Thiago Meirelles Ventura

Universidade Federal de Mato Grosso (UFMT) | UFMT · Departamento de Ciência da Computação

Artificial Neural Networks (ANN) have been widely used to model several types of data. The precision of ANN models is dependent upon their configuration, i.e., input parameters, training algorithm and architecture configurations. The problem lies in the amount of possible combinations of these parameters which results in countless unique ANNs. One...

Hidden Markov Model (HMM) Mel Frequency Cepstral Coefficients (MFCCs) Robust frame selection a b s t r a c t A major challenge in the automated acoustic recognition of bird species is the audio segmentation, which aims to select portions of audio that contain meaningful sound events and eliminates segments that contain predominantly background nois...

Uma abordagem computacional para preenchimento de falhas em dados micro meteorológicos A computational approach for gap filling in micrometeorological data RESUMO Estações micro meteorológicas utilizam equipamentos para captar dados sobre fenômenos climatológicos. Essa captação está sujeita a falhas e influências externas que ocasiona ausência de d...

Meteorological elements can affect the environment and cultures differently and may alter the natural development process contributing significantly to climate change. Meteorological variables of the Brazilian Pantanal were studied and used to determine evapotranspiration with fewer variables. It was found that artificial intelligence can substanti...

Many stages of information systems projects developed in public institutions are defined by laws and regulations, which reduces the management flexibility. In the particular case of Business Process Management (BPM) projects, it has even more influence since the business processes are also constrained by legislation. In this context, it is importan...

The Brazilian savanna, locally known as Cerrado, native vegetation has been replaced by an agro-pastoral land cover over the last few decades, which has affected its hydrological cycle and the availability of its water resources. Reference evapotranspiration (ET o) estimates are an important tool for water resources managements because they estimat...

Automated acoustic recognition of birds is considered an important technology in support of biodiversity monitoring and biodiversity conservation activities. These activities require processing large amounts of soundscape recordings. Typically, recordings are transformed to a number of acoustic features, and a machine learning method is used to bui...

Os sensores instalados em estações meteorológicas podem gerar uma grande quantidade de dados todos os dias. Esses dados, eventualmente, precisam ser processados antes de serem analisados. Nesse processo, a quantidade de dados pode dificultar a sua manipulação, controle e interpretação. Inclusive para técnicas computacionais, a quantidade de dados s...

Screams and moans are a specific way of communicating and carry a feeling behind the sound player. Machine Learning tecniques were used to detect feelings in various sounds produced by people. It was developed a model using Deep Learning to do this kind of classification achieving a precision of 93,5%.

This paper proposes the development of a convolutional neural network for the morphological classification of galaxies through optical images, classifying them into six distinct classes based on the Hubble Tuning Fork model. In order to automate the mass identification and separation of the huge volume of data generated in recent astronomical obser...

Despite the significant developments in project management methodologies and tools, achieving success is still a challenge for managers. In this scenario, the experimentation of a model that incorporates activities to characterize and manage success throughout a government information systems project was initiated. It includes activities to identif...

This paper brings the development of new alternatives for the Burndown, a graphic tool used to monitor and follow-up a project. In its traditional form this graphic estimates linear wane of the development in each cycle of a project. The problem comes up when the team does not have a development pace as linear as the graphic draws. To solve this pr...

Este trabalho apresenta uma análise acerca de diferentes aspectos da aplicação de testes automatizados em comparação aos testes manuais. Como estudo de caso, foram observadas e comentadas as experiências no desenvolvimento de um sistema para a área da saúde, desenvolvido por uma equipe utilizando metodologia ágil. Neste estudo é apresentado a aplic...

Com o propósito de entender como como o tratamento de dados meteorológicos é efetuado no Brasil, este trabalho apresenta um estudo mapeando a forma de trabalho dos pesquisadores da área de Ciência Ambiental. Para alcançar esse objetivo, foi elaborada uma pesquisa durante 2 meses, entre as datas de 20 de outubro a 19 de dezembro de 2016. O questioná...

This paper presents Mannga (Multiple variables with Artificial Neural Network and Genetic Algorithm), a method designed for gap filling meteorological data. The main approach is to estimate the missing data based on values of other meteorological variables measured at the same time in the same local, since the meteorological variables are strongly...

Este trabalho apresenta uma análise acerca de diferentes aspectos da aplicação de testes automatizados em comparação aos testes manuais. Como estudo de caso, foram observadas e comentadas as experiências no desenvolvimento de um sistema para a área da saúde, desenvolvido por uma equipe utilizando metodologia ágil. Neste estudo é apresentado a aplic...

This paper brings the development of new alternatives for the Burndown, a graphic tool used to monitor and follow-up a project. In its traditional form this graphic estimates linear wane of the development in each cycle of a project. The problem comes up when the team does not have a development pace as linear as the graphic draws. To solve this pr...

Conhecer o perfil de profissionais de tecnologia no nosso país é uma necessidade e também um desafio. Muitas pesquisas são realizadas sobre o ambiente acadêmico, mas pouco se sabe sobre estes estudantes após sua formação. De forma semelhante, as pesquisas sobre mulheres na computação no Brasil são em sua maioria realizadas com alunas de ensino supe...

