Dissertação apresentada na Faculdade de Ciências e Tecnologia da Universidade Nova de Lisboa para obtenção do grau de Mestre em Engenharia Electrotécnica e de Computadores

Recommending media content based on machine learning methods

Dissertação para obtenção do Grau de Mestre em Engenharia Informática

Learning networks and moodle use in online courses: a social network analysis study

Dissertação para obtenção do Grau de Doutor em Ciências da Educação Especialidade em Tecnologias, Redes e Multimédia na Educação e Formação

Adapter module for self-learning production systems

Dissertação para obtenção do Grau de Mestre em Engenharia Electrotécnica, Sistemas e Computadores

Design de Comunicação Para Sistemas Educativos não Formais

Relatório de Actividade Profissional apresentado para cumprimento dos requisitos necessários à obtenção do grau de Mestre em Ciências da Comunicação – vertente de Novos Média e Práticas Web

Ultrassonografia torácica : impacto no diagnóstico e estadiamento do cancro do pulmão

RESUMO:RESUMO: Nos últimos anos a ultrassonografia emergiu como um instrumento importante no diagnóstico da patologia torácica. O progresso tecnológico possibilitou a conceção de novos equipamentos como a ecoendoscopia brônquica radial e linear. Verificou-se, igualmente, o aparecimento de indicações para a realização de ecografia transtorácica. Uma das principais doenças impulsionadoras da técnica ultrassonográfica no tórax foi o cancro do pulmão, primeira causa de morte oncológica a nível mundial. A aplicabilidade e conhecimento do papel dos ultrassons no âmbito do diagnóstico e estadiamento do cancro do pulmão não se encontram esgotados, persistindo focos de controvérsia e dúvida científica que se pretendem esclarecer. A presente tese foi organizada em cinco capítulos: o primeiro abordou de forma geral e introdutória o estado da arte referente à ultrassonografia torácica, cancro do pulmão e a sua conjugação; o segundo destacou os principais objetivos; o terceiro sumarizou a metodologia utilizada; o quarto englobou os cinco estudos publicados, descritos subsequentemente, e o quinto incluiu uma discussão concisa, as principais conclusões e perspetivas futuras. O primeiro estudo avaliou a rentabilidade diagnóstica, segurança e curva de aprendizagem num coorte de 179 doentes submetidos a ecoendoscopia brônquica linear. De acordo com as indicações para este procedimento os doentes foram subdivididos em três grupos: (1) diagnóstico, (2) diagnóstico e estadiamento e (3) estadiamento. Para o primeiro, segundo e terceiro grupos a sensibilidade da ecoendoscopia foi 86.1%, 86.7% e 95% respetivamente e a precisão técnica foi 87.5%, 93.1% e 97.7% respetivamente. O treino originou um aumento progressivo do número de locais puncionados por doente, com menor duração e sem complicações, comprovando a eficácia e segurança do método quando realizado na população Portuguesa por broncologistas com experiência. O segundo estudo foi conduzido para averiguar a eficácia e custo da ecoendoscopia brônquica linear realizada através da via aérea e/ou esófago no diagnóstico de lesões sugestivas de neoplasia do pulmão, após ineficácia das técnicas convencionais. Nos doentes incluídos prospetivamente alcançou-se um diagnóstico definitivo em 106 casos (87.6%). A sensibilidade global para o diagnóstico de cancro do pulmão foi 89.8%, a especificidade foi 100%, o valor preditivo positivo foi 100%, o valor preditivo negativo foi 20% e a precisão foi 90.1%. Esta estratégia ultrassonográfica abrangente evitou intervenções cirúrgicas diagnósticas em doentes anteriormente submetidos a broncoscopia flexível ou punção aspirativa transtorácica guiada por tomografia computorizada, proporcionando uma redução significativa dos custos. No terceiro estudo investigou-se a viabilidade e papel da conjugação da ecoendoscopia brônquica linear com técnicas moleculares na avaliação de antigénios tumorais e padrões de metastização ganglionar em doentes com cancro do pulmão de não-pequenas células (CPNPC). Os marcadores citoqueratina 19 (CK-19), antigénio carcinoembrionário (CEA), molécula de adesão celular epitelial (EPCAM), sialyl-Lewis X e CD44 foram determinados nos aspirados ganglionares de 33 doentes com neoplasia e 17 controlos 10 Ultrassonografia através de citometria de fluxo (CF) e reação em cadeia da polimerase em tempo real (RTPCR). Os doentes com CPNPC possuíam um compartimento celular epitelial significativamente aumentado e com marcação superior de CK-19 comparativamente ao grupo de controlo. O compartimento imune foi também analisado nestas amostras e revelou-se