Análise de desempenho da rede neural artificial do tipo multilayer perceptron na era multicore

Artificial neural networks are usually applied to solve complex problems. In problems with more complexity, by increasing the number of layers and neurons, it is possible to achieve greater functional efficiency. Nevertheless, this leads to a greater computational effort. The response time is an important factor in the decision to use neural networks in some systems. Many argue that the computational cost is higher in the training period. However, this phase is held only once. Once the network trained, it is necessary to use the existing computational resources efficiently. In the multicore era, the problem boils down to efficient use of all available processing cores. However, it is necessary to consider the overhead of parallel computing. In this sense, this paper proposes a modular structure that proved to be more suitable for parallel implementations. It is proposed to parallelize the feedforward process of an RNA-type MLP, implemented with OpenMP on a shared memory computer architecture. The research consistes on testing and analizing execution times. Speedup, efficiency and parallel scalability are analyzed. In the proposed approach, by reducing the number of connections between remote neurons, the response time of the network decreases and, consequently, so does the total execution time. The time required for communication and synchronization is directly linked to the number of remote neurons in the network, and so it is necessary to investigate which one is the best distribution of remote connections

Desenvolvimento de um material têxtil termosenssível com micro/nanocápsulas imobilizadas em fibras regeneradas

Intelligent and functional Textile Materials have been widely developed and researched with the purpose of being used in several areas of science and technology. These fibrous materials require different chemical and physical properties to obtain a multifunctional material. With the advent of nanotechnology, the techniques developed, being used as essential tools to characterize these new materials qualitatively. Lately the application of micro and nanomaterials in textile substrates has been the objective of many studies, but many of these nanomaterials have not been optimized for their application, which has resulted in increased costs and environmental pollution, because there is still no satisfactory effluent treatment available for these nanomaterials. Soybean fiber has low adsorption for thermosensitive micro and nanocapsules due to their incompatibility of their surface charges. For this reason, in this work initially chitosan was synthesized to functionalise soybean fibres. Chitosan is a natural polyelectrolyte with a high density of positive charges, these fibres have negative charges as well as the micro/nanocápsules, for this reason the chitosan acts as auxiliary agent to cationize in order to fix the thermosensitive microcapsules in the textile substrate. Polyelectrolyte was characterized using particle size analyses and the measurement of zeta potential. For the morphological analysis scanning Electron Microscopy (SEM) and x-Ray Diffraction (XRD) and to study the thermal properties, thermogravimetric analysis (TGA), Differential Scanning Calorimetry (DSC), Near Infrared Spectroscopy analysis in the Region of the Fourier Transform Infrared (FTIR), colourimetry using UV-VIS spectrum were simultaneously performed on the substrate. From the measurement of zeta potential and in the determination of the particle size, stability of electrostatic chitosan was observed around 31.55mV and 291.0 nm respectively. The result obtained with (GD) for chitosan extracted from shrimp was 70 %, which according to the literature survey can be considered as chitosan. To optimize the dyeing process a statistical software, Design expert was used. The surface functionalisation of textile substrate with 2% chitosan showed the best result of K/S, being the parameter used for the experimental design, in which this showed the best response of dyeing absorbance in the range of 2.624. It was noted that soy knitting dyed with the thermosensitive micro andnanocapsules property showed excellent washing solidity, which was observed after 25 home washes, and significant K/S values.

