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.

Wetland Habitat Studies using various Classification Techniques on Multi-Spectral Landsat Imagery: Case study: Tram chim National Park, Dong Thap Vietnam

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

Automatic sleep apnea detection and sleep classification using the ECG and the SpO2 signals

Dissertation for a Masters Degree in Computer and Electronic Engineering

An overview of the higher level classification of Pucciniomycotina based on combined analyses of nuclear large and small subunit rDNA sequences

Mycologia, Vol. 98, nº6

The contribution of multitemporal information from multispectral satellite images for automatic land cover classification at the national scale

Thesis submitted to the Instituto Superior de Estatística e Gestão de Informação da Universidade Nova de Lisboa in partial fulfillment of the requirements for the Degree of Doctor of Philosophy in Information Management – Geographic Information Systems

A gestão dos resíduos hospitalares e o papel da autoridade de saúde : caso do concelho da Amad

RESUMO O Problema. A natureza, diversidade e perigosidade dos resíduos hospitalares (RH) exige procedimentos específicos na sua gestão. A sua produção depende do número de unidades de prestação de cuidados de saúde (upcs), tipo de cuidados prestados, número de doentes observados, práticas dos profissionais e dos órgãos de gestão das upcs, inovação tecnológica, entre outros. A gestão integrada de RH tem evoluído qualitativamente nos últimos anos. Existe uma carência de informação sobre os quantitativos de RH produzidos nas upcs e na prestação de cuidados domiciliários, em Portugal. Por outro lado, os Serviços de Saúde Pública, abrangendo o poder de Autoridade de Saúde, intervêm na gestão do risco para a saúde e o ambiente associado à produção de RH, necessitando de indicadores para a sua monitorização. O quadro legal de um país nesta matéria estabelece a estratégia de gestão destes resíduos, a qual é condicionada pela classificação e definição de RH por si adoptadas. Objectivos e Metodologias. O presente estudo pretende: quantificar a produção de RH resultantes da prestação de cuidados de saúde, em seres humanos e animais nas upcs, do sistema público e privado, desenvolvendo um estudo longitudinal, onde se quantifica esta produção nos Hospitais, Centros de Saúde, Clínicas Médicas e Dentárias, Lares para Idosos, Postos Médicos de Empresas, Centros de Hemodiálise e Clínicas Veterinárias do Concelho da Amadora, e se compara esta produção em dois anos consecutivos; analisar as consequências do exercício do poder de Autoridade de Saúde na gestão integrada de RH pelas upcs; quantificar a produção média de RH, por acto prestado, nos cuidados domiciliários e, com um estudo analítico transversal, relacionar essa produção média com as características dos doentes e dos tratamentos efectuados; proceder à análise comparativa das definições e classificações de RH em países da União Europeia, através de um estudo de revisão da legislação nesta matéria em quatro países, incluindo Portugal. Resultados e Conclusões. Obtém-se a produção média de RH, por Grupos I+II, III e IV: nos Hospitais, por cama.dia, considerando a taxa de ocupação; por consulta, nos Centros de Saúde, Clínicas Médicas e Dentárias e Postos Médicos de Empresas; por cama.ano, nos Lares para Idosos, considerando a sua taxa de ocupação; e por ano, nas Clínicas de Hemodiálise e Veterinárias. Verifica-se que a actuação da Autoridade de Saúde, produz nas upcs uma diferença estatisticamente significativa no aumento das contratualizações destas com os operadores de tratamento de RH. Quantifica-se o peso médio de resíduos dos Grupos III e IV produzido por acto prestado nos tratamentos domiciliários e relaciona-se esta variável dependente com as características dos doentes e dos tratamentos efectuados. Comparam-se os distintos critérios utilizados na elaboração das definições e classificações destes resíduos inscritas na legislação da Alemanha, Reino Unido, Espanha e Portugal. Recomendações. Apresentam-se linhas de investigação futura e propõe-se uma reflexão sobre eventuais alterações de aspectos específicos no quadro legal português e nos planos de gestão integrada de RH, em Portugal. ABSTRACT The problem: The nature, diversity and hazardousness of hospital wastes (HW) requires specific procedures in its management. Its production depends on the number and patterns of healthcare services, number of patients, professional and administration practices and technologic innovations, among others. Integrated management of HW has been developping, in the scope of quality, for the past few years. There is a lack of information about the amount of HW produced in healthcare units and in the domiciliary visits, in Portugal. On the other hand, the Public Health Services, embracing the Health Authority’s power, play a very important role in managing the risk of HW production to public and environmental health. They need to use some indicators in its monitorization. In a country, rules and regulations define hospital waste management policies, which are confined by the addopted classification and definition of HW. Goals and Methods: This research study aims to quantify the production of HW as a result of healthcare services in human beings and animals, public service and private one. Through a longitudinal study, this production is quantified