Roberto Luiz Souza Monteiro

A Model for Improving the Learning Curves of Artificial Neural Networks

In this article, the performance of a hybrid artificial neural network (i.e. scale-free and small-world) was analyzed and its learning curve compared to three other topologies: random, scale-free and small-world, as well as to the chemotaxis neural network of the nematode Caenorhabditis Elegans. One hundred equivalent networks (same number of vertices and average degree) for each topology were generated and each was trained for one thousand epochs. After comparing the mean learning curves of each network topology with the C. elegans neural network, we found that the networks that exhibited preferential attachment exhibited the best learning curves.

Analysis of a Sorter Cascade Applied to Control a Wheelchair

The precise eye state detection is a fundamental stage for various activities that require human-machine interaction (HMI). This chapter presents an analysis of the implementation of a system for navigating a wheelchair with automation (CRA), based on facial expressions, especially eyes closed using a Haar cascade classifier (HCC). Aimed at people with locomotor disability of the upper and lower limbs, the state detection was based on two steps: the capture of the image, which concentrates on the detection actions and image optimization; actions of the chair, which interprets the data capture and sends the action to the chair. The results showed that the model has excellent accuracy in identification with robust performance in recognizing eyes closed, bypassing well occlusion issues and lighting with about 98% accuracy. The application of the model in the simulations opens the implementation and marriage opportunity with the chair sensor universe aiming a safe and efficient navigation to the user.

Study of the Impact of the Topology of Artificial Neural Networks for the Prediction of Meteorological Data

In this chapter, we present an analysis of the capacity of six topologies of neural networks—multilayer perceptron (MLP), complete (CP), random (RD), scale-free (SF), small world (SW), and hybrid (HY)—to perform next-step predictions of temperature and solar radiation. For this purpose, 100 networks of each complex topology, including an MLP network and a complete network, were created, and each network contained twenty-six neurons (five entries, twenty processing units, and one output). The networks were trained for 2000 epochs and used for the next-step prediction of the selected climate variables. The MLP and Complete networks were trained 100 times, and the averages were taken for comparison. The parameters of comparison were the root mean square error (RMSE), the mean time to learn (ETL), and the mean time to predict the next step after training (ETP), using 1000 h of input data obtained from INMET (National Institute of Meteorology), a station on the coast of Bahia. The set of 1000 h of data was divided into two parts: 700 h for network training and 300 h to verify the effectiveness of learning.

Prevalência de amputações de membros superiores e inferiores no estado de Alagoas atendidos pelo SUS entre 2008 e 2015

A amputacao e um recurso terapeutico utilizado para realizar a remocao de um membro, outro apendice ou saliencia do corpo, na ocorrencia de lesoes graves de nervos, arterias, partes moles e ossos. O objetivo desta pesquisa foi verificar a prevalencia de amputacoes de membros no estado de Alagoas. Tratou-se de um estudo de dados secundarios, com abordagem epidemiologica e observacional, no periodo de 2008 a 2015. As informacoes foram coletadas do banco de dados do SIHSUS. Foram registrados 361.585 procedimentos de amputacoes de membros no Brasil, com predominância nas regioes Sudeste, Nordeste e Sul, responsaveis por 88,13% desse total. Alagoas ocupou o 21o lugar em numero de amputacoes entre os estados brasileiros: seus procedimentos ocorreram em seis microrregioes, destas, 3 foram responsaveis por 95% dos casos. A prevalencia de amputacao em Alagoas foi de 19,05 amputacoes/100 mil habitantes. Tres tipos de procedimentos apresentam maior predominância: amputacao de membros inferiores, dedos, pe e tarso, o que representa 95% das amputacoes.

Social network analysis as a strategy for monitoring the dissemination of information between hospitals

This article explores the structure of connections between the hospitals that are members of a hospital management innovation and learning network. This study was based on the assumption that there are limitations to encourage the communication and diffusion of knowledge between health service organizations if they are not effectively connected through social networks. Social Network Analysis was used as a strategy for monitoring the dissemination of information between hospitals. Theoretical concepts of diffusion of knowledge allowed emphasizing the role of the phenomena and communication and learning processes as the driving forces for health service innovation. The results showed weak interactions between hospitals and a lack of cohesion within the network. Therefore, there is a need for policies to promote the flow of data and information, which requires network openness to foster the exchange of innovative processes. Interactions between these hospitals in horizontal and disseminated structures have yet to be stimulated, established, incorporated, and developed by individuals, institutions and health service organizations. Keywords : Knowledge diffusion. Innovation. Social network analysis.

Scientific Collaboration Networks of the “Energy and Environment INCT”

Os Institutos Nacionais de Ciencia e Tecnologia (INCT) objetivam dinamizar e agregar, atraves de articulacoes, os grupos referencias em areas estrategicas visando o desenvolvimento sustentavel do Brasil. Dentre as metas para a criacao dos INCT, pode-se destacar a necessidade de mobilizar e agregar de forma articulada os grupos de excelencia em areas de fronteira da ciencia e em areas estrategicas para o desenvolvimento sustentavel do pais. Neste sentido, este trabalho teve como objetivo avaliar o comportamento da rede de colaboracao do INCT de Energia e Ambiente (INCT EA) no periodo de 2009 a 2014. Para tanto, foram criados bancos de dados padronizados utilizando as publicacoes periodicas dos pesquisadores do INCT EA (periodicos indexados descritos nos relatorios de atividades anuais do INCT EA e curriculo lattes). Apos validacao das informacoes, foram gerados atributos especificos para construcao e avaliacao das redes formadas. As propriedades das redes geradas foram calculadas, analisadas e interpretadas. E observada a existencia do fenomeno small world na rede de colaboracao do INCT EA, assim como as distribuicoes de graus das redes de coautoria antes e depois da criacao do instituto sugerem a existencia de uma lei de potencia. Atraves dos resultados obtidos neste estudo foi possivel concluir que o INCT EA cumpre seu papel quanto as articulacoes geradas entre o grupo de pesquisadores. Grande parte dos principais pesquisadores/articuladores do INCT EA compoe o comite gestor do Instituto. Isto fortalece a rede de colaboracao e impulsiona a disseminacao do conhecimento para o desenvolvimento da Ciencia, Inovacao e Tecnologia no Brasil . DOI: 10.5935/1984-6835.20160088