Implementação de uma matriz de neurônios dinamicamente reconfigurável para descrição de topologias de redes neurais artificiais multilayer perceptrons

The Artificial Neural Networks (ANN), which is one of the branches of Artificial Intelligence (AI), are being employed as a solution to many complex problems existing in several areas. To solve these problems, it is essential that its implementation is done in hardware. Among the strategies to be adopted and met during the design phase and implementation of RNAs in hardware, connections between neurons are the ones that need more attention. Recently, are RNAs implemented both in application specific integrated circuits's (Application Specific Integrated Circuits - ASIC) and in integrated circuits configured by the user, like the Field Programmable Gate Array (FPGA), which have the ability to be partially rewritten, at runtime, forming thus a system Partially Reconfigurable (SPR), the use of which provides several advantages, such as flexibility in implementation and cost reduction. It has been noted a considerable increase in the use of FPGAs for implementing ANNs. Given the above, it is proposed to implement an array of reconfigurable neurons for topologies Description of artificial neural network multilayer perceptrons (MLPs) in FPGA, in order to encourage feedback and reuse of neural processors (perceptrons) used in the same area of the circuit. It is further proposed, a communication network capable of performing the reuse of artificial neurons. The architecture of the proposed system will configure various topologies MLPs networks through partial reconfiguration of the FPGA. To allow this flexibility RNAs settings, a set of digital components (datapath), and a controller were developed to execute instructions that define each topology for MLP neural network.

Implementação de uma matriz de neurônios dinamicamente reconfigurável para descrição de topologias de redes neurais artificiais multilayer perceptrons

The Artificial Neural Networks (ANN), which is one of the branches of Artificial Intelligence (AI), are being employed as a solution to many complex problems existing in several areas. To solve these problems, it is essential that its implementation is done in hardware. Among the strategies to be adopted and met during the design phase and implementation of RNAs in hardware, connections between neurons are the ones that need more attention. Recently, are RNAs implemented both in application specific integrated circuits's (Application Specific Integrated Circuits - ASIC) and in integrated circuits configured by the user, like the Field Programmable Gate Array (FPGA), which have the ability to be partially rewritten, at runtime, forming thus a system Partially Reconfigurable (SPR), the use of which provides several advantages, such as flexibility in implementation and cost reduction. It has been noted a considerable increase in the use of FPGAs for implementing ANNs. Given the above, it is proposed to implement an array of reconfigurable neurons for topologies Description of artificial neural network multilayer perceptrons (MLPs) in FPGA, in order to encourage feedback and reuse of neural processors (perceptrons) used in the same area of the circuit. It is further proposed, a communication network capable of performing the reuse of artificial neurons. The architecture of the proposed system will configure various topologies MLPs networks through partial reconfiguration of the FPGA. To allow this flexibility RNAs settings, a set of digital components (datapath), and a controller were developed to execute instructions that define each topology for MLP neural network.

Sistema inteligente para estimar a porosidade em sedimentos a partir da análise de sinais GPR

This Thesis presents the elaboration of a methodological propose for the development of an intelligent system, able to automatically achieve the effective porosity, in sedimentary layers, from a data bank built with information from the Ground Penetrating Radar GPR. The intelligent system was built to model the relation between the porosity (response variable) and the electromagnetic attribute from the GPR (explicative variables). Using it, the porosity was estimated using the artificial neural network (Multilayer Perceptron MLP) and the multiple linear regression. The data from the response variable and from the explicative variables were achieved in laboratory and in GPR surveys outlined in controlled sites, on site and in laboratory. The proposed intelligent system has the capacity of estimating the porosity from any available data bank, which has the same variables used in this Thesis. The architecture of the neural network used can be modified according to the existing necessity, adapting to the available data bank. The use of the multiple linear regression model allowed the identification and quantification of the influence (level of effect) from each explicative variable in the estimation of the porosity. The proposed methodology can revolutionize the use of the GPR, not only for the imaging of the sedimentary geometry and faces, but mainly for the automatically achievement of the porosity one of the most important parameters for the characterization of reservoir rocks (from petroleum or water)

Desenvolvimento de uma formulação cólon específica visando o tratamento da colite ulcerativa

