Automatic syllabification for danish text-to-speech systems

In this paper, a rule-based automatic syllabifier for Danish is described using the Maximal Onset Principle. Prior success rates of rule-based methods applied to Portuguese and Catalan syllabification modules were on the basis of this work. The system was implemented and tested using a very small set of rules. The results gave rise to 96.9% and 98.7% of word accuracy rate, contrary to our initial expectations, being Danish a language with a complex syllabic structure and thus difficult to be rule-driven. Comparison with data-driven syllabification system using artificial neural networks showed a higher accuracy rate of the former system.

High-Content Analysis of Breast Cancer Using Single-Cell Deep Transfer Learning

High-content analysis has revolutionized cancer drug discovery by identifying substances that alter the phenotype of a cell, which prevents tumor growth and metastasis. The high-resolution biofluorescence images from assays allow precise quantitative measures enabling the distinction of small molecules of a host cell from a tumor. In this work, we are particularly interested in the application of deep neural networks (DNNs), a cutting-edge machine learning method, to the classification of compounds in chemical mechanisms of action (MOAs). Compound classification has been performed using image-based profiling methods sometimes combined with feature reduction methods such as principal component analysis or factor analysis. In this article, we map the input features of each cell to a particular MOA class without using any treatment-level profiles or feature reduction methods. To the best of our knowledge, this is the first application of DNN in this domain, leveraging single-cell information. Furthermore, we use deep transfer learning (DTL) to alleviate the intensive and computational demanding effort of searching the huge parameter's space of a DNN. Results show that using this approach, we obtain a 30% speedup and a 2% accuracy improvement.

Previsão e definição de perfis na gestão dos recursos de energia no âmbito de edifícios auto-sustentáveis

Nos últimos anos o consumo de energia elétrica produzida a partir de fontes renováveis tem aumentado significativamente. Este aumento deve-se ao impacto ambiental que recursos como o petróleo, gás, urânio, carvão, entre outros, têm no meio ambiente e que são notáveis no diaa- dia com as alterações climáticas e o aquecimento global. Por sua vez, estes recursos têm um ciclo de vida limitado e a dada altura tornar-se-ão escassos. A preocupação de uma melhoria contínua na redução dos impactos ambientais levou à criação de Normas para uma gestão mais eficiente e sustentável do consumo de energia nos edifícios. Parte da eletricidade vendida pelas empresas de comercialização é produzida através de fontes renováveis, e com a recente publicação do Decreto de Lei nº 153/2014 de 20 outubro de 2014 que regulamenta o autoconsumo, permitindo que também os consumidores possam produzir a sua própria energia nas suas residências para reduzir os custos com a compra de eletricidade. Neste contexto surgiram os edifícios inteligentes. Por edifícios inteligentes entende-se que são edifícios construídos com materiais que os tornam mais eficientes, possuem iluminação e equipamentos elétricos mais eficientes, e têm sistemas de produção de energia que permitem alimentar o próprio edifício, para um consumo mais sustentado. Os sistemas implementados nos edifícios inteligentes visam a monitorização e gestão da energia consumida e produzida para evitar desperdícios de consumo. O trabalho desenvolvido visa o estudo e a implementação de Redes Neuronais Artificiais (RNA) para prever os consumos de energia elétrica dos edifícios N e I do ISEP/GECAD, bem como a previsão da produção dos seus painéis fotovoltáicos. O estudo feito aos dados de consumo permitiu identificar perfis típicos de consumo ao longo de uma semana e de que forma são influenciados pelo contexto, nomeadamente, com os dias da semana versus fim-de-semana, e com as estações do ano, sendo analisados perfis de consumo de inverno e verão. A produção de energia através de painéis fotovoltaicos foi também analisada para perceber se a produção atual é suficiente para satisfazer as necessidades de consumo dos edifícios. Também foi analisada a possibilidade da produção satisfazer parcialmente as necessidades de consumos específicos, por exemplo, da iluminação dos edifícios, dos seus sistemas de ar condicionado ou dos equipamentos usados.

