Planeamento e otimização de femto-células em ambiente empresarial

O objetivo deste trabalho consiste em avaliar as capacidades das femto-células, no âmbito do planeamento e otimização de redes Universal Mobile Telecommunication System (UMTS) instaladas no interior de edifícios num ambiente empresarial. A avaliação será feita através do estudo da tecnologia das femto-células, e do planeamento efetuado num cenário real onde, através do desenvolvimento e teste de um conjunto parametrizações, será avaliado o funcionamento das femto-células assim como forma de otimizar o seu desempenho. O estudo realizado permitiu identificar um conjunto de características que as femto-células partilham com as Self-Organizing Networks (SON), como a auto-configuração, auto-otimização de parâmetros rádio, ajuste dinâmico da área de cobertura, atribuição automática de Scrambling Codes (SC) e da frequência da portadora, criação automática de relações de vizinhança, entre outras, que permitem facilitar o processo de planeamento e otimização de redes móveis UMTS. Recorrendo a um cenário empresarial real, foi efetuado um planeamento celular indoor de raiz, através do qual foi possível testar o funcionamento da algumas das principais funções das femto-células, nomeadamente a capacidade de ajuste dinâmico da área de cobertura. Foi também avaliado o funcionamento de um grupo co-localizado de femto-células, onde foi possível testar parametrizações com o objetivo de melhorar o processo de handover entre as femto-células do grupo, e entre estas e a rede macro Global System for Mobile Communications (GSM). A avaliação de cada um de cada uma das parametrizações testada, é efetuada a partir das medidas recolhidas no terreno, recorrendo à ferramenta TEMS® Investigation, assim como aos Key Performance Indicators (KPIs) que as femto-células disponibilizam. Os resultados obtidos mostram o benefício da utilização das femto-células num ambiente empresarial real, assim como os eventuais problemas e desafios que podem surguir do planeamento celular indoor recorrendo à tecnologia das femto-células, sendo apresentada a parametrização que permite obter o melhor desempenho da rede instalada.

Detecção de sectores cruzados e optimização de cobertura em redes LTE

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

Optimização da lista de células vizinhas em redes LTE

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

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.

Improving accuracy for OTD based 3G geolocation in real urban/suburban environments

This paper presents the recent research results about the development of a Observed Time Difference (OTD) based geolocation algorithm based on network trace data, for a real Universal Mobile Telecommunication System (UMTS) Network. The initial results have been published in [1], the current paper focus on increasing the sample convergence rate, and introducing a new filtering approach based on a moving average spatial filter, to increase accuracy. Field tests have been carried out for two radio environments (urban and suburban) in the Lisbon area, Portugal. The new enhancements produced a geopositioning success rate of 47% and 31%, and a median accuracy of 151 m and 337 m, for the urban and suburban environments, respectively. The implemented filter produced a 16% and 20% increase on accuracy, when compared with the geopositioned raw data. The obtained results are rather promising in accuracy and geolocation success rate. OTD positioning smoothed by moving average spatial filtering reveals a strong approach for positioning trace extracted events, vital for boosting Self-Organizing Networks (SON) over a 3G network.

Neighbour list optimization for real LTE radio network

With the increasing complexity of current networks, it became evident the need for Self-Organizing Networks (SON), which aims to automate most of the associated radio planning and optimization tasks. Within SON, this paper aims to optimize the Neighbour Cell List (NCL) for Long Term Evolution (LTE) evolved NodeBs (eNBs). An algorithm composed by three decisions were were developed: distance-based, Radio Frequency (RF) measurement-based and Handover (HO) stats-based. The distance-based decision, proposes a new NCL taking account the eNB location and interference tiers, based in the quadrants method. The last two algorithms consider signal strength measurements and HO statistics, respectively; they also define a ranking to each eNB and neighbour relation addition/removal based on user defined constraints. The algorithms were developed and implemented over an already existent radio network optimization professional tool. Several case studies were produced using real data from a Portuguese LTE mobile operator. © 2014 IEEE.

