Engenharia Elétrica

URI Permanente desta comunidade

http://repositorio.ufes.br/handle/10/17617
Programa de Pós-Graduação em Engenharia Elétrica

Centro: CT
Telefone: (27) 4009 2663
URL do programa: https://engenhariaeletrica.ufes.br/pt-br/pos-graduacao/PPGEE

Navegar

Navegando Engenharia Elétrica por Autor "Almeida, Ailson Rosetti de"

Agora exibindo 1 - 3 de 3
  • Nenhuma Miniatura disponível
    Item
    Estudo do sinal eletroencefalográfico (EEG) aplicado a interfaces cérebro computador com uma abordagem de reconhecimento de padrões
    (Universidade Federal do Espírito Santo, 2005-09-06) Azevedo, Anderson Prado; Almeida, Ailson Rosetti de; Salles, Evandro Ottoni Teatini; Bastos Filho, Teodiano Freire; Andreão, Rodrigo Varejão
    The conjunction of signal processing, pattern recognition and brain electrical signal acquisition made possible a new communication modality, until now a subject for science fiction movies: the Brain-Computer Interface (BCI). This complex system can acquire and process the brain signals in order to obtain information to be used as a control signal. This innovation can benefit people who have neuromuscular disorders, which cause damages on the volunteer movement. These people would communicate, or even move, using a BCI to control electronic devices. Looking ahead, these systems can be used in other applications, mainly for multimedia purposes. The purpose of this work is study the EEG characteristics, the signal processing and pattern recognition techniques in order to use in a Brain Computer Interface (BCI) For this, will be used a international data base, in order to compare our results with results of other international groups. In this context, this work describes the human brain and the EEG characteristics relevant to BCI understanding. Moreover, it presents the implementation of a pattern recognition system, which is able to classify the motor imagination laterality with accuracy over 85%.
  • Nenhuma Miniatura disponível
    Item
    Modelo de Seleção de Carteiras Baseado em Erros de Predição
    (Universidade Federal do Espírito Santo, 2008-12-18) Freitas, Fábio Daros de; Souza, Alberto Ferreira de; Almeida, Ailson Rosetti de; Salles, Evandro Ottoni Teatini; Zandonade, Eliana; França, Felipe Maia Galvão
    This work presents a new prediction errors-based portfoliooptimization model that cap-tures short-term investment opportunities. We used autoregressive moving references neuralnetwork predictors to predict the stock’s returns and derived a risk measure based on thepredictor’s errors of prediction that maintains the same statistical foundation of the mean-variance model. The efficient diversification effects hold by selecting predictors with lowand complimentary error profiles. A large set of experimentswith real data from the Brazil-ian stock market was employed to evaluate our portfolio optimization model, which includedthe examination of the Normality of the errors of prediction. Our main results showed that itis possible to obtain Normal prediction errors with non-Normal series of stock returns, andthat the prediction errors-based portfolio optimization model better captured the short termopportunities, outperforming the mean-variance model andbeating the market index.
  • Nenhuma Miniatura disponível
    Item
    Sistema de visão para robôs móveis: uma aplicação ao reconhecimento de referências geométricas
    (Universidade Federal do Espírito Santo, 1999-02-26) Freitas, Roger Alex de Castro; Sarcinelli Filho, Mário; Bastos Filho, Teodiano Freire; Almeida, Ailson Rosetti de; Rillo, Márcio
    The availability of sensorial data is an important issue for the navigation systemof autonomous mobile robots. The robot needs information about its surroundingenvironment in order to make a decision on what to do when it faces an obstacle. Insome cases, it not only does need to detect the presence of the obstacle but also torecognize it. This way, it is necessary that the onboard sensing system be much morespecialized. For an agent-based controlled autonomous mobile robot, a sensing systemthat combines ultrasonic sensors and artificial vision is here addressed. It makesavailable information about the type of obstacle detected in the trajectory of the robot, aswell as the distance from the detected object to the robot. This external sensing systemis also able to avoid the generation of redundant and unnecessary information, besidesnot demanding too much computational effort to process the acquired images onboardthe robot