Embedded platform for ECG biometric recognition

Trabalho Final de Mestrado para obtenção do grau de Mestre em Engenharia de Electrónica e Telecomunicações

Transacção de componentes multimédia suportada por agentes

O objectivo do projecto descrito nesta dissertação é o desenvolvimento da interface entre as empresas e a plataforma Business-to-Business (B2B) de negociação automática de anúncios em construção. A plataforma, no seu todo, deve garantir que os intervalos da programação são preenchidos com um alinhamento de anúncios compatível com os interesses expressos e o perfil construído dos espectadores. A plataforma funciona como um mercado electrónico de negociação automática destinado a agências de publicidade (empresas produtoras) e empresas provedoras de conteúdos e serviços multimédia aos consumidores finais (empresas distribuidoras). As empresas, uma vez registadas na plataforma, passam a ser representadas por agentes que negoceiam automaticamente os itens submetidos com o comportamento especificado. Do ponto de vista da arquitectura, a plataforma consiste num sistema multiagente organizado em três camadas compostas por: (i) agentes de interface com as empresas; (ii) agentes de modelação das empresas; e (iii) agentes delegados, de duração efémera, exclusivamente criados para participar em negociações específicas de conteúdos multimédia. Cada empresa representada na plataforma possui, para além de um número indeterminado de delegados envolvidos em negociações específicas, dois agentes: (i) o agente de interface com a empresa, que expõe um conjunto de operações de interface ao exterior através de um serviço Web, localizado na primeira camada; e (ii) o agente que modela a empresa na plataforma, que expõe através de um serviço Web um conjunto de operações aos agentes das restantes camadas da plataforma, residente na camada intermédia. Este projecto focou-se no desenvolvimento da camada superior de interface da plataforma com as empresas e no enriquecimento da camada intermédia. A realização da camada superior incluiu a especificação da parte da ontologia da plataforma que dá suporte às operações de interface com o exterior, à sua exposição como serviços Web e à criação e controlo dos agentes de interface. Esta camada superior deve permitir às empresas carregar e descarregar toda informação relevante de e para a plataforma, através de uma interface gráfica ou de forma automática, e apresentar de forma gráfica e intuitiva os resultados alcançados, nomeadamente, através da apresentação da evolução das transacções. Em relação à camada intermédia, adicionou-se à ontologia da plataforma a representação do conhecimento de suporte às operações de interface com a camada superior, adoptaram-se taxonomias de classificação de espectadores, anúncios e programas, desenvolveu-se um algoritmo de emparelhamento entre os espectadores, programas e anúncios disponíveis e, por fim, procedeu-se ao armazenamento persistente dos resultados das negociações. Do ponto de vista da plataforma, testou-se o seu funcionamento numa única plataforma física e assegurou-se a segurança e privacidade da comunicação entre empresa e plataforma e entre agentes que representam uma mesma empresa.

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.

Global localization with non-quantized local image features

In the field of appearance-based robot localization, the mainstream approach uses a quantized representation of local image features. An alternative strategy is the exploitation of raw feature descriptors, thus avoiding approximations due to quantization. In this work, the quantized and non-quantized representations are compared with respect to their discriminativity, in the context of the robot global localization problem. Having demonstrated the advantages of the non-quantized representation, the paper proposes mechanisms to reduce the computational burden this approach would carry, when applied in its simplest form. This reduction is achieved through a hierarchical strategy which gradually discards candidate locations and by exploring two simplifying assumptions about the training data. The potential of the non-quantized representation is exploited by resorting to the entropy-discriminativity relation. The idea behind this approach is that the non-quantized representation facilitates the assessment of the distinctiveness of features, through the entropy measure. Building on this finding, the robustness of the localization system is enhanced by modulating the importance of features according to the entropy measure. Experimental results support the effectiveness of this approach, as well as the validity of the proposed computation reduction methods.

An unsupervised approach to feature discretization and selection

Many learning problems require handling high dimensional datasets with a relatively small number of instances. Learning algorithms are thus confronted with the curse of dimensionality, and need to address it in order to be effective. Examples of these types of data include the bag-of-words representation in text classification problems and gene expression data for tumor detection/classification. Usually, among the high number of features characterizing the instances, many may be irrelevant (or even detrimental) for the learning tasks. It is thus clear that there is a need for adequate techniques for feature representation, reduction, and selection, to improve both the classification accuracy and the memory requirements. In this paper, we propose combined unsupervised feature discretization and feature selection techniques, suitable for medium and high-dimensional datasets. The experimental results on several standard datasets, with both sparse and dense features, show the efficiency of the proposed techniques as well as improvements over previous related techniques.

ECG-based biometrics: A real time classification approach

Behavioral biometrics is one of the areas with growing interest within the biosignal research community. A recent trend in the field is ECG-based biometrics, where electrocardiographic (ECG) signals are used as input to the biometric system. Previous work has shown this to be a promising trait, with the potential to serve as a good complement to other existing, and already more established modalities, due to its intrinsic characteristics. In this paper, we propose a system for ECG biometrics centered on signals acquired at the subject's hand. Our work is based on a previously developed custom, non-intrusive sensing apparatus for data acquisition at the hands, and involved the pre-processing of the ECG signals, and evaluation of two classification approaches targeted at real-time or near real-time applications. Preliminary results show that this system leads to competitive results both for authentication and identification, and further validate the potential of ECG signals as a complementary modality in the toolbox of the biometric system designer.