Análise espacial do habitat do lobo no Noroeste de Portugal

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

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

Caracterização das NUTS da Europa de acordo com a dinâmica de ocupações/uso do solo entre 1990 e 2000

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

Modelação do risco de incêndio florestal com redes neuronais artificiais: aplicação ao Parque Natural de Montesinho

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

O empreendedorismo social como promotor da integração socioprofissional: um estudo exploratório

Dissertação de Mestrado apresentado ao Instituto de Contabilidade e Administração do Porto para a obtenção do grau de Mestre em Empreendedorismo e Internacionalização, sob orientação de Dra. Susana Bernardino e Professor Doutor José Freitas Santos

A aplicação de redes neuronais na deteção da influência do High Frequency Trading na negociação de ações (caso português)

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

Exploraty Multivariate Statistical Methods Applied to Pharmaceutical Industry CRM Data

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

Diabetes : percepção da doença e auto-cuidado

RESUMO - O aumento da prevalência da diabetes e a baixa adesão ao seu tratamento estão associados a um mau controlo metabólico, desenvolvimento de complicações, aumento dos custos económicos e ineficiência do sistema de saúde. De acordo com o modelo de auto-regulação, o estudo das representações da doença permite predizer os comportamentos dos doentes face a esta patologia. O objectivo do estudo é verificar a existência de relação entre a forma como os diabéticos tipo 2 percepcionam a sua doença, de acordo com o modelo de auto-regulação de Leventhal e colaboradores, e a adesão às actividades de auto-cuidado da diabetes. Consiste num estudo observacional, descritivo, analítico, do tipo transversal, a desenvolver em Cuidados de Saúde Primários. A amostra é constituída por 339 indivíduos diabéticos, de ambos os sexos, com idade igual ou superior a 20 anos e com diagnóstico de diabetes tipo 2 há mais de 6 meses. Trata-se de uma amostra probabilística, aleatória simples, seleccionada numa Unidade de Saúde Familiar (USF). A recolha de dados é realizada através do preenchimento de uma ficha de caracterização socio-demográfica e clínica, a partir do processo clínico electrónico, e através da aplicação de dois questionários de auto-preenchimento. Os resultados são analisados através do Statistical Program for Social Sciences (SPSS) – versão 17.0.

Avaliação da evolução do perfil regional em inovação. O caso das regiões europeias 2003/2009

A inovação é considerada pelos economistas como fator determinante para o crescimento económico e social sustentável. No contexto da atual economia, global e marcada por uma profunda crise, torna-se imperativo compreender os padrões de inovação para suportar melhores políticas e respostas aos desafios que se impõem. Este entendimento conduz à ilação de que os desvios significativos no crescimento económico observado entre diferentes regiões são também explicados por diferenças espaciais nos padrões de inovação. Na sequência do exposto tem-se assistido a um renovado e crescente interesse no estudo da inovação numa perspetiva territorial e a uma crescente produção e disponibilização de dados para estudo e compreensão das suas dinâmicas. O objectivo principal da presente dissertação é demonstrar a utilidade de uma técnica de Data Mining, a rede neuronal Self Organizing Map, na exploração destes dados para estudo da inovação. Em concreto pretende-se demonstrar a capacidade desta técnica tanto para identificar perfis regionais de inovação bem como para visualizar a evolução desses perfis no tempo num mapa topológico virtual, o espaço de atributos do SOM, por comparação com um mapa geográfico. Foram utilizados dados Euronext relativos a 236 regiões europeias para os anos compreendidos entre 2003 e 2009. O Self Organizing Map foi construído com base no GeoSOM, software desenvolvido pelo Instituto Superior de Estatística e Gestão de Informação. Os resultados obtidos permitem demonstrar a utilidade desta técnica na visualização dos padrões de inovação das regiões europeias no espaço e no tempo.