in Hospitals, Health Centers, Medical and Dental Clinics, Residential Centers for old people, Companies Medical Centers and Veterinary and Haemodyalisis Clinics in Amadora’s Council, comparing this production in two consecutive years. This study also focus the consequences of the Health Authority’s role in the healthcare services integrated management of HW. The middle production of HW in the domiciliary treatments is also quantified and, with a transversal analytic study, its association with patients and treatments’ characteristics is enhanced. Finally, the definitions and classifications in the European Union Countries are compared through a study that revises this matter’s legislation in four countries, including Portugal. Results and Conclusions: We get the middle production of Groups I+II, III and IV: HW: in Hospitals, by bed.day, bearing the occupation rate; by consultation, in Health Centers, Medical and Dental Clinics and Companies Medical Centers; by bed.year in Residential Centers for old people, considering their occupation rate; by year, in Veterinary and Haemodyalisis Clinics. We verify that the Health Authority’s role produces a significative statistical difference in the rise of the contracts between healthcare services and HW operators. We quantify the Groups III and IV’s wastes middle weight, produced by each medical treatment in domiciliary visits and relate this dependent variable with patients and treatments’ characteristics. We compare the different criteria used in the making of definitions and classifications of these wastes registered in German, United Kingdom, Spain and Portugal’s laws. Recommendations: Lines of further investigation are explaned. We also tender a reflexion about potential changes in rules, in regulations and in the integrated plans for managing hospital wastes in Portugal. RÉSUMÉ Le Problème. La gestion des déchets d'activités hospitalières (DAH) et de soins de santé (DSS) exige des procédures spécifiques en raison de leur nature, diversité et dangerosité. Leur production dépend, parmi d’autres, du nombre d’unités de soins de santé (USS), du type de soins administrés, du nombre de malades observés, des pratiques des professionnels et des organes de gestion des USS, de l’innovation technologique. La gestion intégrée des DAH et des DSS subit une évolution qualitative dans les dernières années. Il existe un déficit d’information sur les quantitatifs de DAH et de DSS provenant des USS et de la prestation de soins domiciliaires, au Portugal. D’autre part les Services de Santé Publique, y compris le pouvoir de l’Autorité de Santé, qui interviennent dans la gestion du risque pour la santé et pour l’environnement associé à la production de DAH et de DSS, ont besoin d’indicateurs pour leur surveillance. Dans cette matière le cadre légal établit la stratégie de gestion de ces déchets, laquelle est conditionnée par la classification et par la définition des DAH et des DSS adoptées par le pays. Objectifs et Méthodologie. Cet étude prétend: quantifier la production de DAH et de DSS provenant de la prestation de soins de santé, en êtres humains et animaux dans les USS du système public et privé. À travers un étude longitudinal, on quantifie cette production dans les Hôpitaux, Centres de Santé, Cliniques Médicales et Dentaires, Maisons de Repos pour personnes âgées, Cabinets Médicaux d’ Entreprises, Centres d’Hémodialyse et Cliniques Vétérinaires du municipe d’ Amadora, en comparant cette production en deux ans consécutifs; analyser les conséquences de l’exercice du pouvoir de l’Autorité de Santé dans la gestion intégrée des DAH et des DSS par les USS; quantifier la production moyenne de DAH et de DSS dans la prestation de soins domiciliaires et, avec un étude analytique transversal, rapporter cette production moyenne avec les caractéristiques des malades et des soins administrés; procéder à l’ analyse comparative des définitions et classifications des DAH et des DSS dans des pays de l’Union Européenne, à travers un étude de révision de la législation relative à cette matière dans quatre pays, Portugal y compris. Résultats et Conclusions. On obtient la production moyenne de DAH et des DSS, par Classes I+II, III et IV: dans les hôpitaux, par lit.jour, en considérant le taux d’occupation; par consultation, dans les Centres de Santé, Cliniques Médicales et Dentaires et Cabinets Médicaux d’ Entreprises par lit.an dans les Maisons de Repos pour personnes âgées en considérant le taux d’occupation; et par an, dans les Cliniques d’Hémodialyse et Vétérinaires. On constate que l’actuation de l’Autorité de Santé produit dans les USS une différence statistiquement significative dans l’accroissement de leurs contractualisations avec les opérateurs de traitement de DAH et de DSS. On quantifie le poids moyen des déchets des Classes III et IV produit par acte de prestation de soins à domicile et on rapporte cette variable dépendante avec les caractéristiques des malades et des soins administrés. On compare les différents critères utilisés dans l’élaboration des définitions et des classifications de ces déchets inscrites dans la légis

Unsupervised automatic music genre classification

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

Automatic cymbal classification

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

Multi-scale vegetation classification using earth observation data of the Sundarban mangrove forest, Bangladesh.