Micro and nanoparticulate systems as drug delivery carriers have achieved successful therapeutic use by enhancing efficacy and reducing toxicity of potent drugs. The improvement of pharmaceutical grade polymers has allowed the development of such therapeutic systems. Microencapsulation is a process in which very thin coatings of inert natural or synthetic polymeric materials are deposited around microsized particles of solids or around droplets. Products thus formed are known as microparticles. Xylan is a natural polymer abundantly found in nature. It is the most common hemicellulose, representing more than 60% of the polysaccharides existing in the cell walls of corn cobs, and is normally degraded by the bacterial enzymes present in the colon of the human body. Therefore, this polymer is an eligible material to produce colon-specific drug carriers. The aim of this study was to evaluate the technological potential of xylan for the development of colon delivery systems for the treatment of inflammatory bowel diseases. First, coacervation was evaluated as a feasible method to produce xylan microcapsules. Afterwards, interfacial cross-linking polymerization was studied as a method to produce microcapsules with hydrophilic core. Additionally, magnetic xylan-coated microcapsules were prepared in order to investigate the ability of producing gastroresistant systems. Besides, the influence of the external phase composition on the production and mean diameter of microcapsules produced by interfacial cross-linking polymerization was investigated. Also, technological properties of xylan were determined in order to predict its possible application in other pharmaceutical dosage forms

Novos sistemas de liberação de fármacos à base de xilana

The aim of this work was to perform the extraction and characterization of xylan from corn cobs and prepare xylan-based microcapsules. For that purpose, an alkaline extraction of xylan was carried out followed by the polymer characterization regarding its technological properties, such as angle of repose, Hausner factor, density, compressibility and compactability. Also, a low-cost and rapid analytical procedure to identify xylan by means of infrared spectroscopy was studied. Xylan was characterized as a yellowish fine powder with low density and poor flow properties. After the extraction and characterization of the polymer, xylan-based microcapsules were prepared by means of interfacial crosslinking polymerization and their characterization was performed in order to obtain gastroresistant multiparticulate systems. This work involved the most suitable parameters of the preparation of microcapsules as well as the study of the process, scale-up methodology and biological analysis. Magnetic nanoparticles were used as a model system to be encapsulated by the xylan microcapsules. According to the results, xylan-based microcapsules were shown to be resistant to several conditions found along the gastrointestinal tract and they were able to avoid the early degradation of the magnetic nanoparticles

Micropartículas poliméricas à base de xilana e Eudragit® S-100 contendo mesalazina visando à liberação cólon-específica

Colon-specific drug delivery systems have attracted increasing attention from the pharmaceutical industry due to their ability of treating intestinal bowel diseases (IBD), which represent a public health problem in several countries. In spite of being considered a quite effective molecule for the treatment of IBD, mesalazine (5-ASA) is rapidly absorbed in the upper gastrointestinal tract and its systemic absorption leads to risks of adverse effects. The aim of this work was to develop a microparticulate system based on xylan and Eudragit® S- 100 (ES100) for colon-specific delivery of 5-ASA and evaluate the interaction between the polymers present in the systems. Additionaly, the physicochemical and rheological properties of xylan were also evaluated. Initially, xylan was extracted from corn cobs and characterized regarding the yield and rheological properties. Afterwards, 10 formulations were prepared in different xylan and ES100 weight ratios by spray-drying the polymer solutions in 0.6N NaOH and phosphate buffer pH 7.4. In addition, 3 formulations consisting of xylan microcapsules were produced by interfacial cross-linking polymerization and coated by ES100 by means of spray-drying in different polymer weight ratios of xylan and ES100. The microparticles were characterized regarding yield, morphology, homogeneity, visual aspect, crystallinity and thermal behavior. The polymer interaction was investigated by infrared spectroscopy. The extracted xylan was presented as a very fine and yellowish powder, with mean particle size smaller than 40μm. Regarding the rheological properties of xylan, they demonstrated that this polymer has a poor flow, low density and high cohesiveness. The microparticles obtained were shown to be spherical and aggregates could not be observed. They were found to present amorphous structure and have a very high thermal stability. The yield varied according to the polymer ratios. Moreover, it was confirmed that the interaction between xylan and ES100 occurs only by means of physical aggregation

