Artificial Neural Network for Compositional Ionic Liquid Viscosity Prediction

Being a new generation of green solvents and high-tech reaction media of the future, ionic liquids have increasingly attracted much attention. Of particular interest in this context are room temperature ionic liquids (in short as ILs in this paper). Due to the relatively high viscosity, ILs is expected to be used in the form of solvent diluted mixture with reduced viscosity in industrial application, where predicting the viscosity of IL mixture has been an important research issue. Different IL mixture and many modelling approaches have been investigated. The objective of this study is to provide an alternative model approach using soft computing technique, i.e., artificial neural network (ANN) model, to predict the compositional viscosity of binary mixtures of ILs [C _n-mim][NTf ₂] with n=4, 6, 8, 10 in methanol and ethanol over the entire range of molar fraction at a broad range of temperatures from T=293.0-328.0K. The results show that the proposed ANN model provides alternative way to predict compositional viscosity successfully with highly improved accuracy and also show its potential to be extensively utilized to predict compositional viscosity taking account of IL alkyl chain length, as well as temperature and compositions simultaneously, i.e., more complex intermolecular interactions between components in which it would be hard or impossible to establish the analytical model. This illustrates the potential application of ANN in the case that the physical and thermodynamic properties are highly non-linear or too complex. © 2012 Copyright the authors.

Artificial neural network model to predict compositional viscosity over a broad range of temperatures

The objective of this study is to provide an alternative model approach, i.e., artificial neural network (ANN) model, to predict the compositional viscosity of binary mixtures of room temperature ionic liquids (in short as ILs) [C _n-mim] [NTf ₂] with n=4, 6, 8, 10 in methanol and ethanol over the entire range of molar fraction at a broad range of temperatures from T=293.0328.0K. The results show that the proposed ANN model provides alternative way to predict compositional viscosity successfully with highly improved accuracy and also show its potential to be extensively utilized to predict compositional viscosity over a wide range of temperatures and more complex viscosity compositions, i.e., more complex intermolecular interactions between components in which it would be hard or impossible to establish the analytical model. © 2010 IEEE.

Non-parametric bill of quantities estimation of concrete road bridges' superstructure: an artificial neural networks approach

Bridge construction responds to the need for environmentally friendly design of motorways and facilitates the passage through sensitive natural areas and the bypassing of urban areas. However, according to numerous research studies, bridge construction presents substantial budget overruns. Therefore, it is necessary early in the planning process for the decision makers to have reliable estimates of the final cost based on previously constructed projects. At the same time, the current European financial crisis reduces the available capital for investments and financial institutions are even less willing to finance transportation infrastructure. Consequently, it is even more necessary today to estimate the budget of high-cost construction projects -such as road bridges- with reasonable accuracy, in order for the state funds to be invested with lower risk and the projects to be designed with the highest possible efficiency. In this paper, a Bill-of-Quantities (BoQ) estimation tool for road bridges is developed in order to support the decisions made at the preliminary planning and design stages of highways. Specifically, a Feed-Forward Artificial Neural Network (ANN) with a hidden layer of 10 neurons is trained to predict the superstructure material quantities (concrete, pre-stressed steel and reinforcing steel) using the width of the deck, the adjusted length of span or cantilever and the type of the bridge as input variables. The training dataset includes actual data from 68 recently constructed concrete motorway bridges in Greece. According to the relevant metrics, the developed model captures very well the complex interrelations in the dataset and demonstrates strong generalisation capability. Furthermore, it outperforms the linear regression models developed for the same dataset. Therefore, the proposed cost estimation model stands as a useful and reliable tool for the construction industry as it enables planners to reach informed decisions for technical and economic planning of concrete bridge projects from their early implementation stages.

