Artificial Intelligence in geospatial analysis: applications of self-organizing maps in the context of geographic information science.

A thesis submitted in partial fulfilment of the requirements for the degree of Doctor of Philosophy in Information Systems.

Analysis and recognition of similar environmental sounds

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

Exploratory geospatial data analysis using self-organizing maps

Dissertação apresentada como requisito parcial para obtenção do grau de Mestre em Ciência e Sistemas de Informação Geográfica

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.

Visualization of clusters in geo-referenced data using three-dimensional self-organizing maps

Dissertação apresentada como requisito parcial para obtenção do grau de Mestre em Estatística e Gestão de Informação

Planning the medical workforce - an analysis of the third repport of the Medical Workforce Standing Advisory Committee

Arquivos de Medicina 1998; 12(4): 246-248

CARTO-SOM - Cartogram creation using self-organizing maps

Dissertação apresentada como requisito parcial para obtenção do grau de Mestre em Ciência e Sistemas de Informação Geográfica

Planear e inovar : contributo para o planeamento de recursos com base nas necessidades auto-avaliadas pela população com 65 e mais anos

RESUMO - Enquadramento: O envelhecimento da população ocorre em todas as sociedades desenvolvidas, resultando num aumento da prevalência da dependência funcional, associado recorrentemente à presença de doenças crónicas. Estes novos padrões demográficos, epidemiológicos, implicando populações vulneráveis com necessidades específicas, resultam em desafios incontestáveis. Como resposta a este novo paradigma, em 2006, Portugal implementa a Rede Nacional de Cuidados Continuados Integrados (RNCCI). Finalidade/objectivos: Caracterização da população com base no perfil das necessidades auto-referidas pelas pessoas com ≥65 anos, com algum nível de independência/dependência nas actividades de vida diária e/ou com pelo menos uma doença crónica. Pretende-se, ainda, desenvolver uma metodologia que permita simular cenários que contribuam para o planeamento do número de camas para internamento de carácter permanente em Unidades de Longa Duração e Manutenção (ULDM) da RNCCI. Metodologia: Construção de dois indicadores: índice de independência/dependência e existência ou não de doenças crónicas. Análise estatística e caracterização, individual e conjunta, das variáveis sociodemográficas, socioeconómicas, auto-avaliação do estado de saúde, nível de independência/dependência e/ou existência de pelo menos uma doença crónica. Simulação de cenários com base nas metas definidas pela RNCCI para 2013. Resultados e Conclusões: Da aplicação do índice de independência/dependência, resulta que 78,8% são independentes na realização das actividades de vida diária e 21,2% apresentam algum nível de dependência. À excepção do Centro, todas as regiões apresentam padrões similares. Globalmente, os resultados obtidos vão de encontro aos enunciados na literatura internacional, realçando-se apenas alguns mais pertinentes: Observa-se uma predominância de mulheres idosas. Destaca-se também uma relação directa entre a idade e os níveis de dependência. As variáveis socioeconómicas indicam que a existência de algum nível de dependência tende a ser mais frequente entre os que têm menor escolaridade e rendimento. Em média o estado de saúde é auto-avaliado como mau, piorando com o aumento da idade e níveis de dependência mais acentuados e melhorando com o aumento da escolaridade. Da simulação de cenários destaca-se que, face às 4 camas previstas nas metas de 2013, seria de alocar em média 1,7 camas ou 1 cama ao internamento permanente em ULDM. Trabalhar em rede implica canais de comunicação. A incorporação da distribuição espacial das necessidades e serviços com recurso aos sistemas de informação geográfica torna-se numa mais-valia. Possibilita avaliar hipóteses, análises sustentadas e disseminação de informação e resultados, contribuindo para um planeamento, monitorização e avaliação mais eficaz e eficiente das actividades do sector da saúde. ---------------------------------- ABSTRACT - Background: Population aging occurs in all developed societies resulting in an increased prevalence of functional dependence, frequently associated with the presence of chronic diseases. These new demographic and epidemiological patterns, which include dependency ad vulnerability situations, with specific needs, result in undeniable challenges. In response to this new paradigm, in 2006, Portugal implements the National Network for Integrated Care (RNCCI). Aim/Objectives: Characterize the population based on the self-reported needs of ≥65 year’s people, with some level of independence/dependency in activities of daily living and/or with at least one chronic disease. Also intends to develop a methodological approach that allows scenarios simulation which contributes to the planning of the number of permanent inpatient beds in Long Term Care Units (ULDM) of RNCCI. Methods: Construction of two indicators: independence/dependence index and existence of chronic diseases. Statistical analysis and characterization, individually and jointly, of sociodemographics, socioeconomics, selfassessment of health status, level of independence/dependence and/or existence of at least one chronic disease variables. Scenarios simulation based on RNCCI targets set for 2013. Results and Conclusions: According with independence/dependence index, 78.8% are independent in carrying out the activities of daily living and 21.2% have some level of dependency. With the exception of the Centroregion, all regions have similar patterns. Generally, the results are concordant with international literature, highlighting here only some of the most relevant results: A predominance of older women is observed. A direct relationship between age and levels of dependence is emphasized. Socio-economic variables indicate that the existence of some level of dependency tends to be more frequent among those with lower income and education levels. On average, health status is self-assessed as poor, being even more critical with aging and higher dependency level. On the other hand, high education levels are related with better health status. Scenarios simulations highlights that, based on 4 beds considered in the 2013 planned goals, an average of 1.7 or 1 beds in ULDM should be allocated to permanent inpatient beds. Networking involves communication channels. The incorporation of spatial distribution of needs and services using geographical information systems becomes an added value. It enables hypothesis, evaluation, sustainable analysis and information and results dissemination, contributing to a more effective and efficient planning, monitoring and assessment of the health sector activities.

