Machine learning Gaussian short rate

Dissertação para obtenção do Grau de Doutor em Estatística e Gestão do Risco

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.

Mobile and web tools for participative learning

Dissertação apresentada na Faculdade de Ciências e Tecnologia da Universidade Nova de Lisboa, para a obtenção do grau de Mestre em Engenharia Informática

Learning to manage in knowledge-based organizations: the role of learning logs or portfolios

Paper presented at the 8th European Conference on Knowledge Management, Barcelona, 6-7 Sep. 2008 URL: http://www.academic-conferences.org/eckm/eckm2007/eckm07-home.htm

A learning approach to swarm-based path detection and tracking

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

Business model optimization of Prego Gourmet

A Work Project, presented as part of the requirements for the Award of a Masters Degree in Management from the NOVA – School of Business and Economics

New visualization model for large scale biosignals analysis

Benefits of long-term monitoring have drawn considerable attention in healthcare. Since the acquired data provides an important source of information to clinicians and researchers, the choice for long-term monitoring studies has become frequent. However, long-term monitoring can result in massive datasets, which makes the analysis of the acquired biosignals a challenge. In this case, visualization, which is a key point in signal analysis, presents several limitations and the annotations handling in which some machine learning algorithms depend on, turn out to be a complex task. In order to overcome these problems a novel web-based application for biosignals visualization and annotation in a fast and user friendly way was developed. This was possible through the study and implementation of a visualization model. The main process of this model, the visualization process, comprised the constitution of the domain problem, the abstraction design, the development of a multilevel visualization and the study and choice of the visualization techniques that better communicate the information carried by the data. In a second process, the visual encoding variables were the study target. Finally, the improved interaction exploration techniques were implemented where the annotation handling stands out. Three case studies are presented and discussed and a usability study supports the reliability of the implemented work.

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.

A comunicação intercultural ao nível da intervenção pedagógica no ensino do português como língua estrangeira a alunos chineses na China

A globalização aproxima os povos: o mundo chinês e o mundo português nunca tiveram uma relação tão estreita como a atual. Apesar de os portugueses terem ido os primeiros ocidentais a entrar na China com a chegada de Jorge Álvares a uma ilha chinesa, em 1513, e os últimos ocidentais a deixar o governo de um território chinês, com a transferência da administração portuguesa de Macau para a China a 20 de dezembro de 1999, nunca haviam sido registados, nos últimos séculos, grandes contatos ou intercâmbios comerciais e culturais entre a China e Portugal e entre o mundo chinês e o mundo lusófono, em comparação com os contatos entre o mundo chinês e outros mundos ocidentais: como o inglês, o francês, o alemão e o espanhol. Os objetivos gerais desta investigação são três: 1 - Reconhecer o papel do desenvolvimento da competência omunicativa intercultural no contexto do ensino-aprendizagem do português como LE na China. 2 - Promover o desenvolvimento da competência comunicativa intercultural dos alunos chineses no processo de aprendizagem da língua portuguesa na China. 3 - Analisar os métodos pedagógicos e de integração curricular para apoiar e desenvolver um ensino mais eficaz do português como LE na China. O desenvolvimento do nosso trabalho articula-se em duas áreas científicas: Ciências da Linguagem e Ciências da Educação. A abordagem metodológica utilizada é o estudo de caso, com recolha de dados primários realizada através de questionários, entrevistas e observação participante em profundidade, que permitiu a confirmação e/ou refutação das hipóteses levantadas, privilegiando a metodologia qualitativa. Os resultados permitem estabelecer uma relação significativa, do ponto de vista pedagógico, entre a comunicação intercultural na educação e as práticas pedagógicas desenvolvidas no ensino do português como língua estrangeira na China. Contudo e de acordo com a nossa pesquisa, o maior problema que impede as práticas pedagógicas para desenvolver as competências comunicativas no ensino, é a falta de materiais didáticos com estrutura para elaborar um programa de atividades coerentes e complementares nas aulas.