alterado no CPNPC com aumento da população de monócitos e diminuição das subpopulações linfocitárias. Os transcriptos de CK-19, CEA e EPCAM estavam elevados nos doentes com cancro do pulmão, identificando-se uma correlação positiva entre estes marcadores e o tamanho da lesão primária. Concluiu-se que a identificação de CK-19, CEA e EPCAM nas amostras obtidas por ecoendoscopia e avaliadas por CF e RTPCR foi viável, podendo auxiliar na deteção de metástases ganglionares no CPNPC. O quarto estudo envolveu a combinação da ecoendoscopia brônquica radial com uma criosonda para o diagnóstico de lesões pulmonares sólidas periféricas. Foi determinada a viabilidade, rentabilidade diagnóstica, tamanho das amostras e segurança do método. Lesões inferiores a 40mm foram localizadas por ultrassonografia sendo os doentes randomizados para a realização de biópsias transbrônquicas com pinça seguidas por criosonda ou vice-versa. Nos 39 casos incluídos a lesão foi visualizada pela minisonda em 31 doentes (79.5%), com 80.6% de prevalência de cancro do pulmão na amostra. A rentabilidade diagnóstica da pinça de biópsia foi 61.3% e da criosonda foi 74.2%. O tamanho do tecido adquirido pelas criobiópsias foi significativamente maior do que o alcançado por pinça (11.17mm2 vs. 4.69mm2, p<0.001). Ocorreu um único caso de hemorragia moderada, controlada através de medidas conservadoras. As biópsias transbrônquicas com criosonda sob orientação de ecoendoscopia radial foram seguras e eficazes na obtenção de amostras histológicas. O quinto estudo determinou o valor diagnóstico da ecografia transtorácica na identificação de malignidade em doentes com derrame pleural de natureza indeterminada. Foram examinados de forma prospetiva 154 doentes. Os resultados clínicos e radiológicos de cada caso foram ocultados ao executante do exame que gerou imagens estáticas e vídeos ultrassonográficos relevantes. Estes foram posteriormente visualizados, sendo as suas características classificadas por revisores independentes e comparadas com o diagnóstico definitivo. Em 66 casos o diagnóstico foi de derrame pleural maligno (68.2% com cancro do pulmão) e em 67 de derrame benigno. A ecografia torácica obteve 80.3% de sensibilidade, 83.6% de especificidade, 81.2% de valor preditivo negativo e 82.8% de valor preditivo positivo na deteção de malignidade. A nodularidade pleural ou diafragmática, espessamento pleural superior a 10mm e sinal de swirling foram significativamente diferentes (p<0.001) sendo sugestivos de derrame maligno. A existência de nodularidade pleural e ausência de broncograma aéreo ecográfico aumentaram a probabilidade de malignidade (OR 29.0 e OR 10.4, respetivamente). A ecografia transtorácica permitiu diferenciar derrame pleural maligno do benigno. A existência de nódulos pleurais constituiu o fator discriminador mais relevante. Em conclusão, os resultados desta tese possibilitam uma melhor compreensão do papel da ecoendoscopia brônquica (linear e radial) e ecografia transtorácica no diagnóstico e estadiamento do cancro do pulmão, com implicações e aplicabilidade na prática clínica.------------- ABSTRACT: In recent years ultrasonography has emerged as an important instrument in the diagnosis of thoracic diseases. Technological progress has enabled the design of new equipment such as radial and linear endobronchial ultrasound. In addition, indications for transthoracic echography were established. One of the main diseases responsible for the progression of chest sonography was lung cancer, the leading cause of cancer mortality worldwide. The applicability and knowledge of the role of ultrasonography in diagnosing and staging lung cancer is not depleted, persisting foci of controversy and scientific doubt that we intend to elucidate. The present thesis was organized into five chapters: the first included a general introduction regarding chest ultrasound, lung cancer and their combination; the second emphasized the main objectives; the third summarized the methodology used; the fourth encompassed the five published studies, subsequently described, and the fifth included a concise discussion, the main findings and future perspectives. The first study evaluated the diagnostic yield, safety and learning curve in a cohort of 179 patients submitted to linear endobronchial ultrasound. According to procedure indications, the patients were divided into three groups: (1) diagnosis, (2) diagnosis and staging, and (3) staging. For the first, second and third groups, endobronchial ultrasound sensitivity was 86.1%, 86.7% and 95% respectively and accuracy was 87.5%, 93.1% and 