A evasão de estudantes no nível superior é um sério problema. Neste trabalho, é apresentado uma metodologia baseada em banco de dados orientado a grafos com o intuito de entender e identificar estudantes com potencial de desistência. Foi utilizado exclusivamente o histórico escolar dos alunos, algo facilmente obtido para a aplicação da metodologia...

Os dados meteorológicos são de grande importância para os estudos científicos, pois auxiliam na tomada de decisões em diferentes áreas do conhecimento. As estações automáticas realizam o trabalho de captar esses dados, porém, problemas podem ocorrer nos instrumentos causando falhas nas séries de dados e inutilizando um período ou até mesmo toda a s...

O avanço tecnológico dos dispositivos móveis promoveram o crescimento de aplicativos que trabalham com dados geoespaciais, exibindo dados de interesse do usuário baseados na sua posição geográfica. Em geral, esses dados são solicitados por meio de conexões de internet móvel, assim o processamento das consultas geoespaciais ocorrem em um computador...

Rainfall is the key element in regional water balance, and has direct influence over economic activity. Quantifying rainfall at spatial and temporal scales in regions where meteorological stations are scarce is important for agriculture, natural resource management and land-atmosphere interactions science. Thus, we evaluated neural network performa...

Rainfall is the key element in regional water balance, and has direct influence over economic activity. Quantifying rainfall at spatial and temporal scales in regions where meteorological stations are scarce is important for agriculture, natural resource management and land-atmosphere interactions science. Thus, we evaluated neural network performa...

Com a utilização de sensores obtemos dados meteorológicos, que são estudados para interpretar fenômenos climáticos. Estes dados vêm em séries que podem aparecer dados fora do comum, chamados de outliers. Neste trabalho comparamos o desempenho de três métodos de detecção de outliers para verificar a aplicabilidade nesse tipo de dados, são eles: Box-...

A meteorological phenomenon is a weather event that can be explained by principles of meteorology. Meteorological data are used to study meteorological phenomena. This study is important mainly for comprehension of severe weather phenomena that are conditions hazardous to human life. Also, this comprehension about weather can help to improve the pe...

Climate modeling uses weather data to generate their results. These variables are normally collected simultaneously, and likewise are used in modeling. However, we believe that some variables can generate better results in modeling when used in composition with their previous measures, not only with the simultaneous measurement to the other variabl...

Studies involving meteorological data are carried out by multidisciplinary teams and often with large numbers of people. These characteristics mean that the use of more complete computational tools is required, rather than just spreadsheets, for proper management of data used. This management involves the secure sharing of data, because at certain...

The modeling with meteorological data benefits several fields, such as agriculture, environmental conservation and civil defense. For this modeling can be performed, the meteorological data must be complete, i.e., without the presence of gaps. Therefore, two actions can be made: i) delete the failed records, reducing the data set and losing the con...

The knowledge of precipitation spatiotemporal distribution allows a discussion on climate vulnerabilities and their consequences and it is important in order to control the renewable resources that affect the economy, and the ecological and agricultural development. Comparing rainfall time series in different locations enables the identification of...

The project Tropical Rainfall Measuring Mission (TRMM) is a major source of rainfall data that provides data since 1998, in temporal resolution of three hours and spatial resolution of 0.25º. A large volume of data is generated by this product. These data are available in binary format: Hierarchical Data Format (HDF) or Network Common Data Form (Ne...

A major challenge in the automated acoustic recognition of bird species is the audio segmentation, which aims to select portions of audio that contain meaningful sound events and eliminates segments that contain predominantly background noise or sound events of other origin. Here we report on the development of an audio parameterization method with...

The goals of this study were to compare a growth model developed to the real growth of the measured fruits in the field using two values of initial relative growth rate, one established by literature and other estimated for each fruit, and to estimate inferior and superior basal temperature for fruits of 'Alpha' mango using the technique of artific...

fruto e, estimar a temperatura base-inferior e superior para frutos de mangueira 'Alfa' pela técnica de inteligência artificial, denominada de algoritmo genético. Para realizar a estimativa de crescimento, o modelo utilizado considerou os valores da taxa inicial de crescimento relativo dos frutos, massa seca (atual e máxima) e graus-dia. Neste trab...

Rainfall is the key element in regional water balance, and has direct influence over economic activity. There is increasing interest of climatic and meteorological data in large spatial and temporal scale. Likewise, computational methods and techniques for climatic and meteorological estimates in large areas with small dataset are growing. Thus, we...

Researches involving the long-wave balance have intensified in order to understand the environmental performance of micrometeorological variables. This study tried to determine the parameters of Brunt’s equation for the northern Pantanal of Mato Grosso, using “genetic algorithm”. The results show that the values estimated by the model significantly...

Research involving the long wave balance have been intensified in order to know the environmental performance of micrometeorological variables. In this study we sought to implement an algorithm in the field of artificial intelligence to determine the parameters of the equation brunt of a particular location. To test the algorithm, it was used to de...