Clustering-based selective neural network ensemble

INTRODUCTION Neural network ensemble is becoming a hot spot in machine learning and data mining recently. Many researchers have shown that simply combining the output of many neural networks can generate more accurate predictions than that of any of the individual networks. Most previous work either focused on how to combine the output of multiple trained networks or how to directly design a good set of neural networks. Theoretical and empirical work showed that a good ensemble is one wh…     

Identification of rice seed varieties using neural network

A digital image analysis algorithm based color and morphological features was developed to identify the six varieties (ey7954, syz3, xs1 1, xy5968, xy9308, z903) rice seeds which are widely planted in Zhejiang Province. Seven color and fourteen morphological features were used for discriminant analysis. Two hundred and forty kernels used as the training data set and sixty kernels as the test data set in the neural network used to identify rice seed varieties. When the model was tested on the test data set,the identification accuracies were 90.00％, 88.00％, 95.00％, 82.00％, 74.00％, 80.00％ for ey7954, syz3, xsl 1, xy5968, xy9308,z903 respectively.     

Principal component analysis using LISREL 8

The object of this article is to demonstrate that the widely disseminated program LISREL 8 can be used to carry out principal component analyses. LISREL 8 offers a number of useful possibilities including multigroup principal component analysis and principal component regression. Several illustrative analyses are reported.     

A hybrid neural network model for consciousness

A new framework for consciousness is introduced based upon traditional artificial neural network models. This framework reflects explicit connections between two parts of the brain: one global working memory and distributed modular cerebral networks relating to specific brain functions. Accordingly this framework is composed of three layers,physical mnemonic layer and abstract thinking layer,which cooperate together through a recognition layer to accomplish information storage and cognition using algorithms of how these interactions contribute to consciousness:(1)the reception process whereby cerebral subsystems group distributed signals into coherent object patterns;(2)the partial recognition process whereby patterns from particular subsystems are compared or stored as knowledge; and(3)the resonant learning process whereby global workspace stably adjusts its structure to adapt to patterns' changes. Using this framework,various sorts of human actions can be explained,leading to a general approach for analyzing brain functions.     

A hybrid neural network model for consciousness

INTRODUCTION The goal of understanding the brain and making artificial minds has propelled many scientificfields greatly. In a sense it may be the final goal othe whole science. It is impossible that one unifiedtheory will be sufficient for explaining the brain’functionality because of its unimaginable complexity. Multi-discipline combinations havebrought about so many achievements towards thigoal. Taylor (1994) introduced the “relationamind” approach in …     

Assessment of highway slope failure using neural networks

An artificial intelligence technique of back-propagation neural networks is used to assess the slope failure. On-site slope failure data from the South Cross-Island Highway in southern Taiwan are used to test the performance of the neural network model. The numerical results demonstrate the effectiveness of artificial neural networks in the evaluation of slope failure potential based on five major factors, such as the slope gradient angle, the slope height, the cumulative precipitation, daily rainfall and strength of materials.     

Stability analysis of discrete-time BAM neural networks based on standard neural network models

To facilitate stability analysis of discrete-time bidirectional associative memory (BAM) neural networks, they were converted into novel neural network models, termed standard neural network models (SNNMs), which interconnect linear dynamic systems and bounded static nonlinear operators. By combining a number of different Lyapunov functionals with S-procedure, some useful criteria of global asymptotic stability and global exponential stability of the equilibrium points of SNNMs were derived. These stability conditions were formulated as linear matrix inequalities (LMIs). So global stability of the discrete-time BAM neural networks could be analyzed by using the stability results of the SNNMs. Compared to the existing stability analysis methods, the proposed approach is easy to implement, less conservative, and is applicable to other recurrent neural networks.     

Neural decoding based on probabilistic neural network

Brain-machine interface (BMI) has been developed due to its possibility to cure severe body paralysis. This technology has been used to realize the direct control of prosthetic devices,such as robot arms,computer cursors,and paralyzed muscles. A variety of neural decoding algorithms have been designed to explore relationships between neural activities and movements of the limbs. In this paper,two novel neural decoding methods based on probabilistic neural network (PNN) in rats were introduced,the PNN decode...     

Multi-agent reinforcement learning using modular neural network Q-learning algorithms

1 Introduction Reinforcement learning is a machine learningmethod for agents to acquire the optimal policyautonomously from the environment of their behaviors.When an action is executed, the agent receives areinforcement signal by interacting with theenvironment. This technology has recently been used inmany fields, such as robot control [1], artificialintelligence [2], especially multi-agent system [3,4].Generally, when the state space of the environment issmall enough and all states can be e…     

主成分分析法及其EXCEL实现

主成分分析是一种重要的多元统计分析方法,其广泛应用于自然科学和社会科学的研究中。主成分分析运算过程较复杂,一般需要借助于统计软件来实现。如果手工运算不但计算量大,而且容易出错。文章利用EXCEL中的相关函数,给出了一种实现主成分分析的EXCEL简便算法。     

基于倒立摆系统前馈型神经网络实验的开发

介绍一个基于MATLAB/SIMULINK和直线一级倒立摆系统的前馈型人工神经网络的实验方案。设计了一级倒立摆系统BP神经网络控制器,并完成了仿真和实物控制实验。实验结果有利于对前馈型人工神经网络的本质认识。     