Protocolo de fisioterapia, com auxílio de biofeedback electromiográfico, em utentes com disfunções do ombro: efeitos na dor, funcionalidade e estabilidade dinâmica

RESUMO: Introdução: A dor e disfunções do movimento no complexo articular do ombro (CAO) são comuns e debilitantes. O uso de exercícios segundo os pressupostos de estabilidade dinâmica (ED), com auxílio de Biofeedback electromiográfico (BEMG) tem vindo a ser referido, como uma forma de aumentar a efectividade da intervenção nas disfunções do complexo articular do ombro (DCAO)Objectivo Principal: Estudar os efeitos de um protocolo de intervenção, com BEMG, cujas finalidades foram abolir a dor, aumentar a funcionalidade e a ED da omoplata, em utentes com DCAO. Objectivos secundários: Comparar os subgrupos e quanto às características, resultados, tempos de intervenção total e até atingir critérios de alta; Comparar os resultados nos momentos inicial e final. Métodos: Foi realizado um coorte clínico, longitudinal, retrospectivo, observacional, analítico. A amostra foi constituída por 82 sujeitos, divididos em dois subgrupos (n=53 SCSA e n=29 IGU). Os instrumentos de medida utilizados foram a EVA, o DASH, o SPADI e o BEMG. Foi seguido o protocolo de ED proposto por Santos e Matias (2007), de acordo com as 3 fases de intervenção por eles descritas, realizando uma sessão semanal, monitorizando exercícios que seguem estes princípios, com BEMG. Foram avaliadas as variáveis dor, postura, padrão de recrutamento, controlo motor, posição inicial da omoplata (PIO), amplitudes articulares (AA’s), força muscular (FM) e postura. Para analisar os dados, recorreu-se a estatística descritiva e inferencial. Resultados: A intervenção foi efectiva na abolição da dor no momento (0,43 para 0,00/10EVA no subgrupo SCSA e 0,66 para 0,00/10EVA no subgrupo IGU) na pior dor (5,47/10EVA para 0,06/10EVA no subgrupo SCSA e 5,28/10 para 0,14/10 no subgrupo IGU), no aumento da função (28,57 para 0,66/100DASH e 39,00 para 0,63/100SAPDI no subgrupo SCSA e 25,80 para 0,38/100DASH e 28,19 para 0,39/100 no subgrupo IGU) e no aumento da ED da omoplata com normalização do padrão de recrutamento, controlo motor, PIO dentro do espectro de normalidade e boa capacidade de controlar a sua posição, ao longo do movimento do membro superior (MS). A intervenção proporcionou, ainda a normalização das AA’s, FM e autocorrecção postural. O tempo médio de intervenção foi de 6,45semanas no subgrupo SCSA e 5,83sem no subgrupo IGU. Estes resultados são semelhantes comparativamente a estudos que utilizaram uma intervenção baseada nos mesmos princípios (Matias e Cruz, 2004; Cunha e Matias, 2006; Santos e Matias, 2007; Rodrigues e Matias, 2009). Conclusão: O protocolo de intervenção aplicado, com uso de exercícios baseados nos princípios da ED e uso de BEMG, permitiu o alcance dos objectivos, junto de utentes com DCAO (SCSA e IGU). Verificou-se que, independentemente da condição, os resultados foram idênticos em ambos subgrupos, não apresentando diferenças significativas entre as variáveis de medida final, o tempo total de intervenção e os tempos até atingir os critérios de alta, expecto para a Dor, sendo este superior no subgrupo SCSA.---------------------------------------- ABSTRACT:Introduction: Movement disorders and pain in the shoulder joint complex (SJC) are common and debilitating. The use of exercises under the premises of dynamic stability (DS), with the aid of electromyographic biofeedback (EMGBF) has been mentioned as a way to increase the effectiveness of the intervention in disorders of the shoulder joint complex (DSJC) Main Objective: To evaluate the results of an intervention protocol, with EMGBF whose aims were to abolish the pain, increase functionality and DS of the scapula in patients with DSJC. Objectives: To compare the subgroups and the characteristics, outcomes, and total intervention times to reach discharge criteria; to compare the results at the beginning and at the end. Methods: We conducted a clinical cohort, longitudinal, retrospective, observational analysis. The sample consisted of 82 subjects, divided into two subgroups (n = 53 shoulder impingement syndrome SIS n = 29 shoulder joint instability SJI). The measurement instruments used were the VAS, DASH, SPADI, and EMGBF. It was followed the DS protocol proposed by Santos and Matias (2007), according to the three phases of intervention, described by performing a weekly session, monitoring exercises that follow these principles, with EMGBF. The variables were pain, posture, recruitment pattern, motor control, the initial position of the scapula (IPS), range of motion (ROM), muscular strength (MS) and posture. To analyze the data, we used the descriptive and inferential statistics. Results: The intervention was effective in abolishing the pain at the time (0.43 to 0.00/10 VAS in the SIS subgroup and 0.66 to 0.00/10 VAS in the SJI subgroup) in worst pain (5.47 to 0,06/10 VAS in the SIS subgroup and 5.28/ to 0.14/10 VAS in the SJI subgroup), increasing the function (28,57 to 0,66/100 DASH and 39,00 to 0,63/100 SAPDI in the SIS subgroup and 25,80 to 0,38/100 DASH and 28,19 to 0,39/100 SPADI in the SJI subgroup) and the increase in DS of the scapula with normalization of the pattern recruitment, motor control, IPS within the spectrum of normalcy and good ability to control its position along the movement of the upper limb (UL). The intervention provided, although the normalization of ROM, MS and self-correcting posture. The average length of intervention was 6.45 weeks in the SIS subgroup and 5.83 in the IS subgroup. These results are comparable with similar studies that used an intervention based on the same principles (Matias e Cruz, 2004; Cunha e Matias, 2006; Santos e Matias, 2007; Rodrigues e Matias, 2009). Conclusion: The intervention protocol implemented with the use of exercises based on the principles of DS and the use of EMGBF was effective, allowing the accomplishment of goals, in patients with DSJC (SIS and SJI). It was found that, regardless of condition, the results were identical in both groups, showing no significant differences between the variables of the final measure, the total time of intervention and the times to reach discharge criteria, except for pain, which was higher in the SIS subgroup.