97.7% respectively. Practise led to an increase number of punctured sites per patient, in a shorter period of time and without complications, proving the safety and efficacy of the method when performed in the Portuguese population by expert echoscopists. The second study was conducted to determine the efficacy and cost of linear endobronchial ultrasound performed through the airway and/or oesophagus for diagnosis of lesions suggestive of lung cancer, after failure of conventional techniques. Of the patients prospectively enrolled a definitive diagnosis was reached in 106 cases (87.6%). The overall sensitivity for the diagnosis of lung cancer was 89.8%, specificity was 100%, positive predictive value was 100%, negative predictive value was 20% and accuracy was 90.1%. In conclusion, this global ultrasonographic strategy avoided diagnostic surgical procedures in patients that had undergone flexible bronchoscopy or computed tomography-guided transthoracic needle aspiration, providing a significant cost reduction. In the third study, the feasibility and role of linear endobronchial ultrasound combined with molecular techniques in the evaluation of tumour antigens and patterns of lymph node metastasis in patients with non-small cell lung cancer (NSCLC) was investigated. Cytokeratin 19 (CK-19), carcinoembryonic antigen (CEA), epithelial cell adhesion molecule (EPCAM), sialyl Lewis-X and CD44 were determined in lymph node aspirates of 33 lung cancer patients and 17 controls, using flow cytometry (FC) and reverse transcription polymerase chain reaction (RT-PCR). In patients with NSCLC the epithelial cell compartment was significantly increased nd showed brighter CK-19 staining, compared to the control group. In NSCLC patients the immune compartment revealed an increased monocyte population and decreased lymphocyte subsets. The transcripts of CK- 19, CEA and EPCAM were higher in lung cancer patients and a positive correlation between these markers and the size of the primary lesion was also found. We concluded that the identification of CK-19, CEA and EPCAM in endobronchial ultrasound samples, using RT-PCR and FC was feasible and might aid in the detection of NSCLC lymph node metastases. The fourth study involved the combination of the radial endobronchial ultrasound with the cryoprobe for diagnosing solid peripheral lung lesions. We determined the feasibility, diagnostic yield, sample size and safety of the method. Lesions less than 40mm were located by ultrasound and forceps or cryobiopsies were performed in a randomized order. Of the 39 cases included, the lesion could be visualized by the miniprobe in 31 patients (79.5%), and lung cancer prevalence was 80.6%. The diagnostic yield of the biopsy forceps was 61.3% and for the cryobiopsy was 74.2 %. Cryobiopsies were significantly larger than forceps biopsies (11.17mm2 vs. 4.69mm2, p<0.001). There was only one case of moderate bleeding that was controlled by conservative measures. Transbronchial cryobiopsies under radial endobronchial ultrasound guidance were safe and effective in obtaining histological samples. The fifth study determined the diagnostic value of transthoracic sonography in predicting malignancy in patients with an undiagnosed pleural effusion. One hundred and fifty four patients were prospectively scanned. Relevant ultrasound images and videos were generated by an operator blinded to clinical and radiological results. These were subsequently visualized, its characteristics classified by independent reviewers and compared to the final diagnosis. A malignant pleural effusion was diagnosed in 66 cases (68.2 % with lung cancer) and a benign effusion in 67 cases. Thoracic ultrasound had a sensitivity of 80.3 %, specificity of 83.6%, negative predictive value of 81.2 % and positive predictive value of 82.8% to detect malignancy. The presence of pleural or diaphragmatic nodularity, pleural thickening greater than 10mm and swirling signal were significantly different (p<0.001 ), being suggestive of malignant effusion. The existence of pleural nodularity and absence of lung air bronchogram were more likely to indicate malignancy (OR 29.0 and OR 10.4, respectively). Transthoracic ultrasonography permits the distinction between malignant and benign pleural effusions. Pleural nodules were the most relevant feature. In conclusion, the results of this thesis provide a better understanding of the role of endobronchial ultrasound (linear and radial) and transthoracic sonography in lung cancer diagnosis and staging, with direct implications and applicability in clinical practice.

