Francisco Fambrini

In this paper, the authors describe the design, development and implementation of a deep-learning based system mounted on a terrestrial vehicle roof-top. The main objective is to capture images of overheat elements from the distribution powergrid network during the travel. Initially the vehicle was equipped with nine cameras to cover inspection in both side of the road and also covers the front view. This solution results in the capability to inspect hundreds of miles of power distribution lines without the need to stop the vehicle and without the need for a human operator. In the near future autonomous vehicles could be equipped with such a system to perform a full automatic inspection.

Matriz de Microeletrodos (microelectode array, MEA) é um dispositivo usado para cultura de neurônios in-vitro e registro de sinais eletrofisiológicos. A análise desses sinais é útil para o estudo da dinâmica de redes neuronais, teste de drogas farmacológicas, entre outras aplicações.  Os sinais elétricos capturados pela MEA são de baixa amplitude e requer sistemas de amplificação especiais. Neste artigo, é descrito um sistema de amplificação para MEA, com o uso do fenômeno de Ressonância Estocástica (RE), que faz uso benéfico do ruído, para detectar e amplificar sinais de microeletrodos de pequena amplitude. Um protótipo de um canal desse sistema foi simulado e testado com sucesso. 

A segmentation and recognition system for thermographic images of electric power distribution network using Artificial Intelligence is proposed in this article. The infrared thermography is usually used to proceed inspections in electrical power distribution lines, assisted by a human operator, which is usually responsible for operating all the equipment, selecting the hottest spots in the image (corresponding to the places needing maintenance), making reports and calling the technical team, which will do the repairs. The proposed automatic diagnosis system aims to replace the manual inspection operation using image processing algorithms. A method of segmentation for thermal images known as JSEG is implemented and tested and a Convolution Neural Network is responsible to recognize the segmented elements. The results show the feasibility of the algorithm, and the monitoring system.

O objetivo deste estudo é estabelecer uma compreensão a respeito do lugar da mulher na produção do conhecimento científico, a partir do conceito de organizador sociocultural cunhado por René Kaës. Trata-se de um estudo teórico de psicanálise aplicada ao contexto grupal (grupanalítico). Articula-se a definição do mito de Adão e Eva aos conceitos de organizadores psíquicos e socioculturais. Considera-se que no decorrer dos séculos, em diferentes períodos, o imaginário coletivo foi impregnado por mitos, e a estruturação dos vínculos foi colorida por crenças advindas. Atualmente, herda-se um produto desse processo de “ruminação” do mito de Adão e Eva. A elaboração social e cultural dessa representação mítica produz modelos de grupalidade decorrentes. Este mito enquanto expressão de organizadores socioculturais grupais está implicado no processo de desumanização das mulheres. Foi tomado para explicar a violência contra as mulheres, cerceamento e/ou exclusão de sua participação em diferentes âmbitos da sociedade, notadamente, no contexto acadêmico. Entende-se que a representação de Eva esteja mais impregnada pelo pecado, maligno, do que pela curiosidade, virtude, no que se refere a busca do conhecimento. Faz-se necessário desenvolver estratégias de enfrentamento de possíveis desigualdades de acesso a educação, a formação acadêmica, a cargos de gestão baseadas em sexismo.

The exponential increase in global data traffic has imposed numerous challenges for telecommunication systems. There is a trade-off between the interest of telecom operators of increasing net revenue and of customers, of increasing the rate of data transmission. Thus, several solutions have been discussed in the scope of optical communications. One of the proposals studied is the more intense application of digital signal processing. In this work the use of OFDM (Orthogonal Frequency Division Multiplexing) modulation was evaluated in the new generation optical networks. As proof of concept, the performance of optical networks in different configurations was analyzed using OptiSystem Software®. Some advantages and disadvantages of the use of OFDM modulation for the next generation networks were evidenced. It was concluded that OFDM modulation is a viable alternative for use in new generation networks.