Reliability analysis of a timber truss system subjected to decay

Assessing the safety of existing timber structures is of paramount importance for taking reliable decisions on repair actions and their extent. The results obtained through semi-probabilistic methods are unrealistic, as the partial safety factors present in codes are calibrated considering the uncertainty present in new structures. In order to overcome these limitations, and also to include the effects of decay in the safety analysis, probabilistic methods, based on Monte-Carlo simulation are applied here to assess the safety of existing timber structures. In particular, the impact of decay on structural safety is analyzed and discussed, using a simple structural model, similar to that used for current semi-probabilistic analysis.

A qualitive reasoning approach for improving query results for sketch based queries by topological analysis of spatial aggregation

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

Spatial and temporal analysis of recent drought using vegetation temperature condition index: case of Somali regional state of Ethiopia

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

Integrated study by NMR and X-ray Crystallography on the analysis of the molecular interactions in heme-binding proteins

Dissertação para obtenção do Grau de Doutor em Bioquímica, Especialidade Bioquímica Estrutural

Recent droughts and the impact of North Atlantic Oscillation in Iberia; a spatiotemporal analysis based on vegetation temperature condition Index (VTCI)

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

Os enfermeiros e as dimensões motivacionais : estudo não experimental, descritivo, analítico e transversal, baseado na técnica de inquérito

RESUMO - A profissão de enfermagem é definida por Virgínia Henderson (1966), como tendo por objeto "ajudar o indivíduo, saudável ou doente, na execução das atividades que contribuem para conservar a sua saúde ou a sua recuperação, de tal maneira, devendo desempenhar esta função no sentido de tornar o indivíduo o mais independente possível, ou seja, a alcançar a sua anterior independência". A atenção à saúde ao longo da história da humanidade vem sendo desenvolvida de muitos modos e por diversos atores sociais. O trabalho em saúde é essencial para a vida humana e envolve atividades realizadas por profissionais e equipas multidisciplinares que dominam os conhecimentos e técnicas essenciais para assistir o indivíduo com problemas de saúde ou em risco de adoecer, em atividades de investigação, de prevenção, curativo e de reabilitação. À Enfermagem tal como a outras profissões, são cada vez mais exigidos requisitos de eficiência, eficácia e polivalência na sua atividade, tendo a motivação um papel fundamental na atitude, postura e desempenho do profissional. Este trabalho descreve o estudo da motivação profissional, numa população de enfermeiros portugueses numa instituição privada. A versão adaptada de um inquérito como instrumento de autopreenchimento representa vários construtos implicados no processo motivacional, em contexto profissional. Pretendo com este estudo identificar a dimensão da motivação mais relevantes no processo motivacional dos enfermeiros, assim como as suas variações face a variáveis de características pessoais, profissionais e institucionais. A partir dos resultados obtidos pretendo ainda apresentar sugestões de maneira a oferecer oportunidade de transformação do seu ambiente organizacional em instituições similares.