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

Unsupervised classification of remote sensing images combining Self Organizing Maps and segmentation techniques

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

Contract-program evaluation: Impact of the DRG classification system on hospitals' outputs

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

Exploratory analysis of OpenStreetMap for land use classification

In the last years, volunteers have been contributing massively to what we know nowadays as Volunteered Geographic Information. This huge amount of data might be hiding a vast geographical richness and therefore research needs to be conducted to explore their potential and use it in the solution of real world problems. In this study we conduct an exploratory analysis of data from the OpenStreetMap initiative. Using the Corine Land Cover database as reference and continental Portugal as the study area, we establish a possible correspondence between both classification nomenclatures, evaluate the quality of OpenStreetMap polygon features classification against Corine Land Cover classes from level 1 nomenclature, and analyze the spatial distribution of OpenStreetMap classes over continental Portugal. A global classification accuracy around 76% and interesting coverage areas’ values are remarkable and promising results that encourages us for future research on this topic.

Context classification for service robots

This dissertation presents a solution for environment sensing using sensor fusion techniques and a context/environment classification of the surroundings in a service robot, so it could change his behavior according to the different rea-soning outputs. As an example, if a robot knows he is outdoors, in a field environment, there can be a sandy ground, in which it should slow down. Contrariwise in indoor environments, that situation is statistically unlikely to happen (sandy ground). This simple assumption denotes the importance of context-aware in automated guided vehicles.

Analysis of classification algorithms for crop detection using LANDSAT 8 images

Remote sensing - the acquisition of information about an object or phenomenon without making physical contact with the object - is applied in a multitude of different areas, ranging from agriculture, forestry, cartography, hydrology, geology, meteorology, aerial traffic control, among many others. Regarding agriculture, an example of application of this information is regarding crop detection, to monitor existing crops easily and help in the region’s strategic planning. In any of these areas, there is always an ongoing search for better methods that allow us to obtain better results. For over forty years, the Landsat program has utilized satellites to collect spectral information from Earth’s surface, creating a historical archive unmatched in quality, detail, coverage, and length. The most recent one was launched on February 11, 2013, having a number of improvements regarding its predecessors. This project aims to compare classification methods in Portugal’s Ribatejo region, specifically regarding crop detection. The state of the art algorithms will be used in this region and their performance will be analyzed.

Mapping the Pasture Steppe in Bayankhongor, Mongolia: comparison of classification methods, using Landsat-8 and geophysical data

Grasslands in semi-arid regions, like Mongolian steppes, are facing desertification and degradation processes, due to climate change. Mongolia’s main economic activity consists on an extensive livestock production and, therefore, it is a concerning matter for the decision makers. Remote sensing and Geographic Information Systems provide the tools for advanced ecosystem management and have been widely used for monitoring and management of pasture resources. This study investigates which is the higher thematic detail that is possible to achieve through remote sensing, to map the steppe vegetation, using medium resolution earth observation imagery in three districts (soums) of Mongolia: Dzag, Buutsagaan and Khureemaral. After considering different thematic levels of detail for classifying the steppe vegetation, the existent pasture types within the steppe were chosen to be mapped. In order to investigate which combination of data sets yields the best results and which classification algorithm is more suitable for incorporating these data sets, a comparison between different classification methods were tested for the study area. Sixteen classifications were performed using different combinations of estimators, Landsat-8 (spectral bands and Landsat-8 NDVI-derived) and geophysical data (elevation, mean annual precipitation and mean annual temperature) using two classification algorithms, maximum likelihood and decision tree. Results showed that the best performing model was the one that incorporated Landsat-8 bands with mean annual precipitation and mean annual temperature (Model 13), using the decision tree. For maximum likelihood, the model that incorporated Landsat-8 bands with mean annual precipitation (Model 5) and the one that incorporated Landsat-8 bands with mean annual precipitation and mean annual temperature (Model 13), achieved the higher accuracies for this algorithm. The decision tree models consistently outperformed the maximum likelihood ones.