Image restoration techniques based on fuzzy neural networks

By establishing some suitable partitions of input and output spaces, a novel fuzzy neural network (FNN) which is called selection type FNN is developed. Such a system is a multilayer feedforward neural network, which can be a universal approximator with maximum norm. Based on a family of fuzzy inference rules that are of real senses, a simple and useful inference type FNN is constructed. As a result, the fusion of selection type FNN and inference type FNN results in a novel filter-FNN filter. It is simple in structure. And also it is convenient to design the learning algorithm for structural parameters. Further, FNN filter can efficiently suppress impulse noise superimposed on image and preserve fine image structure, simultaneously. Some examples are simulated to confirm the advantages of FNN filter over other filters, such as median filter and adaptive weighted fuzzy mean (AWFM) filter and so on, in suppression of noises and preservation of image structure.     

用神经网络计算矩阵特征值与特征向量

该文研究用神经网格求解一般实对称矩阵的全部特征向量的问题。详细讨论了网络的平均态度合的结构并建立了平衡态集合的构造定理。通过求解简单的一维微分方程求出了网络的解析表达式。这一表达式是由对称矩阵的特征值与特征向量表达的、因而非常清晰利用解的解析表达式分析了网络的解的全局渐近行为。提出了用一些单位向量作为网络初始值计算对称矩阵的全部特征值与特征向量的具体算法。     

基于非线性Volterra信道的复数神经多项式盲均衡算法

针对传统常模算法收敛速度慢、均方误差大以及传统神经网络参数多、复杂度高的问题,提出了基于非线性Volterra信道的复数神经多项式盲均衡算法(Fuzzy neural network-complex valued neural polynomial-constant modulus algorithm,FNN -CNP-CMA）。该算法包含单层神经网络和非线性处理器的复数神经多项式,模块结构简单、复杂度低。由模糊神经网络(Fuzzy neural network, FNN）设计的模糊规则控制器能有效提高步长的控制精度。仿真实验结果表明,该算法系统结构简单、复杂度低、收敛速度快且稳态误差小,较好地解决了收敛速度与均方误差之间存在的矛盾。     

Dynamical optimal training for interval type-2 fuzzy neural network (T2FNN)

Type-2 fuzzy logic system (FLS) cascaded with neural network, type-2 fuzzy neural network (T2FNN), is presented in this paper to handle uncertainty with dynamical optimal learning. A T2FNN consists of a type-2 fuzzy linguistic process as the antecedent part, and the two-layer interval neural network as the consequent part. A general T2FNN is computational-intensive due to the complexity of type 2 to type 1 reduction. Therefore, the interval T2FNN is adopted in this paper to simplify the computational process. The dynamical optimal training algorithm for the two-layer consequent part of interval T2FNN is first developed. The stable and optimal left and right learning rates for the interval neural network, in the sense of maximum error reduction, can be derived for each iteration in the training process (back propagation). It can also be shown both learning rates cannot be both negative. Further, due to variation of the initial MF parameters, i.e., the spread level of uncertain means or deviations of interval Gaussian MFs, the performance of back propagation training process may be affected. To achieve better total performance, a genetic algorithm (GA) is designed to search optimal spread rate for uncertain means and optimal learning for the antecedent part. Several examples are fully illustrated. Excellent results are obtained for the truck backing-up control and the identification of nonlinear system, which yield more improved performance than those using type-1 FNN.     

Numerical solution of a system of fuzzy polynomials by fuzzy neural network

In this paper, a new approach for solving systems of fuzzy polynomials based on fuzzy neural network (FNN) is presented. This method can also lead to improve numerical methods. In this work, an architecture of fuzzy neural networks is also proposed to find a real root of a system of fuzzy polynomials (if exists) by introducing a learning algorithm. Finally, we illustrate our approach by numerical examples.     

基于模糊神经网络的网络业务分类研究

该文利用神经网络的自学习能力和模糊逻辑的动态性和及时性等特点,将模糊逻辑和神经网络有机地结合起来,构造出了四层模糊神经网络,并用训练神经网络的相应学习算法训练网络,将该模型用于网络业务源特征提取与分类的研究中,并与单纯的神经网络算法相比较。计算机仿真结果表明,模糊神经网络方法比神经网络算法更优越,该文的研究结果为解决网络业务源特征提取与分类奠定了基础。     

多传感器技术在污水分析中的应用研究

实现污水分析的自动化和分析结果的准确性是污水处理厂的重要任务,模糊神经网络技术的迅速发展及其理论的不断完善为其在此领域的应用奠定了基础,通过实践证明:该理论用于污水分析系统是可行的。传统的污水自动分析系统中存在许多问题,多传感器技术的应用,使这些问题得到了解决。利用模糊神经网络技术对多传感器系统进行模型的建立,并将该模型应用到实际的污水分析系统中,与传统的系统及方法进行比较,得到了良好的实验效果。     

