Algoritmos genéticos e processamento paralelo aplicados à definição e treinamento de redes neurais perceptron de múltiplas camadas

ln this work, it was deveIoped a parallel cooperative genetic algorithm with different evolution behaviors to train and to define architectures for MuItiIayer Perceptron neural networks. MuItiIayer Perceptron neural networks are very powerful tools and had their use extended vastIy due to their abiIity of providing great resuIts to a broad range of appIications. The combination of genetic algorithms and parallel processing can be very powerful when applied to the Iearning process of the neural network, as well as to the definition of its architecture since this procedure can be very slow, usually requiring a lot of computational time. AIso, research work combining and appIying evolutionary computation into the design of neural networks is very useful since most of the Iearning algorithms deveIoped to train neural networks only adjust their synaptic weights, not considering the design of the networks architecture. Furthermore, the use of cooperation in the genetic algorithm allows the interaction of different populations, avoiding local minima and helping in the search of a promising solution, acceIerating the evolutionary process. Finally, individuaIs and evolution behavior can be exclusive on each copy of the genetic algorithm running in each task enhancing the diversity of populations

Contribuição para o estudo do embarque de uma rede neural artificial em field programmable gate array (FPGA)

This study shows the implementation and the embedding of an Artificial Neural Network (ANN) in hardware, or in a programmable device, as a field programmable gate array (FPGA). This work allowed the exploration of different implementations, described in VHDL, of multilayer perceptrons ANN. Due to the parallelism inherent to ANNs, there are disadvantages in software implementations due to the sequential nature of the Von Neumann architectures. As an alternative to this problem, there is a hardware implementation that allows to exploit all the parallelism implicit in this model. Currently, there is an increase in use of FPGAs as a platform to implement neural networks in hardware, exploiting the high processing power, low cost, ease of programming and ability to reconfigure the circuit, allowing the network to adapt to different applications. Given this context, the aim is to develop arrays of neural networks in hardware, a flexible architecture, in which it is possible to add or remove neurons, and mainly, modify the network topology, in order to enable a modular network of fixed-point arithmetic in a FPGA. Five synthesis of VHDL descriptions were produced: two for the neuron with one or two entrances, and three different architectures of ANN. The descriptions of the used architectures became very modular, easily allowing the increase or decrease of the number of neurons. As a result, some complete neural networks were implemented in FPGA, in fixed-point arithmetic, with a high-capacity parallel processing

Análise de escalabilidade de uma implementação paralela do simulated annealing acoplado

This paper analyzes the performance of a parallel implementation of Coupled Simulated Annealing (CSA) for the unconstrained optimization of continuous variables problems. Parallel processing is an efficient form of information processing with emphasis on exploration of simultaneous events in the execution of software. It arises primarily due to high computational performance demands, and the difficulty in increasing the speed of a single processing core. Despite multicore processors being easily found nowadays, several algorithms are not yet suitable for running on parallel architectures. The algorithm is characterized by a group of Simulated Annealing (SA) optimizers working together on refining the solution. Each SA optimizer runs on a single thread executed by different processors. In the analysis of parallel performance and scalability, these metrics were investigated: the execution time; the speedup of the algorithm with respect to increasing the number of processors; and the efficient use of processing elements with respect to the increasing size of the treated problem. Furthermore, the quality of the final solution was verified. For the study, this paper proposes a parallel version of CSA and its equivalent serial version. Both algorithms were analysed on 14 benchmark functions. For each of these functions, the CSA is evaluated using 2-24 optimizers. The results obtained are shown and discussed observing the analysis of the metrics. The conclusions of the paper characterize the CSA as a good parallel algorithm, both in the quality of the solutions and the parallel scalability and parallel efficiency

Projeto de Sistemas Integrados de Propósito Geral Baseados em Redes em Chip Expandindo as Funcionalidades dos Roteadores para Execução de Operações: A plataforma IPNoSys

It bet on the next generation of computers as architecture with multiple processors and/or multicore processors. In this sense there are challenges related to features interconnection, operating frequency, the area on chip, power dissipation, performance and programmability. The mechanism of interconnection and communication it was considered ideal for this type of architecture are the networks-on-chip, due its scalability, reusability and intrinsic parallelism. The networks-on-chip communication is accomplished by transmitting packets that carry data and instructions that represent requests and responses between the processing elements interconnected by the network. The transmission of packets is accomplished as in a pipeline between the routers in the network, from source to destination of the communication, even allowing simultaneous communications between pairs of different sources and destinations. From this fact, it is proposed to transform the entire infrastructure communication of network-on-chip, using the routing mechanisms, arbitration and storage, in a parallel processing system for high performance. In this proposal, the packages are formed by instructions and data that represent the applications, which are executed on routers as well as they are transmitted, using the pipeline and parallel communication transmissions. In contrast, traditional processors are not used, but only single cores that control the access to memory. An implementation of this idea is called IPNoSys (Integrated Processing NoC System), which has an own programming model and a routing algorithm that guarantees the execution of all instructions in the packets, preventing situations of deadlock, livelock and starvation. This architecture provides mechanisms for input and output, interruption and operating system support. As proof of concept was developed a programming environment and a simulator for this architecture in SystemC, which allows configuration of various parameters and to obtain several results to evaluate it