Learning Activities with Semantic. Hypermedia in Higher Education

The increasing use of information and communication technologies (ICT) in diverse professional and personal contexts calls for new knowledge, and a set of abilities, competences and attitudes, for an active and participative citizenship. In this context it is acknowledged that universities have an important role innovating in the educational use of digital media to promote an inclusive digital literacy. The educational potential of digital technologies and resources has been recognized by both researchers and practitioners. Multiple pedagogical models and research approaches have already contributed to put in evidence the importance of adapting instructional and learning practices and processes to concrete contexts and educational goals. Still, academic and scientific communities believe further investments in ICT research is needed in higher education. This study focuses on educational models that may contribute to support digital technology uses, where these can have cognitive and educational relevance when compared to analogical technologies. A teaching and learning model, centered in the active role of the students in the exploration, production, presentation and discussion of interactive multimedia materials, was developed and applied using the internet and exploring emergent semantic hypermedia formats. The research approach focused on the definition of design principles for developing class activities that were applied in three different iterations in undergraduate courses from two institutions, namely the University of Texas at Austin, USA and the University of Lisbon, Portugal. The analysis of this study made possible to evaluate the potential and efficacy of the model proposed and the authoring tool chosen in the support of metacognitive skills and attitudes related to information structuring and management, storytelling and communication, using computers and the internet.

Learning facial-expression models with crowdsourcing

The computational power is increasing day by day. Despite that, there are some tasks that are still difficult or even impossible for a computer to perform. For example, while identifying a facial expression is easy for a human, for a computer it is an area in development. To tackle this and similar issues, crowdsourcing has grown as a way to use human computation in a large scale. Crowdsourcing is a novel approach to collect labels in a fast and cheap manner, by sourcing the labels from the crowds. However, these labels lack reliability since annotators are not guaranteed to have any expertise in the field. This fact has led to a new research area where we must create or adapt annotation models to handle these weaklylabeled data. Current techniques explore the annotators’ expertise and the task difficulty as variables that influences labels’ correction. Other specific aspects are also considered by noisy-labels analysis techniques. The main contribution of this thesis is the process to collect reliable crowdsourcing labels for a facial expressions dataset. This process consists in two steps: first, we design our crowdsourcing tasks to collect annotators labels; next, we infer the true label from the collected labels by applying state-of-art crowdsourcing algorithms. At the same time, a facial expression dataset is created, containing 40.000 images and respective labels. At the end, we publish the resulting dataset.

Learning new tricks: Corticostriatal dynamics during novel skill learning

Learning novel actions and skills is a prevalent ability across multiple species and a critical feature for survival and competence in a constantly changing world. Novel actions are generated and learned through a process of trial and error, where an animal explores the environment around itself, generates multiple patterns of behavior and selects the ones that increase the likelihood of positive outcomes. Proper adaptation and execution of the selected behavior requires the coordination of several biomechanical features by the animal. Cortico-basal ganglia circuits and loops are critically involved in the acquisition, learning and consolidation of motor skills.(...)