Desenvolvimento de Ontologia para Apoio ao Diagnóstico de Distúrbios do Humor

Mestrado em Computação e Instrumentação Médica

Classification Performance of Multilayer Perceptrons with Different Risk Functionals

In the present paper we assess the performance of information-theoretic inspired risks functionals in multilayer perceptrons with reference to the two most popular ones, Mean Square Error and Cross-Entropy. The information-theoretic inspired risks, recently proposed, are: HS and HR2 are, respectively, the Shannon and quadratic Rényi entropies of the error; ZED is a risk reflecting the error density at zero errors; EXP is a generalized exponential risk, able to mimic a wide variety of risk functionals, including the information-thoeretic ones. The experiments were carried out with multilayer perceptrons on 35 public real-world datasets. All experiments were performed according to the same protocol. The statistical tests applied to the experimental results showed that the ubiquitous mean square error was the less interesting risk functional to be used by multilayer perceptrons. Namely, mean square error never achieved a significantly better classification performance than competing risks. Cross-entropy and EXP were the risks found by several tests to be significantly better than their competitors. Counts of significantly better and worse risks have also shown the usefulness of HS and HR2 for some datasets.

ECG biometrics using a dissimilarity space representation

Electrocardiogram (ECG) biometrics are a relatively recent trend in biometric recognition, with at least 13 years of development in peer-reviewed literature. Most of the proposed biometric techniques perform classifi-cation on features extracted from either heartbeats or from ECG based transformed signals. The best representation is yet to be decided. This paper studies an alternative representation, a dissimilarity space, based on the pairwise dissimilarity between templates and subjects' signals. Additionally, this representation can make use of ECG signals sourced from multiple leads. Configurations of three leads will be tested and contrasted with single-lead experiments. Using the same k-NN classifier the results proved superior to those obtained through a similar algorithm which does not employ a dissimilarity representation. The best Authentication EER went as low as 1:53% for a database employing 503 subjects. However, the employment of extra leads did not prove itself advantageous.

Text classification using compression-based dissimilarity measures

Arguably, the most difficult task in text classification is to choose an appropriate set of features that allows machine learning algorithms to provide accurate classification. Most state-of-the-art techniques for this task involve careful feature engineering and a pre-processing stage, which may be too expensive in the emerging context of massive collections of electronic texts. In this paper, we propose efficient methods for text classification based on information-theoretic dissimilarity measures, which are used to define dissimilarity-based representations. These methods dispense with any feature design or engineering, by mapping texts into a feature space using universal dissimilarity measures; in this space, classical classifiers (e.g. nearest neighbor or support vector machines) can then be used. The reported experimental evaluation of the proposed methods, on sentiment polarity analysis and authorship attribution problems, reveals that it approximates, sometimes even outperforms previous state-of-the-art techniques, despite being much simpler, in the sense that they do not require any text pre-processing or feature engineering.

Conservation GIS: Ontology and spatial reasoning for commonsense knowledge.

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

Methodology for collaborative enterprise reference ontology building

Dissertation presented at Faculdade de Ciências e Tecnologia of Universidade Nova de Lisboa to obtain the Master degree in Electrical Engineering and Computer Science

Organizational Culture in Cooperatives: an exploratory approach

In recent years, organizational culture has become one of the common themes of interest of scientific and academic research. Each organization has its own unique cultural identity. Based on the recognition that organizational culture is considered important to an organization’s results, and social economy organizations are concerned with improving managerial practices and results, our objective is to study organizational culture in cooperatives: identifying their organizational culture as a specific type of organization of the social economy, recognized as increasingly important economic agents; and in doing so, explore the usage of a widely known model, the Competing Values Framework (Quinn & Rohrbaugh 1983). Three cooperatives were studied. Their presidents were interviewed, and a questionnaire was applied to cooperative members to obtain demographic and organizational culture data. Differences between the cooperatives’ cultural profiles seem to be consistent with both the circumstances of Portuguese social economy organizations (SEOs), and to the organizations’ uniqueness regarding their trade, focuses, and history. International firm trends were compared with this study’s results, and also appear to be explained by the SEO’s management practices evolution standpoint: lack of structured way of working, and the need to improvise and innovate in order to get things done. The importance of our research is held in the fact that social economy, and the cooperative movement in particular, has a developing importance in the expansion of many economies, the lack of literature on culture in SEOs, and the exploratory usage of a well-known model of management literature in cooperatives.

Organizational culture in cooperatives: an exploratory approach

In recent years, organizational culture has become one of the common themes of interest of scientific and academic research. Each organization has its own unique cultural identity. Based on the recognition that organizational culture is considered important to an organization’s results, and social economy organizations are concerned with improving managerial practices and results, our objective is to study organizational culture in cooperatives: identifying their organizational culture as a specific type of organization of the social economy, recognized as increasingly important economic agents; and in doing so, explore the usage of a widely known model, the Competing Values Framework (Quinn & Rohrbaugh 1983). Three cooperatives were studied. Their presidents were interviewed, and a questionnaire was applied to cooperative members to obtain demographic and organizational culture data. Differences between the cooperatives’ cultural profiles seem to be consistent with both the circumstances of Portuguese social economy organizations (SEOs), and to the organizations’ uniqueness regarding their trade, focuses, and history. International firm trends were compared with this study’s results, and also appear to be explained by the SEO’s management practices evolution standpoint: lack of structured way of working, and the need to improvise and innovate in order to get things done. The importance of our research is held in the fact that social economy, and the cooperative movement in particular, has a developing importance in the expansion of many economies, the lack of literature on culture in SEOs, and the exploratory usage of a well-known model of management literature in cooperatives.

Stratigraphic interpretation of Well-Log data of the Athabasca Oil Sands of Alberta Canada through Pattern recognition and Artificial Intelligence

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