Scalable Intelligence for Scheduling Systems

A personalização é um aspeto chave de uma interação homem-computador efetiva. Numa era em que existe uma abundância de informação e tantas pessoas a interagir com ela, de muitas maneiras, a capacidade de se ajustar aos seus utilizadores é crucial para qualquer sistema moderno. A criação de sistemas adaptáveis é um domínio bastante complexo que necessita de métodos muito específicos para ter sucesso. No entanto, nos dias de hoje ainda não existe um modelo ou arquitetura padrão para usar nos sistemas adaptativos modernos. A principal motivação desta tese é a proposta de uma arquitetura para modelação do utilizador que seja capaz de incorporar diferentes módulos necessários para criar um sistema com inteligência escalável com técnicas de modelação. Os módulos cooperam de forma a analisar os utilizadores e caracterizar o seu comportamento, usando essa informação para fornecer uma experiência de sistema customizada que irá aumentar não só a usabilidade do sistema mas também a produtividade e conhecimento do utilizador. A arquitetura proposta é constituída por três componentes: uma unidade de informação do utilizador, uma estrutura matemática capaz de classificar os utilizadores e a técnica a usar quando se adapta o conteúdo. A unidade de informação do utilizador é responsável por conhecer os vários tipos de indivíduos que podem usar o sistema, por capturar cada detalhe de interações relevantes entre si e os seus utilizadores e também contém a base de dados que guarda essa informação. A estrutura matemática é o classificador de utilizadores, e tem como tarefa a sua análise e classificação num de três perfis: iniciado, intermédio ou avançado. Tanto as redes de Bayes como as neuronais são utilizadas, e uma explicação de como as preparar e treinar para lidar com a informação do utilizador é apresentada. Com o perfil do utilizador definido torna-se necessária uma técnica para adaptar o conteúdo do sistema. Nesta proposta, uma abordagem de iniciativa mista é apresentada tendo como base a liberdade de tanto o utilizador como o sistema controlarem a comunicação entre si. A arquitetura proposta foi desenvolvida como parte integrante do projeto ADSyS - um sistema de escalonamento dinâmico - utilizado para resolver problemas de escalonamento sujeitos a eventos dinâmicos. Possui uma complexidade elevada mesmo para utilizadores frequentes, daí a necessidade de adaptar o seu conteúdo de forma a aumentar a sua usabilidade. Com o objetivo de avaliar as contribuições deste trabalho, um estudo computacional acerca do reconhecimento dos utilizadores foi desenvolvido, tendo por base duas sessões de avaliação de usabilidade com grupos de utilizadores distintos. Foi possível concluir acerca dos benefícios na utilização de técnicas de modelação do utilizador com a arquitetura proposta.

Redes Neuronais Artificiais na Otimização do Processo de Digestão Anaeróbia - Aplicação a uma ETAR da AdCL

Numa sociedade com elevado consumo energético, a dependência de combustíveis fósseis em evidente diminuição de disponibilidades é um tema cada vez mais preocupante, assim como a poluição atmosférica resultante da sua utilização. Existe, portanto, uma necessidade crescente de recorrer a energias renováveis e promover a otimização e utilização de recursos. A digestão anaeróbia (DA) de lamas é um processo de estabilização de lamas utilizado nas Estações de Tratamento de Águas Residuais (ETAR) e tem, como produtos finais, a lama digerida e o biogás. Maioritariamente constituído por gás metano, o biogás pode ser utilizado como fonte de energia, reduzindo, deste modo, a dependência energética da ETAR e a emissão de gases com efeito de estufa para a atmosfera. A otimização do processo de DA das lamas é essencial para o aumento da produção de biogás. No presente relatório de estágio, as Redes Neuronais Artificiais (RNA) foram aplicadas ao processo de DA de lamas de ETAR. As RNA são modelos simplificados inspirados no funcionamento das células neuronais humanas e que adquirem conhecimento através da experiência. Quando a RNA é criada e treinada, produz valores de output aproximadamente corretos para os inputs fornecidos. Uma vez que as DA são um processo bastante complexo, a sua otimização apresenta diversas dificuldades. Foi esse o motivo para recorrer a RNA na otimização da produção de biogás nos digestores das ETAR de Espinho e de Ílhavo da AdCL, utilizando o software NeuralToolsTM da PalisadeTM, contribuindo, desta forma, para a compreensão do processo e do impacto de algumas variáveis na produção de biogás.