Projeto e implementação de uma plataforma MP-SoC usando SystemC

This work presents the concept, design and implementation of a MP-SoC platform, named STORM (MP-SoC DirecTory-Based PlatfORM). Currently the platform is composed of the following modules: SPARC V8 processor, GPOP processor, Cache module, Memory module, Directory module and two different modles of Network-on-Chip, NoCX4 and Obese Tree. All modules were implemented using SystemC, simulated and validated, individually or in group. The modules description is presented in details. For programming the platform in C it was implemented a SPARC assembler, fully compatible with gcc s generated assembly code. For the parallel programming it was implemented a library for mutex managing, using the due assembler s support. A total of 10 simulations of increasing complexity are presented for the validation of the presented concepts. The simulations include real parallel applications, such as matrix multiplication, Mergesort, KMP, Motion Estimation and DCT 2D

Segmentação fuzzy de imagens coloridas com características texturais: uma aplicação a rochas sedimentares

Image segmentation is the process of labeling pixels on di erent objects, an important step in many image processing systems. This work proposes a clustering method for the segmentation of color digital images with textural features. This is done by reducing the dimensionality of histograms of color images and using the Skew Divergence to calculate the fuzzy a nity functions. This approach is appropriate for segmenting images that have colorful textural features such as geological, dermoscopic and other natural images, as images containing mountains, grass or forests. Furthermore, experimental results of colored texture clustering using images of aquifers' sedimentary porous rocks are presented and analyzed in terms of precision to verify its e ectiveness.

Revisão sobre técnicas de controle em estruturas inteligentes

One of the great challenges of structural dynamics is to ally structures lighther and stronger. The great difficulty is that light systems, in general, have a low inherent damping. Besides, they contain resonance frequencies in the low frequency range. So, any external disturbance can excite the system in some resonance and the resulting effect can be drastic. The methodologies of active damping, with control algorithms and piezoelectric sensors and actuators coupled in a base structure, are attractive in current days, in order to overcome the contradictory features of these requeriments. In this sense, this article contributes with a bibliographical review of the literature on the importance of active noise and vibration control in engineering applications, models of smart structures, techniques of optimal placement of piezoelectric sensors and actuators and methodologies of structural active control. Finally, it is discussed the future perspectives in this area.

Robust and fast vowel recognition using optimum-path forest

The applications of Automatic Vowel Recognition (AVR), which is a sub-part of fundamental importance in most of the speech processing systems, vary from automatic interpretation of spoken language to biometrics. State-of-the-art systems for AVR are based on traditional machine learning models such as Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs), however, such classifiers can not deal with efficiency and effectiveness at the same time, existing a gap to be explored when real-time processing is required. In this work, we present an algorithm for AVR based on the Optimum-Path Forest (OPF), which is an emergent pattern recognition technique recently introduced in literature. Adopting a supervised training procedure and using speech tags from two public datasets, we observed that OPF has outperformed ANNs, SVMs, plus other classifiers, in terms of training time and accuracy. ©2010 IEEE.

Avaliação de operadores de algoritmos genéticos em otimização multidimensional

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Técnicas de paralelização em GPGPU aplicadas em algoritmo para remoção de ruído multiplicativo

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

A metáfora e a sua representação em sistemas de processamento automático de línguas naturais

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Pesquisa de ovos de helmintos e cistos de protozoários parasitos em recursos hídridos destinados à irrigação agrícola e/ou consumo animal na região peri-urbana de Botucatu-SP-Brasil

Pós-graduação em Medicina Veterinária - FMVZ

Division of labor between M and P visual pathways: different visual pathways minimize joint entropy differently

Visual perception and action are strongly linked with parallel processing channels connecting the retina, the lateral geniculate nucleus, and the input layers of the primary visual cortex. Achromatic vision is provided by at least two of such channels formed by the M and P neurons. These cell pathways are similarly organized in primates having different lifestyles, including species that are diurnal, nocturnal, and which exhibit a variety of color vision phenotypes. We describe the M and P cell properties by 3D Gábor functions and their 3D Fourier transform. The M and P cells occupy different loci in the Gábor information diagram or Fourier Space. This separation allows the M and P pathways to transmit visual signals with distinct 6D joint entropy for space, spatial frequency, time, and temporal frequency. By combining the M and P impacts on the cortical neurons beyond V1 input layers, the cortical pathways are able to process aspects of visual stimuli with a better precision than it would be possible using the M or P pathway alone. This performance fulfils the requirements of different behavioral tasks.

Modelagem do mCSEM no domínio do tempo usando transformada discreta de Fourier

A modelagem do mCSEM é feita normalmente no domínio da frequência, desde sua formulação teórica até a análise dos resultados, devido às simplificações nas equações de Maxwell, possibilitadas quando trabalhamos em um regime de baixa frequência. No entanto, a abordagem através do domínio do tempo pode em princípio fornecer informação equivalente sobre a geofísica da subsuperfície aos dados no domínio da frequência. Neste trabalho, modelamos o mCSEM no domínio da frequência em modelos unidimensionais, e usamos a transformada discreta de Fourier para obter os dados no domínio do tempo. Simulamos ambientes geológicos marinhos com e sem uma camada resistiva, que representa um reservatório de hidrocarbonetos. Verificamos que os dados no domínio do tempo apresentam diferenças quando calculados para os modelos com e sem hidrocarbonetos em praticamente todas as configurações de modelo. Calculamos os resultados considerando variações na profundidade do mar, na posição dos receptores e na resistividade da camada de hidrocarbonetos. Observamos a influência da airwave, presente mesmo em profundidades oceânicas com mais de 1000m, e apesar de não ser possível uma simples separação dessa influência nos dados, o domínio do tempo nos permitiu fazer uma análise de seus efeitos sobre o levantamento. Como parte da preparação para a modelagem em ambientes 2D e 3D, fazemos também um estudo sobre o ganho de desempenho pelo uso do paralelismo computacional em nossa tarefa.