In this paper, the authors discuss the results of the IA based on deep learning to improve the productivity of preventive thermographic inspections of the electrical network when compared to manual methods of analysis. The goal of this process is to use computer to capture and recognize images of hot spots from the distribution powergrid network during car’s inspection deslocation. In order to that, a special vehicle was assembled. Initially the vehicle was equipped with eight cameras to proceed inspection in both side of the road and covers the front view as well. This solution results in the capability to inspect hundreds of miles of power distribution lines without the need to stop the vehicle and without the need for a human operator.

This paper presents a Micro-Electrode Array (MEA) recording system with novel concept of a multiplexer coupled prior to the amplifier and filtering stages. It is described all the recording system, since the pre-amplifier, analog channel multiplexing, amplifier and filter, and AD conversion. For the AD conversion, it was used a commercial module called BeagleBoneBlack, which is an open source board, based on a 32-bit microprocessor, making it much easier to search for neuronal signals from the in-vitro culture on MEA. As result, it is presented the first one second recording data at 1 kHz frequency of Wistar rat embryo hippocampal neuron culture. One importance of such an in-vitro culture recording in human factor is in pharmacological drug tests, before its approval for medicinal use.

This PhD thesis aims at the study and practical implementation of a complete system capable of recording electrical signals from a Microelectrode Array. This multi-electrode planar matrix known as MEA (MicroElectrode Array), is built with the same technology as nanoscale integrated circuits, and allows a biological culture of neural cells to be performed at its center. Through studies on MEAs, we can better understand the pattern of spikes and bursts generated by neurons on in vitro cultures. The electrical signals captured and recorded from microelectrodes have an amplitude of the order of microvolts (μV) and need to be amplified by special circuits, with filters capable of selecting the frequency band of interest. However, often the electrical levels of the signals captured in MEAs are so small that they cannot be amplified by conventional techniques, as they are of the same order as the random noise level produced by the amplifier circuits. Some electrical signals are impossible ...

A segmentation and recognition system for thermographic images of electric power distribution network using Artificial Intelligence is proposed in this article. The infrared thermography is usually used to proceed inspections in electrical power distribution lines, assisted by a human operator, which is usually responsible for operating all the equipment, selecting the hottest spots in the image (corresponding to the places needing maintenance), making reports and calling the technical team, which will do the repairs. The proposed automatic diagnosis system aims to replace the manual inspection operation using image processing algorithms. A method of segmentation for thermal images known as JSEG is implemented and tested and a Convolution Neural Network is responsible to recognize the segmented elements. The results show the feasibility of the algorithm, and the monitoring system.

The exponential increase in global data traffic has imposed numerous challenges for telecommunication systems. There is a trade-off between the interest of telecom operators of increasing net revenue and of customers, of increasing the rate of data transmission. Thus, several solutions have been discussed in the scope of optical communications. One of the proposals studied is the more intense application of digital signal processing. In this work the use of OFDM (Orthogonal Frequency Division Multiplexing) modulation was evaluated in the new generation optical networks. As proof of concept, the performance of optical networks in different configurations was analyzed using OptiSystem Software®. Some advantages and disadvantages of the use of OFDM modulation for the next generation networks were evidenced. It was concluded that OFDM modulation is a viable alternative for use in new generation networks.

The recognition and identification of the fauna and flora of an area, in particular a conservation unit, is of fundamental importance to protect and conserve local biodiversity. Agroforestry Systems (AFSs) are forms of use of land or management, in which tree species (fruit and timber) are combined with agricultural crops. When compared to conventional agriculture, AFSs such as advanced systems for supplying green fertilizers, controlling weeds and mainly, recovering and maintaining soil fertility, since it maintains a great variety in the fauna, simultaneously or in temporal sequence promoting the economic and ecological benefits. A diversity index is a mathematical measure of species diversity in a community. Measuring diversity is important in understanding the structure of the community. Diversity indexes are important because they provide more information about a community than just species richness. Diversity indexes also consider the relative abundance of different species an...