Inteligência artificial aplicada na previsão de mercados financeiros

Neste documento, são investigados vários métodos usados na inteligência artificial, com o objetivo de obter previsões precisas da evolução dos mercados financeiros. O uso de ferramentas lineares como os modelos AR, MA, ARMA e GARCH têm muitas limitações, pois torna-se muito difícil adaptá-los às não linearidades dos fenómenos que ocorrem nos mercados. Pelas razões anteriormente referidas, os algoritmos como as redes neuronais dinâmicas (TDNN, NARX e ESN), mostram uma maior capacidade de adaptação a estas não linearidades, pois não fazem qualquer pressuposto sobre as distribuições de probabilidade que caracterizam estes mercados. O facto destas redes neuronais serem dinâmicas, faz com que estas exibam um desempenho superior em relação às redes neuronais estáticas, ou outros algoritmos que não possuem qualquer tipo de memória. Apesar das vantagens reveladas pelas redes neuronais, estas são um sistema do tipo black box, o que torna muito difícil extrair informação dos pesos da rede. Isto significa que estes algoritmos devem ser usados com precaução, pois podem tornar-se instáveis.

Ensemble classifiers in remote sensing: a comparative analysis

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

Creation of a web application for smart park system and parking prediction study for system integration

In the last few years, we have observed an exponential increasing of the information systems, and parking information is one more example of them. The needs of obtaining reliable and updated information of parking slots availability are very important in the goal of traffic reduction. Also parking slot prediction is a new topic that has already started to be applied. San Francisco in America and Santander in Spain are examples of such projects carried out to obtain this kind of information. The aim of this thesis is the study and evaluation of methodologies for parking slot prediction and the integration in a web application, where all kind of users will be able to know the current parking status and also future status according to parking model predictions. The source of the data is ancillary in this work but it needs to be understood anyway to understand the parking behaviour. Actually, there are many modelling techniques used for this purpose such as time series analysis, decision trees, neural networks and clustering. In this work, the author explains the best techniques at this work, analyzes the result and points out the advantages and disadvantages of each one. The model will learn the periodic and seasonal patterns of the parking status behaviour, and with this knowledge it can predict future status values given a date. The data used comes from the Smart Park Ontinyent and it is about parking occupancy status together with timestamps and it is stored in a database. After data acquisition, data analysis and pre-processing was needed for model implementations. The first test done was with the boosting ensemble classifier, employed over a set of decision trees, created with C5.0 algorithm from a set of training samples, to assign a prediction value to each object. In addition to the predictions, this work has got measurements error that indicates the reliability of the outcome predictions being correct. The second test was done using the function fitting seasonal exponential smoothing tbats model. Finally as the last test, it has been tried a model that is actually a combination of the previous two models, just to see the result of this combination. The results were quite good for all of them, having error averages of 6.2, 6.6 and 5.4 in vacancies predictions for the three models respectively. This means from a parking of 47 places a 10% average error in parking slot predictions. This result could be even better with longer data available. In order to make this kind of information visible and reachable from everyone having a device with internet connection, a web application was made for this purpose. Beside the data displaying, this application also offers different functions to improve the task of searching for parking. The new functions, apart from parking prediction, were: - Park distances from user location. It provides all the distances to user current location to the different parks in the city. - Geocoding. The service for matching a literal description or an address to a concrete location. - Geolocation. The service for positioning the user. - Parking list panel. This is not a service neither a function, is just a better visualization and better handling of the information.

