Sistema inteligente para determinação de limite de crédito

A presente dissertação trata da estipulação de limite de crédito para empresas clientes, de modo automático, com o uso de técnicas de Inteligência Computacional, especificamente redes neurais artificiais (RNA). Na análise de crédito as duas situações mais críticas são a liberação do crédito, de acordo com o perfil do cliente, e a manutenção deste limite ao longo do tempo de acordo com o histórico do cliente. O objeto desta dissertação visa a automação da estipulação do limite de crédito, implementando uma RNA que possa aprender com situações já ocorridas com outros clientes de perfil parecido e que seja capaz de tomar decisões baseando-se na política de crédito apreendida com um Analista de Crédito. O objetivo é tornar o sistema de crédito mais seguro para o credor, pois uma análise correta de crédito de um cliente reduz consideravelmente os índices de inadimplência e mantém as vendas num patamar ótimo. Para essa análise, utilizouse a linguagem de programação VB.Net para o sistema de cadastro e se utilizou do MatLab para treinamento das RNAs. A dissertação apresenta um estudo de caso, onde mostra a forma de aplicação deste software para a análise de crédito. Os resultados obtidos aplicando-se as técnicas de RNAs foram satisfatórias indicando um caminho eficiente para a determinação do limite de crédito.

Redes neurais artificiais aplicadas à determinação do tamanho ótimo da malha para o cálculo da intensidade útil

Neste trabalho é apresentado um estudo para a determinação do tamanho ótimo da malha de elementos, utilizando redes neurais artificiais, para o cálculo da intensidade útil. A ideia principal é treinar as redes de modo a possibilitar a aprendizagem e o reconhecimento do melhor tamanho para diversas áreas superficiais em fontes sonoras com geometria plana. A vantagem de se utilizar redes neurais artificiais deve-se ao fato de apresentarem um único tamanho para a obtenção da intensidade útil, consequentemente, uma redução significativa de tempo computacional quando comparado com o tempo de cálculo de uma malha bem refinada. Ensaios numéricos com placas planas - geometria separável que permite uma solução analítica - são utilizados para se realizar comparações. É apresentado um estudo comparativo entre o tempo computacional gasto para a obtenção da intensidade útil e o mesmo com a malha otimizada via redes neurais artificiais. Também é apresentada uma comparação do nível de potência sonora mediante solução numérica, a fim de validar os resultados apresentados pelas redes neurais.

Inteligência computacional aplicada na geração de respostas impulsivas bi-auriculares e em aurilização de salas

Neste trabalho é apresentada uma nova abordagem para obter as respostas impulsivas biauriculares (BIRs) para um sistema de aurilização utilizando um conjunto de redes neurais artificiais (RNAs). O método proposto é capaz de reconstruir as respostas impulsivas associadas à cabeça humana (HRIRs) por meio de modificação espectral e de interpolação espacial. A fim de cobrir todo o espaço auditivo de recepção, sem aumentar a complexidade da arquitetura da rede, uma estrutura com múltiplas RNAs (conjunto) foi adotada, onde cada rede opera uma região específica do espaço (gomo). Os três principais fatores que influenciam na precisão do modelo arquitetura da rede, ângulos de abertura da área de recepção e atrasos das HRIRs são investigados e uma configuração ideal é apresentada. O erro de modelagem no domínio da frequência é investigado considerando a natureza logarítmica da audição humana. Mais ainda, são propostos novos parâmetros para avaliação do erro, definidos em analogia com alguns dos bem conhecidos parâmetros de qualidade acústica de salas. Através da metodologia proposta obteve-se um ganho computacional, em redução do tempo de processamento, de aproximadamente 62% em relação ao método tradicional de processamento de sinais utilizado para aurilização. A aplicabilidade do novo método em sistemas de aurilização é reforçada mediante uma análise comparativa dos resultados, que incluem a geração das BIRs e o cálculo dos parâmetros acústicos biauriculares (IACF e IACC), os quais mostram erros de magnitudes reduzidas.

Pixelated liquid-crystal light valve for neural network application.

The liquid-crystal light valve (LCLV) is a useful component for performing integration, thresholding, and gain functions in optical neural networks. Integration of the neural activation channels is implemented by pixelation of the LCLV, with use of a structured metallic layer between the photoconductor and the liquid-crystal layer. Measurements are presented for this type of valve, examples of which were prepared for two specific neural network implementations. The valve fabrication and measurement were carried out at the State Optical Institute, St. Petersburg, Russia, and the modeling and system applications were investigated at the Institute of Microtechnology, Neuchâtel, Switzerland.

Gaussian Process Regression Networks

We introduce a new regression framework, Gaussian process regression networks (GPRN), which combines the structural properties of Bayesian neural networks with the non-parametric flexibility of Gaussian processes. This model accommodates input dependent signal and noise correlations between multiple response variables, input dependent length-scales and amplitudes, and heavy-tailed predictive distributions. We derive both efficient Markov chain Monte Carlo and variational Bayes inference procedures for this model. We apply GPRN as a multiple output regression and multivariate volatility model, demonstrating substantially improved performance over eight popular multiple output (multi-task) Gaussian process models and three multivariate volatility models on benchmark datasets, including a 1000 dimensional gene expression dataset.