Emprego de redes neurais artificiais supervisionadas e não supervisionadas no estudo de parâmetros reológicos de excipientes farmacêuticos sólidos

In this paper artificial neural network (ANN) based on supervised and unsupervised algorithms were investigated for use in the study of rheological parameters of solid pharmaceutical excipients, in order to develop computational tools for manufacturing solid dosage forms. Among four supervised neural networks investigated, the best learning performance was achieved by a feedfoward multilayer perceptron whose architectures was composed by eight neurons in the input layer, sixteen neurons in the hidden layer and one neuron in the output layer. Learning and predictive performance relative to repose angle was poor while to Carr index and Hausner ratio (CI and HR, respectively) showed very good fitting capacity and learning, therefore HR and CI were considered suitable descriptors for the next stage of development of supervised ANNs. Clustering capacity was evaluated for five unsupervised strategies. Network based on purely unsupervised competitive strategies, classic "Winner-Take-All", "Frequency-Sensitive Competitive Learning" and "Rival-Penalize Competitive Learning" (WTA, FSCL and RPCL, respectively) were able to perform clustering from database, however this classification was very poor, showing severe classification errors by grouping data with conflicting properties into the same cluster or even the same neuron. On the other hand it could not be established what was the criteria adopted by the neural network for those clustering. Self-Organizing Maps (SOM) and Neural Gas (NG) networks showed better clustering capacity. Both have recognized the two major groupings of data corresponding to lactose (LAC) and cellulose (CEL). However, SOM showed some errors in classify data from minority excipients, magnesium stearate (EMG) , talc (TLC) and attapulgite (ATP). NG network in turn performed a very consistent classification of data and solve the misclassification of SOM, being the most appropriate network for classifying data of the study. The use of NG network in pharmaceutical technology was still unpublished. NG therefore has great potential for use in the development of software for use in automated classification systems of pharmaceutical powders and as a new tool for mining and clustering data in drug development

Técnicas de inteligência artificial para a geração dinâmica de set points para uma coluna de destilação

Artificial Intelligence techniques are applied to improve performance of a simulated oil distillation system. The chosen system was a debutanizer column. At this process, the feed, which comes to the column, is segmented by heating. The lightest components become steams, by forming the LPG (Liquefied Petroleum Gas). The others components, C5+, continue liquid. In the composition of the LPG, ideally, we have only propane and butanes, but, in practice, there are contaminants, for example, pentanes. The objective of this work is to control pentane amount in LPG, by means of intelligent set points (SP s) determination for PID controllers that are present in original instrumentation (regulatory control) of the column. A fuzzy system will be responsible for adjusting the SP's, driven by the comparison between the molar fraction of the pentane present in the output of the plant (LPG) and the desired amount. However, the molar fraction of pentane is difficult to measure on-line, due to constraints such as: long intervals of measurement, high reliability and low cost. Therefore, an inference system was used, based on a multilayer neural network, to infer the pentane molar fraction through secondary variables of the column. Finally, the results shown that the proposed control system were able to control the value of pentane molar fraction under different operational situations

Análise neurocomputacional de Antenas de microfita multibanda para sistemas de comunicação sem fio

This work presents a study of implementation procedures for multiband microstrip patch antennas characterization, using on wireless communication systems. An artificial neural network multilayer perceptron is used to locate the bands of operational frequencies of the antenna for different geometrics configurations. The antenna is projected, simulated and tested in laboratory. The results obtained are compared in order to validate the performance of archetypes that resulted in a good one agreement in metric terms. The neurocomputationals procedures developed can be extended to other electromagnetic structures of wireless communications systems

