Sistema baseado em software livre para reconhecimento de fala em nuvem em português brasileiro com alta disponibilidade

Este trabalho visa propor uma solução contendo um sistema de reconhecimento de fala automático em nuvem. Dessa forma, não há necessidade de um reconhecedor sendo executado na própria máquina cliente, pois o mesmo estará disponível através da Internet. Além do reconhecimento automático de voz em nuvem, outra vertente deste trabalho é alta disponibilidade. A importância desse tópico se d´a porque o ambiente servidor onde se planeja executar o reconhecimento em nuvem não pode ficar indisponível ao usuário. Dos vários aspectos que requerem robustez, tal como a própria conexão de Internet, o escopo desse trabalho foi definido como os softwares livres que permitem a empresas aumentarem a disponibilidade de seus serviços. Dentre os resultados alcançados e para as condições simuladas, mostrou-se que o reconhecedor de voz em nuvem desenvolvido pelo grupo atingiu um desempenho próximo ao do Google.

A system for environmental monitoring of hydroelectric reservoirs in Brazil

Environmental monitoring of aquatic systems is an important tool to support policy makers and environmental managers' decisions. Long-term, continuous collection of environmental data is fundamental to the understanding of an aquatic system. This paper aims to present the integrated system for environmental monitoring (SIMA), a long-term temporal series system with a web-based archive for limnological and meteorological data. The following environmental parameters are measured by SIMA: chlorophyll-a (µgL-1), water surface temperature (ºC), water column temperature by a thermistor string (ºC), turbidity (NTU), pH, dissolved oxygen concentration (mg L-1), electric conductivity (µS cm-1), wind speed (ms-1) and direction (º), relative humidity (%), shortwave radiation (Wm-2) and barometric pressure (hPa). The data were collected in a preprogrammed time interval (1 hour) and were transmitted by satellite in quasi-real time for any user within 2500 km of the acquisition point. So far, 11 hydroelectric reservoirs are being monitored with the SIMA buoy. Basic statistics (mean and standard deviation) and an example of the temporal series of some parameters were displayed at a database with web access. However, sensor and satellite problems occurred due to the high data acquisition frequency. Sensors problems occurred due to the environmental characteristics of each aquatic system. Water quality sensors rapidly degrade in acidic waters, rendering the collected data invalid. Data is also rendered invalid when sensors become infested with periphyton. Problems occur with the satellites' reception of system data when satellites pass over the buoy antenna. However, the data transfer at some inland locations was not completed due to the satellite constellation position. Nevertheless, the integrated system of water quality and meteorological parameters is an important tool in understanding the aquatic system dynamic. It can also be used to create hydrodynamics models of the aquatic system to allow for the study of meteorological implications to the water body.

NodePM: A Remote Monitoring Alert System for Energy Consumption Using Probabilistic Techniques

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Effect of the Layering Technique on Bond Strength and Cohesive Resistance of a Porcelain-Zirconia System

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

An Ultracapacitor-Based No-Break System for Microcomputers

This work aims at presenting a no-break system for microcomputers using ultracapacitors in replacement of the conventional chemical batteries. We analyzed the most relevant data about average power consumption of microcomputers, electrical and mechanical characteristics of ultracapacitors and operation of no-break power circuits, to propose a configuration capable of working properly with a microcomputer switching mode power supply. Our solution was a sixteen-component ultracapacitor bank, with a total capacitance of 350 F and voltage of 10.8 V, adequate to integrate a low-capacity no-break system, capable of feeding a load of 180 Wh, during 75 s. Our proposed no-break increases the reliability of microcomputers by reducing the probability of user data losses, in case of a power grid failure, offering, so, a high benefit-cost ratio. The replacement of the battery by ultracapacitors allows a quick no-break recharge and low maintenance costs, since these modern components have a lifetime longer than the batteries. Moreover, this solution reduces the environmental impact and eliminates the constant recharge of the energy storage device.

Deep learning architecture for gesture recognition

Pós-graduação em Engenharia Mecânica - FEG

Interface para classificação de dados por máquinas de vetores de suporte

In this project the Pattern Recognition Problem is approached with the Support Vector Machines (SVM) technique, a binary method of classification that provides the best solution separating the data in the better way with a hiperplan and an extension of the input space dimension, as a Machine Learning solution. The system aims to classify two classes of pixels chosen by the user in the interface in the interest selection phase and in the background selection phase, generating all the data to be used in the LibSVM library, a library that implements the SVM, illustrating the library operation in a casual way. The data provided by the interface is organized in three types, RGB (Red, Green and Blue color system), texture (calculated) or RGB + texture. At last the project showed successful results, where the classification of the image pixels was showed as been from one of the two classes, from the interest selection area or from the background selection area. The simplest user view of results classification is the RGB type of data arrange, because it’s the most concrete way of data acquisition

Avaliação da usabilidade de representações cartográficas em diferentes escalas para sistema de navegação e guia de rota em automóvel

Pós-graduação em Ciências Cartográficas - FCT

A method using artificial neural networks to morphologically assess mouse blastocyst quality

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Thermodynamic, Economic and Emissions Analysis of a Micro Gas Turbine Cogeneration System operating on Biofuels

Pós-graduação em Engenharia Mecânica - FEG

Preliminary diagnosis of ophtalmological diseases through machine learning techniques

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Expert system to detect incipient fauts in rotating machines using fuzzy logic and virtual instrumentation

This paper refers to the design of an expert system that captures a waveform through the use of an accelerometer, processes the signal and converts it to the frequency domain using a Fast Fourier Transformer to then, using artificial intelligence techniques, specifically Fuzzy Reasoning, it determines if there is any failure present in the underlying mode of the equipment, such as imbalance, misalignment or bearing defects.

Machine vision and planning applied on assembby line of multiple products

This article describes the use of Artificial Intelligence (IA) techniques applied in cells of a manufacturing system. Machine Vision was used to identify pieces and their positions of two different products to be assembled in the same productive line. This information is given as input for an IA planner embedded in the manufacturing system. Therefore, initial and final states are sent automatically to the planner capable to generate assembly plans for a robotic cell, in real time.

ARBOT: augmented reality system for teaching logic algorithmic

This article purposes the ARBot, a system that has as main objective the presentation of concepts of logic for students of elementary and secondary education. The system was developed using the technology known as Augmented Reality (AR), which allows complement the actual environment where the user is, by adding virtual objects. In this scenario the RA created from a virtual game interface is used, through which cognitive challenges are presented. To solve these challenges, users must set up three-dimensional virtual characters using visual language. As a result it follows that, in a playful way, concepts of algorithms and programming are assimilated by users. In addition, the system enables two users to interact in a cooperative game mode. In cooperative mode, the system focuses on collaborative learning, since it allows users to jointly solve the cognitive challenge presented by the system.

Abordagem icônica para modelagem e simulação de ambientes de computação em nuvem ?

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)