Generalization in Adaptation to Stable and Unstable Dynamics

Humans skillfully manipulate objects and tools despite the inherent instability. In order to succeed at these tasks, the sensorimotor control system must build an internal representation of both the force and mechanical impedance. As it is not practical to either learn or store motor commands for every possible future action, the sensorimotor control system generalizes a control strategy for a range of movements based on learning performed over a set of movements. Here, we introduce a computational model for this learning and generalization, which specifies how to learn feedforward muscle activity in a function of the state space. Specifically, by incorporating co-activation as a function of error into the feedback command, we are able to derive an algorithm from a gradient descent minimization of motion error and effort, subject to maintaining a stability margin. This algorithm can be used to learn to coordinate any of a variety of motor primitives such as force fields, muscle synergies, physical models or artificial neural networks. This model for human learning and generalization is able to adapt to both stable and unstable dynamics, and provides a controller for generating efficient adaptive motor behavior in robots. Simulation results exhibit predictions consistent with all experiments on learning of novel dynamics requiring adaptation of force and impedance, and enable us to re-examine some of the previous interpretations of experiments on generalization. © 2012 Kadiallah et al.

Determining of the delay time for a heating ventilating and air-conditioning plant using two weighted neural network approach

This paper presents an two weighted neural network approach to determine the delay time for a heating, ventilating and air-conditioning (HVAC) plan to respond to control actions. The two weighted neural network is a fully connected four-layer network. An acceleration technique was used to improve the General Delta Rule for the learning process. Experimental data for heating and cooling modes were used with both the two weighted neural network and a traditional mathematical method to determine the delay time. The results show that two weighted neural networks can be used effectively determining the delay time for AVAC systems.

SOC dynamic power management using artificial neural network

Dynamic Power Management (DPM) is a technique to reduce power consumption of electronic system by selectively shutting down idle components. In this article we try to introduce back propagation network and radial basis network into the research of the system-level power management policies. We proposed two PM policies-Back propagation Power Management (BPPM) and Radial Basis Function Power Management (RBFPM) which are based on Artificial Neural Networks (ANN). Our experiments show that the two power management policies greatly lowered the system-level power consumption and have higher performance than traditional Power Management(PM) techniques-BPPM is 1.09-competitive and RBFPM is 1.08-competitive vs. 1.79, 1.45, 1.18-competitive separately for traditional timeout PM, adaptive predictive PM and stochastic PM.

Dynamic power management approaches based on neural network

Dynamic Power Management (DPM) is a technique to reduce power consumption of electronic system. by selectively shutting down idle components. In this article we try to introduce back propagation network and radial basis network into the research of the system-level policies. We proposed two PAY policies-Back propagation Power Management (BPPM) and Radial Basis Function Power management (RBFPM) which are based on Artificial Neural Networks (ANN). Our experiments show that the two power management policies greatly lowered the system-level power consumption and have higher performance than traditional Power Management(PM) techniques-BPPM is 1.09-competitive and RBFPM is 1.08-competitive vs. 1.79,145,1.18-competitive separately for traditional timeout PM, adaptive predictive PM and stochastic PM.

SOC dynamic power management using artificial neural network

Dynamic Power Management (DPM) is a technique to reduce power consumption of electronic system by selectively shutting down idle components. In this article we try to introduce back propagation network and radial basis network into the research of the system-level power management policies. We proposed two PM policies-Back propagation Power Management (BPPM) and Radial Basis Function Power Management (RBFPM) which are based on Artificial Neural Networks (ANN). Our experiments show that the two power management policies greatly lowered the system-level power consumption and have higher performance than traditional Power Management(PM) techniques-BPPM is 1.09-competitive and RBFPM is 1.08-competitive vs. 1.79 . 1.45 . 1.18-competitive separately for traditional timeout PM . adaptive predictive PM and stochastic PM.

A DSWN-based specific-purpose neural computing system

The Double Synapse Weighted Neuron (DSWN) is a kind of general-purpose neuron model, which with the ability of configuring Hyper-sausage neuron (HSN). After introducing the design method of hardware DSWN synapse, this paper proposed a DSWN-based specific purpose neural computing device-CASSANN-IIspr. As its application, a rigid body recognition system was developed on CASSANN-IIspr, which achieved better performance than RIBF-SVMs system.

Architecture research and hardware implementation on simplified neural computing system for face identification

This paper describes a special-purpose neural computing system for face identification. The system architecture and hardware implementation are introduced in detail. An algorithm based on biomimetic pattern recognition has been embedded. For the total 1200 tests for face identification, the false rejection rate is 3.7% and the false acceptance rate is 0.7%.

Artificial neural network classification based on high-performance liquid chromatography of urinary and serum nucleosides for the clinical diagnosis of cancer

Nucleosides in human urine and serum have frequently been studied as a possible biomedical marker for cancer, acquired immune deficiency syndrome (AIDS) and the whole-body turnover of RNAs. Fifteen normal and modified nucleosides were determined in 69 urine and 42 serum samples using high-performance liquid chromatography (HPLC). Artificial neural networks have been used as a powerful pattern recognition tool to distinguish cancer patients from healthy persons. The recognition rate for the training set reached 100%. In the validating set, 95.8 and 92.9% of people were correctly classified into cancer patients and healthy persons when urine and serum were used as the sample for measuring the nucleosides. The results show that the artificial neural network technique is better than principal component analysis for the classification of healthy persons and cancer patients based on nucleoside data. (C) 2002 Elsevier Science B.V. All rights reserved.