一种基于FNN的高速网络拥塞控制策略

以ATM（asynchronous transfer mode)为研究对旬,同种基于模糊神经网络（fuzzy neural network,简称FNN）的流量预测和拥塞控制策略,拥塞控制是高速网络（如ATM）研究中的关键问题之一,传统的基于BP神经网络的流量预测方法因其收敛速度较慢且具有较大的误差,影响了拥塞控制效果,而模糊神经网络由于具有处理不确定性问题和很强的学习能力,很好地解决这一问题,最后通过仿真,比较和分析了基于BP神经网络和基于FNN方法和性能,证明此方法是有效的。     

基于因素神经网络的入侵检测模型

通过对网络攻击和防御的分析,提出一种基于因素神经网络理论（FNN）的入侵检测模型,描述入侵检测模型的结构和工作流程,将解析型因素神经网络和模拟型因素神经网络结合起来,解决对复杂入侵行为建模难的问题。通过实验对模型进行验证,实验表明该模型对已知入侵行为检测的准确度高,对未知入侵行为也能做出准确的判断。     

A fuzzy neural network approach for online fault detection in waste water treatment process

In this paper, an effective strategy for fault detection of sludge volume index (SVI) sensor is proposed and tested on an experimental hardware setup in waste water treatment process (WWTP). The main objective of this fault detection strategy is to design a system which consists of the online sensors, the SVI predicting plant and fault diagnosis method. The SVI predicting plant is designed utilizing a fuzzy neural network (FNN), which is trained by a historical set of data collected during fault-free operation of WWTP. The fault diagnosis method, based on the difference between the measured concentration values and FNN predictions, allows a quick revealing of the faults. Then this proposed fault detection method is applied to a real WWTP and compared with other approaches. Experimental results show that the proposed fault detection strategy can obtain the fault signals of the SVI sensor online.     

On multistage fuzzy neural network modeling

In the past couple of years, there has been increasing interest in the fusion of neural networks and fuzzy logic. Most of the existing fuzzy neural network (FNN) models have been proposed to implement different types of single-stage fuzzy reasoning mechanisms and inevitably they suffer from the dimensionality problem when dealing with complex real-world problems. To address the problem, FNN modeling based on multistage fuzzy reasoning (MSFR) is pursued here and two hierarchical network models, namely incremental type and aggregated type, are introduced. The new models called multistage FNN (MSFNN) model a hierarchical fuzzy rule set that allows the consequence of a rule passed to another as a fact through the intermediate variables. From the stipulated input-output data pairs, they can generate an appropriate fuzzy rule set through structure and parameter learning procedures proposed in this paper. In addition, we have particularly addressed the input selection problem of these two types of multistage network models and proposed two efficient methods for them. The effectiveness of the proposed MSFNN models in handling high-dimensional problems is demonstrated through various numerical simulations     

Calcolo degli autovalori di un parametro nei problemi differenziali ordinari con condizioni ai limiti contenenti il parametro stesso

In this paper we present a numerical method for the computation of eigenvalues (real or complex) of one parameter contained in a 2^nd order linear homogeneous differential equation, with Sturm-Liouville boundary conditions. This method, particularly apt for a computer, shortens considerably the calculation time thanks to an algorithm which quickly transforms a determinant, containing the eigenvalue in all its elements, into an equivalent determinant which contains the eingenvalue only in the elements of the principal diagonal; we think that the suggested transformation has some new points and advantages in comparison with the method based on the inversion of a matrix. The method, used to computer the roots of an algebraic equation with real coefficients, shortens further the calculation time when we have to find the eigenvalues of smaller modulus. If initially the eigenvalue is also found in the boundary conditions, the calculation are carried out in a similar way. This paper ends with some examples and notes about the program in «FORTRAN» language.     

Application of reinforcement learning in robot soccer

The robot soccer game has been proposed as a benchmark problem for the artificial intelligence and robotic researches. Decision-making system is the most important part of the robot soccer system. As the environment is dynamic and complex, one of the reinforcement learning (RL) method named FNN-RL is employed in learning the decision-making strategy. The FNN-RL system consists of the fuzzy neural network (FNN) and RL. RL is used for structure identification and parameters tuning of FNN. On the other hand, the curse of dimensionality problem of RL can be solved by the function approximation characteristics of FNN. Furthermore, the residual algorithm is used to calculate the gradient of the FNN-RL method in order to guarantee the convergence and rapidity of learning. The complex decision-making task is divided into multiple learning subtasks that include dynamic role assignment, action selection, and action implementation. They constitute a hierarchical learning system. We apply the proposed FNN-RL method to the soccer agents who attempt to learn each subtask at the various layers. The effectiveness of the proposed method is demonstrated by the simulation and the real experiments.     