一种使用混沌神经网络的电力负荷预测方法

本文对实际电力月负荷数据进行预处理,将其分为趋势序列和剩余序列两部分。计算剩余序列的最大Lyapunov指数、延迟时间等参数,发现其混沌特征。提出了一种使用混沌BP神经网络的电力月负荷预测方法。根据历史负荷序列预处理和Lyapunov指数估算,确定了网络的训练样本和网络参数,通过对实际电力负荷进行预测,结果显示该方法具有一定的可行性。     

Modelling and control PEMFC using fuzzy neural networks

INTRODUCTION With worldwide increase of air pollution and the environmental consciousness of governments,people have to look for new resources to mitigate the energy crisis and improve the present environmental status(Baschuk and Li,2000;Rowe and Li,2001).Fuel cells are highly efficient and environmentally clean electricity generators(Berning et al.,2002)that convert the chemical energy of a gaseous fuel directly into electrical energy and play an important role in solving the energy pro…     

以粒子蜂群网络建立高性能混凝土坍落度模型

以粒子蜂群算法(particle bee algorithm, PBA)结合神经网络(artificial neural network, NN),发展出一套能预测高性能混凝土(high performance concrete, HPC)坍落度模型的方法。以演化运算树(genetic operation tree, GOT)及倒传递网络(back propagation network, BPN)2种已发表的方法来比较其准确度。从模型的准确度可知,粒子蜂群网络(particle bee neural network, PBNN)模型预测的准确度高于GOT,但接近BPN的准确度;从参数的影响性可知,PBNN显示水、强塑剂、粗骨材、细骨材、粉煤灰及水泥添加量对于HPC坍落度的影响性大,而高炉矿渣粉用量对HPC坍落度并不敏感,显示各项材料对于坍落度的影响仍具备高度复杂性。     

Distribution network planning algorithm based on Hopfield neural network

1 Introduction An urban power system is a very important part othe power system and requires a huge investment for itconstruction and operation. This investment can bsubstantially reduced by a system approach to urbapower system planning which is not an easy task due tits dependence upon urban geography conditions. Foexample, feeder lines must be laid along urban streeUp to now, several mathematical models analgorithms have been developed to plan urban powesystem. Peponis and Papadopoulos [1]…     

神经网络融合模型在大坝变形分析中的应用

为了提高大坝变形分析模型的预测精度并检验模型的泛化能力,研究了大坝变形分析的BP神经网络模型,并基于神经网络BP算法和传统的统计模型建立了大坝变形分析的融合模型．结合陈村大坝多年的变形观测数据,对上述3种模型进行了试算及分析．分析结果表明,统计模型的平均预测精度为±0．477mm．BP神经网络模型的平均预测精度为±0．390mm,融合模型的平均预测精度为±0．318mm,相比统计模型和BP神经网络模型分别提高了33％和18％,且泛化能力较强,具有广泛的适用性．     

Interval standard neural network models for nonlinear systems

INTRODUCTION Neural networks have been successfully em- ployed for controlling nonlinear systems since the 1990’s (Narendra and Parthasarathy 1990; Hunt et al., 1992; Suykens et al., 1996). In these nonlinear control systems, neural networks have been used either for modelling the system to be controlled, or for design- ing a controller, or both. Recently, the robustness issue has been an important focus of research in neuro-control circles (Suykens et al., 1996; Wams et al., 1999; Aya…     

灰度共生矩阵和神经网络在医学图像处理中的应用

以龋齿诊断为例,探讨了灰度共生矩阵和神经网络在医学图像处理中的应用。通过对患者龋齿图像的特征分析,采用从灰度共生矩阵中提取的4个参数作为神经网络的输入特征向量,经过对该神经网络的多次训练,实现龋齿的识别。利用Matlab与VC++语言来设计龋齿诊断程序,并借助MIDEVA将其转化为脱离Matlab的工作环境的可执行程序,大大节省了系统资源。     

神经网络在供热管网泄漏故障诊断中的应用(英文)

为了研究供热管网泄漏检测策略,利用图论理论构建了一个基于空间管网的泄漏工况水力计算数学模型,得出节点泄漏和管段泄漏工况下管网各点的压力变化情况.然后,采用人工神经网络方法建立了一个基于BP神经网络的供热管网泄漏诊断系统.该诊断系统可根据管网中压力监测点的压力变化定位泄漏管段,实现对泄漏点位置的初步估计.最后,通过实例验证了该方法的有效性.实验结果表明,这种诊断系统对泄漏管段的预测准确率达到100%.     

Calculation method of ship collision force on bridge using artificial neural network

Ship collision on bridge is a dynamic process featured by high nonlinearity and instantaneity. Calculating ship-bridge collision force typically involves either the use of design-specification-stipulated equivalent static load, or the use of finite element method （FEM） which is more time-consuming and requires supercomputing resources. In this paper, we proposed an alternative approach that combines FEM with artificial neural network （ANN）. The radial basis function neural network （RBFNN） employed for calculating the impact force in consideration of ship-bridge collision mechanics. With ship velocity and mass as the input vectors and ship collision force as the output vector, the neural networks for different network parameters are trained by the learning samples obtained from finite element simulation results. The error analyses of the learning and testing samples show that the proposed RBFNN is accurate enough to calculate ship-bridge collision force. The input-output relationship obtained by the RBFNN is essentially consistent with the typical empirical formulae. Finally, a special toolbox is developed for calculation effi- ciency in application using MATLAB software.