Factores que influenciam o peso e crescimento de cabritos da raça Murciana-granadina, em aleitamento artificial

A exploração caprina de leite tem evoluído no sentido de alguma intensificação, com recurso a raças de elevado potencial produtivo, de que é exemplo a raça Murciana- Granadina. O leite constitui a principal fonte de receita destas explorações. Complementarmente, vendem animais para carne e, as de melhor nível genético, animais para reprodutores. Analisaram-se os pesos de 241 cabritos da raça Murciana-Granadina, numa exploração comercial, com o objectivo de quantificar os pesos e crescimento de cabritos, e identificar os factores que os influenciam. Os cabritos foram aleitados artificialmente, em regime ad libitum, com leite de substituição comercial, dispondo ainda de concentrado comercial, feno de luzerna e palha. Os cabritos foram pesados ao nascimento e, posteriormente, semanalmente, até aos 60 dias de idade. Calcularam-se os respetivos pesos ajustados, bem como os ganhos médios diários, a diferentes idades padrão. Procedeu-se a uma análise de variância com um modelo linear que incluiu os efeitos da época de parto, tipo de parto, sexo e idade da cabra. Foram registados pesos superiores nos partos simples e duplos, relativamente aos triplos, e nos machos, relativamente às fêmeas. Os ganhos médios diários, a partir do mês de idade, registaram valores inferiores na época inverno-primavera, comparativamente com a época primavera-verão. Dairy goat farming has evolved towards intensification, with increased use of high milk-yielding breeds, including the Murciano-Granadina breed. Milk is the main source of farm income. Secondary income sources are the sale of animals for meat and, in genetically superior herds, the sale of breeding animals. The weights of 241 commercial farms artificially reared Murciano-Granadina kids were analyzed with the objective of quantifying weight and growth and identifying variation factors. Kids were artificially reared to weaning, on ad libitum commercial milk replacer, commercial concentrate, lucerne hay and straw. Kids were weighed at birth and at weekly intervals until 60 days of age. Age adjusted weights and growth-rates were calculated. A variance analysis was performed with a model including the effects of season of birth, number of kids per kidding, sex and age of dam. Single and twin-born kids had higher weights than triplets, and males had higher weights than females. Average daily gain after one month of age was lower for kids born in winter-spring than for those born in spring-summer

Logic Programming and Artificial Neural Networks in Pharmacological Screening of Schinus Essential Oils

Some plants of genus Schinus have been used in the folk medicine as topical antiseptic, digestive, purgative, diuretic, analgesic or antidepressant, and also for respiratory and urinary infections. Chemical composition of essential oils of S. molle and S. terebinthifolius had been evaluated and presented high variability according with the part of the plant studied and with the geographic and climatic regions. The pharmacological properties, namely antimicrobial, anti-tumoural and anti-inflammatory activities are conditioned by chemical composition of essential oils. Taking into account the difficulty to infer the pharmacological properties of Schinus essential oils without hard experimental approach, this work will focus on the development of a 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 and the respective Degree-of-Confidence that one has on such an occurrence.

Modelo para a valorização partilhada da marca: a comunicação mediada por computador como suporte ao envolvimento dos recursos humanos na cocriação da marca organizacional

No atual contexto de disseminação e uso das tecnologias da comunicação para a geração de conteúdo não especializado, igualmente partilhado e utilizado, torna-se pertinente sublinhar a participação dos recursos humanos na cocriação da marca organizacional. Esta participação, todavia, encontra alguns constrangimentos e necessidades, tais como a falta de orientação no uso devido da marca gráfica, e a adequação das ferramentas comunicacionais e de gestão do conhecimento de que estes indivíduos são portadores. Neste enquadramento, pretende-se validar um modelo heurístico que explique, satisfatoriamente, de que forma as organizações podem envolver os seus recursos humanos em atividades de valorização da marca, em contextos de informação e comunicação tecnologicamente mediados, e que possa assumirse como um impulsionador da adoção destas práticas. A abordagem metodológica é de natureza exploratória, iterativa e qualitativa, assentando na Grounded Theory e, portanto, num processo indutivo de produção de conhecimento, reconhecendo a existência de momentos de descoberta e, aproximando-se do paradigma construtivista. O estudo que conduz à proposta final de um modelo de comunicação mediada por computador para a valorização da marca assenta, essencialmente, na revisão da literatura através da pesquisa bibliográfica, e num estudo de caso, que assume como procedimentos técnicos os inquéritos por entrevista, para uma primeira verificação dos pressupostos do modelo, a construção de um protótipo não-funcional de uma Central Participativa de Marca (CPM), capaz de expressar a componente tecnológica presente no modelo, e a realização de grupos focais, com o intuito de alcançar a sua validação não-experimental. O estudo de caso realizado debruça-se sobre a Universidade de Aveiro (UA) e sobre o uso e apropriação da sua marca, por parte dos membros da sua comunidade docente e não-docente. Os resultados das entrevistas exploratórias, para as quais se recorre a uma amostra por conveniência composta por entidades relevantes no que à promoção da marca da UA concerne, são combinados com os conteúdos extraídos do levantamento bibliográfico, de modo a serem contemplados tanto na aferição dos domínios de interação que informam o modelo, como na conceção do protótipo de uma plataforma de colaboração online, especificamente orientada à marca, apresentado a cinco grupos focais que neles integram a população-alvo estudada. Este estudo empírico permite uma primeira validação do modelo heurístico proposto, confirmando que a participação na cocriação de artefactos de marca tende a acontecer de forma não oficial, por falta de iniciativas organizacionais que valorizem o capital humano, e que a orientação para o uso e apropriação da marca é fundamental na concretização deste tipo de contributos, dados por indivíduos não especializados em branding, design, comunicação ou estratégia de marketing. Os resultados permitem validar ainda a configuração e a estrutura de interação propostas para o sistema subjacente ao protótipo da CPM, assim como a generalidade das suas funcionalidades, permitindo a proposta de uma heurística focada na experimentação da marca no seio organizacional. Finalmente, são identificadas linhas de investigação futura nesta área, decorrentes dos resultados alcançados e das limitações do estudo realizado.