A classification technique based on radial basis function neural networks

In this paper, a new classification method is proposed based on the radial basis function (RBF) neural network architecture. The method is particularly useful for manufacturing processes, in cases where on-line sensors for classifying the product quality are not available. More specifically, the fuzzy means algorithm is employed on a set of training data, where the input data refer to variables that are measured on-line and the output data correspond to quality variables that are classified by human experts. The produced neural network model acts as an artificial sensor that is able to classify the product quality in real time. The proposed method is illustrated through an application to real data collected from a paper machine. The method produces successful results and outperforms a number of classifiers, which are based on the feedforward neural network (FNN) architecture.     

一种计算矩阵特征值特征向量的神经网络方法

当把Oja学习规则描述的连续型全反馈神经网络(Oja-N)用于求解矩阵特征值特征向量时,网络初始向量需位于单位超球面上,这给应用带来不便.由此,提出一种求解矩阵特征值特征向量的神经网络(1yNN)方法.在lyNN解析解基础上得到了以下结果:初始向量属于任意特征值对应特征向量张成的子空间,则网络平衡向量也将属于该空间;分析了lyNN收敛于矩阵最大特征值对应特征向量的初始向量取值条件;明确了lyNN收敛于矩阵不同特征值的特征子空间时,网络初始向量的最大取值空间;网络初始向量与已知特征向量垂直,则lyNN平衡解向量将垂直于该特征向量;证明了平衡解向量位于由非零初始向量确定的超球面上的结论.基于以上分析,设计了用lyNN求矩阵特征值特征向量的具体算法,实例演算验证了该算法的有效性.1yNN不出现有限溢,而基于Oja-N的方法在矩阵负定、初始向量位于单位超球面外时必出现有限溢,算法失效.与基于优化的方法相比,lyNN实现容易,计算量较小.     

BP神经网络结构参数的计算机自动确定

研究表明,由多层FNN的BP算法误差函数构成的非线性方程组的独立方程个数和FNN的待求未知变量的个数应该相等,该方程组才能有唯一组解。由此导出网络结构方程式,进而导出隐层层数判别式和每层神经元个数判别式。依据Kolmogorov定理,由该判别式得出求解FNN隐层层数和每个隐层神经元个数的具体算法。计算机仿真结果表明该方法简明实用。     

一款可编程语音处理器的设计与应用

提出了一种基于模糊神经网络的数据挖掘算法,把模糊理论和神经网络结合起来构造、训练模糊神经网络,弥补了神经网络结构复杂、网络训练时间长、结果表示不易理解等不足.经过模糊神经网络的建立和训练达到精度要求,实现了运用模糊神经网络方法从数据库中提取知识的目标.     

应用模糊神经网络预测油田产量

为了研究受多变量、时变和不确定因素影响的油田产量预测问题,将模糊逻辑推理技术与人工神经网络相结合,构建具有模糊逻辑推理和学习功能的模糊神经网络(FNN)系统。该系统基于现有的油田开发历史数据,建立相应的规则集,使用神经网络的训练方法(如梯度下降学习算法),在训练过程中调整参数,并自适应增加规则,以使系统的输出最佳地逼近于目标样本。通过对某油田的实际开发历史数据的拟合与测试,结果表明该模糊神经网络能够较精确地预测未来的油产量,与常规的BP神经网络相比,其预测精度更高、训练速度更快。因此,基于模糊神经网络(FNN)的油田产量预测方法研究具有较好的实际应用价值。     

Performance comparisons of intelligent load forecasting structures and its application to energy-saving load regulation

This study mainly focuses on the development of intelligent forecasting structures via a similar time method with historical load change rates for the hourly, daily and monthly load forecasting simultaneously based on the basic frameworks of fuzzy neural network (FNN) and particle swarm optimization (PSO). In the regulative aspect of network parameters, conventional back-propagation (BP) and PSO tuning algorithms are used, and varied learning rates are designed in the sense of discrete-time Lyapunov stability theory. The performance comparisons of different intelligent forecasting structures including neural network (NN) structure with BP tuning algorithm (NN-BP), FNN structure with BP tuning algorithm (FNN-BP), FNN structure with BP tuning algorithm and varied learning rates (FNN-BP-V), FNN structure with PSO tuning algorithm (FNN-PSO) and newly-designed adaptive PSO (APSO) structure are verified by numerical simulations. In order to verify the effectiveness of the superior APSO forecasting structure in practical energy-saving load regulation, the load forecasting during every 15 min is also given, and its result is used to manipulate the scheduled unloading control of a real case in Taiwan campus.     

一种基于模糊神经网络的数据挖掘算法

提出了一种基于模糊神经网络的数据挖掘算法，把模糊理论和神经网络结合起来构造、训练模糊神经网络，弥补了神经网络结构复杂、网络训练时间长、结果表示不易理解等不足。经过模糊神经网络的建立和训练达到精度要求，实现了运用模糊神经网络方法从数据库中提取知识的目标。