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 …     

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…     

Principal component analysis using neural network

The authors present their analysis of the differential equation dX(t)/dt=AX(t)-XT(t)BX(t)X(t), where A is an unsymmetrical real matrix, B is a positive definite symmetric real matrix, X∈Rn; showing that the equation characterizes a class of continuous type full-feedback artificial neural network; We give the analytic expression of the solution; discuss its asymptotic behavior; and finally present the result showing that, in almost all cases, one and only one of following cases is true. 1. For any initial value X0∈Rn, the solution approximates asymptotically to zero vector. In this case, the real part of each eigenvalue of A is non-positive. 2. For any initial value X0 outside a proper subspace of Rn, the solution approximates asymptotically to a nontrivial constant vector (X0). In this case, the eigenvalue of A with maximal real part is the positive number λ=‖(X0)‖2B and (X0) is the corresponding eigenvector. 3. For any initial value X0 outside a proper subspace of Rn, the solution approximates asymptotically to a non-constant periodic function (X0,t). Then the eigenvalues of A with maximal real part is a pair of conjugate complex numbers which can be computed.     

A BOD-DO coupling model for water quality simulation by artificial neural network

A one-dimensional BOD-DO coupling model for water quality simulation is presented,which adopts Streeter-Phelps equations and the theory of back-propagation artificial neural network.The water quality data of Yangtze River in the Chongqing region in the year of 1989 are divided into 5 groups and used in the learning and testing courses of this model.The result shows that such model is feasible for water quality simulation and is more accurate than traditional models.     

A hybrid neural network system for prediction and recognition of promoter regions in human genome

INTRODUCTION The publication and preliminary analysis of thehuman genome sequence (Lander et al., 2001; Venteret al., 2001) marks a significant milestone in the fieldof molecular biology. One of the main goals of theHuman Genome Project is the characterization, an-notation?recognition and categorization of genesfrom human genome to serve as a periodic table forbiomedical research (Lander, 1996). In the past fewyears, many efforts have been devoted to gene anno-tations. The Nation…     

A new neural network model for the feedback stabilization of nonlinear systems

A new neural network model termed ＇standard neural network model＇ （SNNM） is presented, and a state-feedback control law is then designed for the SNNM to stabilize the closed-loop system. The control design constraints are shown to be a set of linear matrix inequalities （LMIs）, which can be easily solved by the MATLAB LMI Control Toolbox to determine the control law. Most recurrent neural networks （including the chaotic neural network） and nonlinear systems modeled by neural networks or Takagi and Sugeno （T-S） fuzzy models can be transformed into the SNNMs to be stabilization controllers synthesized in the framework of a unified SNNM. Finally, three numerical examples are provided to illustrate the design developed in this paper.     

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.     

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...     

基于BP神经网络的公交车辆实时调度

神经网络是一种新兴的数学建模方法,它具有识别复杂非线性系统的特性,比较适合实时调度。论文对神经网络模型-BP神经网络的结构及算法进行了描述,在此基础上提出了基于BP神经网络的实时调度预测模型。基于BP神经网络的实时调度预测模型的输入变量是相关站点同一时间段的客流量,输出变量为发车调度形式。     

基于Elman网络的企业盈利能力测评模型

为了克服传统的企业盈利能力测评方法的诸多缺陷,发挥神经网络能自学习、自组织,能在事先不知事物内部机理的情况下进行建模的优势,建立基于Elman网络的测评模型,对企业盈利能力进行测评,结果表明该模型的仿真结果可靠,测评精度高,具有很大的实用价值.     

基于BP神经网络的校园用水预测模型

校园人口密集,用水量大,对某一栋教学楼或某一区域的定量用水预测,对于发现用水异常、合理下达用水指标有实际意义.本文利用BP神经网络,结合校园用水的特点,建立校园用水预测模型,并以实际数据进行验证,证明其有效性.     

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。     

论传统与现代的能力意识

在中国现代化发展中,人们越来越重视能力的发展。本文就传统与现代的能力意识提出一些自己的看法。     

Neural network and genetic algorithm based global path planning in a static environment

INTRODUCTION The path planning problem of a mobile robot is to find a safe and efficient path for the robot, given a start location, a goal location and a set of obstacles distributed in a workspace. The robot can go from the start location to the goal location without colliding with any obstacle along the path. In addition to the fundamental problem, we also try to find a way to optimize the plan, say to minimize the time required or distance traveled (Wu et al., 1996; Sadati and Ta-he…     

A biologically inspired model for pattern recognition

In this paper, a novel bionic model and its performance in pattern recognition are presented and discussed. The model is constructed from a bulb model and a three-layered cortical model, mimicking the main features of the olfactory system. The olfactory bulb and cortex models are connected by feedforward and feedback fibers with distributed delays. The Breast Cancer Wisconsin dataset consisting of data from 683 patients divided into benign and malignant classes is used to demonstrate the capacity of the mod...     

基于模糊神经网络的智能能量管理策略研究——以混合动力电动汽车模型为例

针对当前在标准行驶工况下开发的混合动力电动汽车优化控制策略不能根据变化的行驶工况动态调整控制策略的问题,提出一种基于模糊神经网络的混合动力电动汽车动态能量管理策略：先利用模糊神经网络进行工况识别,然后根据识别的工况类型动态调整自身控制参数.仿真实验显示,该策略可以有效提高混合动力汽车的燃油消耗,并降低污染物的排放量.     

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．     

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]…     

基于模糊观测数据的RBF神经网络回归模型

提出了一种基于模糊观测数据的RBF神经网络（FORBFNN）,用于解决一类输出不可精确测量但可用模糊隶属度来表征的非线性系统建模问题．神经网络模型中各隐层神经单元的权重系数采用一种新的模糊EM算法辨识获得;隐层神经单元的数量及径向基函数的中心和宽度基于一种数据驱动的方法自适应确定,即首先初始生成一个隐层单元,然后根据一定的规则逐步加入新的单元,该过程不断迭代直到模型满足预设要求．该方法同时考虑了模型的复杂度及预测精度．数值模拟实验结果表明该建模方法是有效的,且建立的模型具有较高的预测精度．     

琢保意识要从小培养

目前全球生态环境的恶化已经严重地威胁着人类的发展，如何在发展经济的同时保护人类赖以生存和发展的生态环境，已成为全世界人民面临的紧迫而艰巨的任务。作为跨世纪的生力军，儿童的环保意识和环保行为是必须具备的基础素质，本文就如何从小培养儿童的环保意识，谈一点看法。