Soft-computing techniques applied to artificial tissue temperature estimation

Tese dout., Engenharia electrónica e computação - Processamento de sinal, Universidade do Algarve, 2008

Experimental study of the macrobenthic colonisation and secondary production in the artificial reefs of Algarve coast

Tese de dout., Ciências do Mar, Faculdade de Ciências do Mar e do Ambiente, Universidade do Algarve, 2010

Chemical communication in the Mozambique tilapia: a role for amino acids

The Mozambique tilapia (Oreochromis mossambicus) is a maternal mouthbrooding cichlid from the southern Africa. The olfactory sensitivity of the species to 20 amino acids was assessed using the electro-olfactogram (EOG). We estimated whether the olfactory potency of the polar fraction of male urine can be explained by the presence of identified amino acids. In addition, filtrate and amino acid mixture of the urine of Nile tilapia were used to estimate their olfactory potency for O.mossambicus. Finally, concentrations of the main amino acids were measured in the urine of males of different social status and the correlations between amino acid concentration and hierarchical status were explored. L-cysteine, L-glutamine and L-threonine were the most potent stimuli at M while L-proline and L-aspartate were the least potent. Four groups of amino acids were identified according to their thresholds of detection and three groups – according to the similarity of their ɣ-factors. The estimated threshold of detection for O.mossambicus mixture was higher than that for the filtrate. On the contrary, the threshold of detection for the mixture of Nile tilapia was lower than that for the filtrate The concentration of L-arginine in the urine was positively correlated with fish dominance index. Both L-arginine and L-glutamic acid concentrations had much greater variability in dominant males (DI˃0.5) than in subordinate males (DI˂0.5). The urinary concentrations of L-phenylalanine had similar variability in dominant and subordinate groups. The Mozambique tilapia has olfactory sensitivity to all twenty amino acids tested. The fish showed more acute sensitivity to conspecific urine filtrate than to the heterospecific. Olfactory potency of O.mossambicus filtrate can be largely but not fully explained by the presence of L-arginine, L-glutamic acid and L-phenylalanine. Larginine and L-glutamic acid may indicate the dominance status of the fish and, possibly, individual identity.

Introdução à inteligência artificial com recurso à programação visual

Relatório da Prática de Ensino Supervisionada, Mestrado em Ensino da Matemática, Universidade de Lisboa, Instituto de Educação, 2014

Impacto da iluminação natural e artificial na disponibilidade de macro-invertebrados bentónicos para as aves limícolas

Tese de mestrado em Ecologia Marinha, apresentada à Universidade de Lisboa, através da Faculdade de Ciências, 2015

An artificial neural network approach for short-term wind power forecasting in Portugal

This paper presents an artificial neural network approach for short-term wind power forecasting in Portugal. The increased integration of wind power into the electric grid, as nowadays occurs in Portugal, poses new challenges due to its intermittency and volatility. Hence, good forecasting tools play a key role in tackling these challenges. The accuracy of the wind power forecasting attained with the proposed approach is evaluated against persistence and ARIMA approaches, reporting the numerical results from a real-world case study.