Contribuições à análise de robustez de sistemas de controle usando redes neurais

This work develops a robustness analysis with respect to the modeling errors, being applied to the strategies of indirect control using Artificial Neural Networks - ANN s, belong to the multilayer feedforward perceptron class with on-line training based on gradient method (backpropagation). The presented schemes are called Indirect Hybrid Control and Indirect Neural Control. They are presented two Robustness Theorems, being one for each proposed indirect control scheme, which allow the computation of the maximum steady-state control error that will occur due to the modeling error what is caused by the neural identifier, either for the closed loop configuration having a conventional controller - Indirect Hybrid Control, or for the closed loop configuration having a neural controller - Indirect Neural Control. Considering that the robustness analysis is restrict only to the steady-state plant behavior, this work also includes a stability analysis transcription that is suitable for multilayer perceptron class of ANN s trained with backpropagation algorithm, to assure the convergence and stability of the used neural systems. By other side, the boundness of the initial transient behavior is assured by the assumption that the plant is BIBO (Bounded Input, Bounded Output) stable. The Robustness Theorems were tested on the proposed indirect control strategies, while applied to regulation control of simulated examples using nonlinear plants, and its results are presented

Detecção e isolamento de falhas em sistemas dinâmicos baseados em redes neurais

This master dissertation presents the development of a fault detection and isolation system based in neural network. The system is composed of two parts: an identification subsystem and a classification subsystem. Both of the subsystems use neural network techniques with multilayer perceptron training algorithm. Two approaches for identifica-tion stage were analyzed. The fault classifier uses only residue signals from the identification subsystem. To validate the proposal we have done simulation and real experiments in a level system with two water reservoirs. Several faults were generated above this plant and the proposed fault detection system presented very acceptable behavior. In the end of this work we highlight the main difficulties found in real tests that do not exist when it works only with simulation environments

Algoritmos inteligentes para auto-correção, auto-verificação e auto-validação de medidas em sensores

This work presents a set of intelligent algorithms with the purpose of correcting calibration errors in sensors and reducting the periodicity of their calibrations. Such algorithms were designed using Artificial Neural Networks due to its great capacity of learning, adaptation and function approximation. Two approaches willbe shown, the firstone uses Multilayer Perceptron Networks to approximate the many shapes of the calibration curve of a sensor which discalibrates in different time points. This approach requires the knowledge of the sensor s functioning time, but this information is not always available. To overcome this need, another approach using Recurrent Neural Networks was proposed. The Recurrent Neural Networks have a great capacity of learning the dynamics of a system to which it was trained, so they can learn the dynamics of a sensor s discalibration. Knowingthe sensor s functioning time or its discalibration dynamics, it is possible to determine how much a sensor is discalibrated and correct its measured value, providing then, a more exact measurement. The algorithms proposed in this work can be implemented in a Foundation Fieldbus industrial network environment, which has a good capacity of device programming through its function blocks, making it possible to have them applied to the measurement process

Estudo do acoplamento entre superfícies seletivas de frequência assimétricas em estruturas de multicamadas

This work presents the development of new microwaves structures, filters and high gain antenna, through the cascading of frequency selective surfaces, which uses fractals Dürer and Minkowski patches as elements, addition of an element obtained from the combination of the other two simple the cross dipole and the square spiral. Frequency selective surfaces (FSS) includes a large area of Telecommunications and have been widely used due to its low cost, low weight and ability to integrate with others microwaves circuits. They re especially important in several applications, such as airplane, antennas systems, radomes, rockets, missiles, etc. FSS applications in high frequency ranges have been investigated, as well as applications of cascading structures or multi-layer, and active FSS. In this work, we present results for simulated and measured transmission characteristics of cascaded structures (multilayer), aiming to investigate the behavior of the operation in terms of bandwidth, one of the major problems presented by frequency selective surfaces. Comparisons are made with simulated results, obtained using commercial software such as Ansoft DesignerTM v3 and measured results in the laboratory. Finally, some suggestions are presented for future works on this subject