There are some benefits in using periocular biometric traits for individual identification. This work describes the use of convolutional neural network Neocognitron, in this novel application, in individual recognition using periocular region images. Besides, it is used the competitive learning using the extreme points of lines detected in the preprocessing of the input images as winner positions. It was used Carnegie Mellon University - Pose, Illumination, and Expression Database (CMU-PIE), with 41,368 images of 68 persons. From these images, 57 \(\times \) 57 periocular images were obtained as training and test samples. The experiments indicate results in the Kappa index of 0.89, for periocular images, and 0.91 for complete face images.

The identification of crop areas marked by biotic and abiotic factors is a challenge in precision agriculture (PA). Remote sensing and supervised segmentation of hyperspectral images (HIs) have become a fast and precise solution of PA for the identification of problems in crops. However, wellknown problems for knowledge extraction in HIs are related to data volumes and capacity for modeling each phenomenal due to the so-called curse of dimensionality. Some techniques for dealing with dimensionality, such as genetic algorithms (GAs), are promising, but they cannot assure a compromise between the segmentation effectiveness and reduction of dimensionality. In this paper, a multi-objective method based on Nondominated Sorting Genetic Algorithm 2 and Gaussian Maximum Likelihood Classifier is proposed for supervised segmentation of HIs dealing with the problem of dimensionality. Experiments with three datasets and cross-validation showed that the proposed method reduced the average number...

Como os vírus evoluíram? Eles são uma forma simplificada de algo que existia há muito tempo ou um ponto culminante final de elementos genéticos menores unidos? A história evolutiva dos vírus representa um tópico fascinante, embora obscuro, para virologistas e biólogos celulares. Devido à grande diversidade entre os vírus, os biólogos têm se esforçado para classificar essas entidades e como relacioná-las com a árvore da vida convencional. Eles podem representar elementos genéticos que ganharam a capacidade de se mover entre as células. Eles podem representar organismos de vida livre que se tornaram parasitas. Eles podem ser os precursores da vida como a conhecemos. Noções básicas de vírus Sabemos que os vírus são bastante diversos. Ao contrário de todas as outras entidades biológicas, alguns vírus, como o poliovírus, têm genomas de RNA e outros, como o herpesvírus, têm genomas de DNA. Além disso, alguns vírus (como o vírus influenza) têm genomas de fita simples, enquanto outros (como varíola) têm genomas de fita dupla. Suas estruturas e estratégias de replicação são igualmente diversas. Os vírus, no entanto, compartilham algumas características: primeiro, geralmente são muito pequenos, com um diâmetro inferior a 200 nanômetros (nm). Segundo, eles podem se replicar apenas dentro de uma célula hospedeira. Terceiro, nenhum vírus conhecido contém ribossomos, um componente necessário do mecanismo de tradução de uma célula para a produção de proteínas. O diagrama esquemático na figura 1 mostra dois grupos de organismos: organismos que codificam o capsídeo e organismos que codificam o ribossomo. Os dois grupos são mostrados em uma esfera dividida ao meio, e as linhas que irradiam de onde as duas metades se encontram representam táxons diferentes dentro dos dois grupos. A metade superior da esfera representa os organismos que codificam o capsídeo, que são vírus, e inclui vírus de Archaea, vírus de bactérias e vírus de Eukarya. A metade inferior da esfera representa organismos que codificam ribossomos e inclui bactérias, arquéias e eucariotos.