Improving silicon probe performance through layer-by-layer coating

Fully comprehending brain function, as the scale of neural networks, will only be possi-ble with the development of tools by micro and nanofabrication. Regarding specifically silicon microelectrodes arrays, a significant improvement in long-term performance of these implants is essential. This project aims to create a silicon microelectrode coating that provides high-quality electrical recordings, while limiting the inflammatory response of chronic implants. To this purpose, a combined chitosan and gold nanoparticles coating was produced allied with electrodes modification by electrodeposition with PEDOT/PSS in order to reduce the im-pedance at 1kHz. Using a dip-coating mechanism, the silicon probe was coated and then charac-terized both morphologically and electrochemically, with focus on the stability of post-surgery performance in anesthetized rodents. Since not only the inflammatory response analysis is vital, the electrodes recording degradation over time was also studied. The produced film presented a thickness of approximately 50 μm that led to an increase of impedance of less than 20 kΩ in average. On a 3 week chronic implant, the impedance in-crease on the coated probe was of 641 kΩ, compared with 2.4 MΩ obtained for the uncoated probe. The inflammatory response was also significantly reduced due to the biocompatible film as proved by histological tests.

Modeling and optimization of extracellular polysaccharides production by Enterobacter A47

Polysaccharides are gaining increasing attention as potential environmental friendly and sustainable building blocks in many fields of the (bio)chemical industry. The microbial production of polysaccharides is envisioned as a promising path, since higher biomass growth rates are possible and therefore higher productivities may be achieved compared to vegetable or animal polysaccharides sources. This Ph.D. thesis focuses on the modeling and optimization of a particular microbial polysaccharide, namely the production of extracellular polysaccharides (EPS) by the bacterial strain Enterobacter A47. Enterobacter A47 was found to be a metabolically versatile organism in terms of its adaptability to complex media, notably capable of achieving high growth rates in media containing glycerol byproduct from the biodiesel industry. However, the industrial implementation of this production process is still hampered due to a largely unoptimized process. Kinetic rates from the bioreactor operation are heavily dependent on operational parameters such as temperature, pH, stirring and aeration rate. The increase of culture broth viscosity is a common feature of this culture and has a major impact on the overall performance. This fact complicates the mathematical modeling of the process, limiting the possibility to understand, control and optimize productivity. In order to tackle this difficulty, data-driven mathematical methodologies such as Artificial Neural Networks can be employed to incorporate additional process data to complement the known mathematical description of the fermentation kinetics. In this Ph.D. thesis, we have adopted such an hybrid modeling framework that enabled the incorporation of temperature, pH and viscosity effects on the fermentation kinetics in order to improve the dynamical modeling and optimization of the process. A model-based optimization method was implemented that enabled to design bioreactor optimal control strategies in the sense of EPS productivity maximization. It is also critical to understand EPS synthesis at the level of the bacterial metabolism, since the production of EPS is a tightly regulated process. Methods of pathway analysis provide a means to unravel the fundamental pathways and their controls in bioprocesses. In the present Ph.D. thesis, a novel methodology called Principal Elementary Mode Analysis (PEMA) was developed and implemented that enabled to identify which cellular fluxes are activated under different conditions of temperature and pH. It is shown that differences in these two parameters affect the chemical composition of EPS, hence they are critical for the regulation of the product synthesis. In future studies, the knowledge provided by PEMA could foster the development of metabolically meaningful control strategies that target the EPS sugar content and oder product quality parameters.

Using customer lifetime value to improve the prediction of bank deposit subscription in telemarketing campaigns

Customer lifetime value (LTV) enables using client characteristics, such as recency, frequency and monetary (RFM) value, to describe the value of a client through time in terms of profitability. We present the concept of LTV applied to telemarketing for improving the return-on-investment, using a recent (from 2008 to 2013) and real case study of bank campaigns to sell long- term deposits. The goal was to benefit from past contacts history to extract additional knowledge. A total of twelve LTV input variables were tested, un- der a forward selection method and using a realistic rolling windows scheme, highlighting the validity of five new LTV features. The results achieved by our LTV data-driven approach using neural networks allowed an improvement up to 4 pp in the Lift cumulative curve for targeting the deposit subscribers when compared with a baseline model (with no history data). Explanatory knowledge was also extracted from the proposed model, revealing two highly relevant LTV features, the last result of the previous campaign to sell the same product and the frequency of past client successes. The obtained results are particularly valuable for contact center companies, which can improve pre- dictive performance without even having to ask for more information to the companies they serve.