Learning domain-specific sentiment lexicons with applications to recommender systems

Search is now going beyond looking for factual information, and people wish to search for the opinions of others to help them in their own decision-making. Sentiment expressions or opinion expressions are used by users to express their opinion and embody important pieces of information, particularly in online commerce. The main problem that the present dissertation addresses is how to model text to find meaningful words that express a sentiment. In this context, I investigate the viability of automatically generating a sentiment lexicon for opinion retrieval and sentiment classification applications. For this research objective we propose to capture sentiment words that are derived from online users’ reviews. In this approach, we tackle a major challenge in sentiment analysis which is the detection of words that express subjective preference and domain-specific sentiment words such as jargon. To this aim we present a fully generative method that automatically learns a domain-specific lexicon and is fully independent of external sources. Sentiment lexicons can be applied in a broad set of applications, however popular recommendation algorithms have somehow been disconnected from sentiment analysis. Therefore, we present a study that explores the viability of applying sentiment analysis techniques to infer ratings in a recommendation algorithm. Furthermore, entities’ reputation is intrinsically associated with sentiment words that have a positive or negative relation with those entities. Hence, is provided a study that observes the viability of using a domain-specific lexicon to compute entities reputation. Finally, a recommendation system algorithm is improved with the use of sentiment-based ratings and entities reputation.

Professores realistas: mais eficazes e otimistas

A indisciplina na sala de aula prejudica o ensino e a aprendizagem sendo uma das principais causas do mal-estar dos professores, roubando-lhes energia e tempo conduzindo, muitos deles, à exaustão física e emocional e apresenta-se como um sério problema quer para professores principiantes, quer para professores experientes. A análise do ensino na perspetiva interpessoal possibilita uma nova visão sobre o ambiente de aprendizagem, nomeadamente no que se refere à relação professor-aluno. Nesta perspetiva, o enfoque dirige-se para a análise das perceções dos alunos sobre o comportamento do professor e o impacto que o mesmo tem sobre os alunos. Além de que, ao considerar-se a turma como um sistema deve ter-se em conta que o comportamento não pode ser visto como uma característica da pessoa mas, sim, como uma característica do sistema formado por aqueles que estão envolvidos na interação comunicacional. Analisar as interações comunicacionais à luz da pragmática da comunicação e dos seus cinco axiomas apresenta-se como um poderoso quadro clarificador de muitos dos comportamentos ditos disruptivos, possibilitando aos professores um “novo olhar” sobre o seu papel enquanto gestores da sala de aula. A formação realista de professores apresenta-se como uma estratégia com efeitos muito positivos uma vez que possibilita e ajuda-os a compreenderem o processo de circularidade característico da turma vista como um sistema. Por outro lado, permite evidenciar a impossibilidade dos professores de solucionarem os problemas disciplinares culpabilizando os alunos. Dito de outro modo, a formação realista conduz os professores a um (re) equacionar das suas práticas encorajando-os a selecionarem um comportamento interpessoal mais adequado. No 1º e 3º período letivo, os professores participantes (N= 15) responderam ao Questionário de Interação do Professor (Q.I.P.) e ao Questionário do Otimismo Académico (Q.O.A.) composto por três subescalas: Autoeficácia, Confiança nos alunos e famílias e Ênfase académica. Paralelamente, foram gravadas em suporte vídeo quatro aulas de cada professor, referentes a duas turmas selecionadas previamente pelos mesmos. Após a observação das suas aulas refletiram por escrito aquilo que observaram. No 2º período, participaram numa ação de formação intitulada “Ecologia da sala de aula: relacionamento interpessoal professor-aluno e a criação de ambientes de aprendizagem positivos” baseada no modelo realista de formação de professores. Desta formação resultou um conjunto de relatórios reflexivos que tiveram por objetivo desenvolver nos participantes a sua competência reflexiva, questionarem crenças tidas como inquestionáveis e otimizar a relação professor-aluno. A partir dos resultados obtidos pode afirmar-se que: 1) verificou-se um aumento no otimismo académico e no sentimento de autoeficácia; 2) observou-se um impacto nas conceções prévias, bem como no contexto organizacional.