A análise de imagens é uma ferramenta que é capaz de fornecer informações extraídas das folhas das culturas, que pode contribuir no diagnóstica da nutrição. O objetivo deste trabalho foi identificar níveis de nitrogênio (N) em plantas de milho, em diferentes épocas de desenvolvimento da cultura, por meio de análise de imagens
digitais das folhas. O experimento foi realizado na fazenda Morro Frio, no município de Bragança Paulista - SP. O cultivo foi feito na safra de verão (safra 2017/2018), com o híbrido Pioneer P30F53; foi adotado o sistema de plantio direto. O delineamento experimental foi em blocos casualizados, sendo os tratamentos compostos por cinco doses de N em cobertura (0, 90, 120, 150 e 180 kg/ha), em 5 blocos experimentais.
Cada parcela experimental foi composta de 8 linhas de milho com 8 metros de
comprimento, totalizando 51,2 m² por parcela. A adubação de base foi dividida igualmente para todos os tratamentos (450 kg ha-1 da fórmula 08 – 24 – 12 +micronutrientes) utilizando o manejo padrão da fazenda, e a aplicação dos tratamentos foi feita manualmente, na linha do milho. O estudo da análise de imagens foi feito nas folhas indicativas no estádio V7 (sétima folha totalmente desenvolvida) e R1 (folha oposta abaixo da primeira espiga). Em cada época estabelecida para o
estudo foram colhidas 6 folhas indicativas de cada parcela experimental, totalizando 24 folhas para cada tratamento. As folhas foram digitalizadas em 600 DPI, identificadas separadamente para cada tratamento, e armazenadas no computador em formato JPEG. A etapa inicial da análise foi a segmentação da amostra, com o auxílio do software lightscreen 3.1. Foram feitos cortes nas imagens de 800x800
pixels, separando as folhas individualmente de cada dose de N, para posterior obtenção dos histogramas nas bandas da cor vermelho (R), verde (G) e azul (B), e calculados os índices excesso de verde, vermelho normalizado, verde normalizado e razão verde-vermelho. Para avaliação dos resultados foi composta a matriz de confusão, onde foram obtidas as porcentagens de acerto global e índice Kappa (medida de confiabilidade da análise), para cada característica referente aos índices
espectrais e a combinação entre eles. Os métodos e técnicas utilizado para extração de características baseados em índices espectrais na faixa do visível, com os classificadores estatísticos estudados, não identificam as doses de nitrogênio em folhas indicativas de milho nos estádios V7 e R1.

The recognition and identification of the fauna and
flora of an area, in particular a conservation unit, is of fundamental
importance to protect and conserve local biodiversity. Agroforestry
Systems (AFSs) are forms of use of land or management, in which
tree species (fruit and timber) are combined with agricultural crops.
When compared to conventional agriculture, AFSs such as advanced
systems for supplying green fertilizers, controlling weeds and mainly,
recovering and maintaining soil fertility, since it maintains a great
variety in the fauna, simultaneously or in temporal sequence
promoting the economic and ecological benefits. A diversity index is
a mathematical measure of species diversity in a community.
Measuring diversity is important in understanding the structure of
the community. Diversity indexes are important because they provide
more information about a community than just species richness.
Diversity indexes also consider the relative abundance of different
species and provide information on the rarity of the species, as the
number of different species present as well. The biodiversity of
edaphic fauna can be measured using statistical parameters derived
from the idea of Entropy. In the present work the following
parameters were used: the Pielou index, Pielou Equability, Pielou
Equitability and Shannon-Wiener index. Five areas were selected:
one for Agroforestry (AFS), one Pasture Area and one Preserved
Forest area located at Private Reserve of Natural Heritage (RPPN)
Serrinha Farmer (Serrinha Neighborhood - Bragança Paulista city,
São Paulo State, Brazil).The fourth place was an area formerly used
as a vegetable garden in a basic education school in the same city,
and the fifth was an area for eucalyptus (Eucalyptus) in the rural zone
of city of Pedra Bela, São Paulo.The area of the greatest biodiversity
was the Eucalyptus Plantation, followed by the area of Preserved
Forest and Agroforestry. The Pasture area was in fourth place,
presenting the largest number of individuals, however, divided into a
few groups. The area of lower biodiversity was the area represented
by the vegetable garden.