A soft computing approach to kidney diseases evaluation

Kidney renal failure means that one’s kidney have unexpectedly stopped functioning, i.e., once chronic disease is exposed, the presence or degree of kidney dysfunction and its progression must be assessed, and the underlying syndrome has to be diagnosed. Although the patient’s history and physical examination may denote good practice, some key information has to be obtained from valuation of the glomerular filtration rate, and the analysis of serum biomarkers. Indeed, chronic kidney sickness depicts anomalous kidney function and/or its makeup, i.e., there is evidence that treatment may avoid or delay its progression, either by reducing and prevent the development of some associated complications, namely hypertension, obesity, diabetes mellitus, and cardiovascular complications. Acute kidney injury appears abruptly, with a rapid deterioration of the renal function, but is often reversible if it is recognized early and treated promptly. In both situations, i.e., acute kidney injury and chronic kidney disease, an early intervention can significantly improve the prognosis.The assessment of these pathologies is therefore mandatory, although it is hard to do it with traditional methodologies and existing tools for problem solving. Hence, in this work, we will focus on the development of a hybrid decision support system, in terms of its knowledge representation and reasoning procedures based on Logic Programming, that will allow one to consider incomplete, unknown, and even contradictory information, complemented with an approach to computing centered on Artificial Neural Networks, in order to weigh the Degree-of-Confidence that one has on such a happening. The present study involved 558 patients with an age average of 51.7 years and the chronic kidney disease was observed in 175 cases. The dataset comprise twenty four variables, grouped into five main categories. The proposed model showed a good performance in the diagnosis of chronic kidney disease, since the sensitivity and the specificity exhibited values range between 93.1 and 94.9 and 91.9–94.2 %, respectively.

An assessment of chronic kidney diseases

Kidney renal failure means that one’s kidney have unexpectedlystoppedfunctioning,i.e.,oncechronicdiseaseis exposed, the presence or degree of kidney dysfunction and its progression must be assessed, and the underlying syndrome has to be diagnosed. Although the patient’s history and physical examination may denote good practice, some key information has to be obtained from valuation of the glomerular filtration rate, and the analysis of serum biomarkers. Indeed, chronic kidney sickness depicts anomalous kidney function and/or its makeup, i.e., there is evidence that treatment may avoid or delay its progression, either by reducing and prevent the development of some associated complications, namely hypertension, obesity, diabetes mellitus, and cardiovascular complications. Acute kidney injury appears abruptly, with a rapiddeteriorationoftherenalfunction,butisoftenreversible if it is recognized early and treated promptly. In both situations, i.e., acute kidney injury and chronic kidney disease, an early intervention can significantly improve the prognosis. The assessment of these pathologies is therefore mandatory, although it is hard to do it with traditional methodologies and existing tools for problem solving. Hence, in this work, we will focus on the development of a hybrid decision support system, in terms of its knowledge representation and reasoning procedures based on Logic Programming, that will allow onetoconsiderincomplete,unknown,and evencontradictory information, complemented with an approach to computing centered on Artificial Neural Networks, in order to weigh the Degree-of-Confidence that one has on such a happening. The present study involved 558 patients with an age average of 51.7 years and the chronic kidney disease was observed in 175 cases. The dataset comprise twenty four variables, grouped into five main categories. The proposed model showed a good performance in the diagnosis of chronic kidney disease, since the sensitivity and the specificity exhibited values range between 93.1 and 94.9 and 91.9–94.2 %, respectively.

An evaluation of parchments' degradation a hybrid approach

Parchment stands for a multifaceted material made from animal skin, which has been used for centuries as a writing support or as bookbinding. Due to the historic value of objects made of parchment, understanding their degradation and their condition is of utmost importance to archives, libraries and museums, i.e., the assessment of parchment degradation is mandatory, although it is hard to do with traditional methodologies and tools for problem solving. Hence, in this work we will focus on the development of a hybrid decision support system, in terms of its knowledge representation and reasoning procedures, under a formal framework based on Logic Programming, complemented with an approach to computing centered on Artificial Neural Networks, to evaluate Parchment Degradation and the respective Degree-of-Confidence that one has on such a happening.

Desenvolvimento de rede neuronal artificial para o diagnóstico de doenças neurodegenerativas

Dissertação de mestrado integrado em Engenharia Eletrónica Industrial e Computadores