一种用于函数学习的小波神经网络

在非线性系统辨识中,系统输入往往是多变量的.小波处理此类问题则比较复杂.结合神经网络形式和小波特点建立一种新型的网络,可简单有效地解决网络多输入问题.同时给出此网络可以逼近任意连续函数的数学证明.并通过实例验证了此方法的正确性.     

非线性函数逼近小波神经网络的优化及仿真

提出一种用于非线性函数逼近的小波神经网络的训练算法。分析了网络的拓扑结构,给出了网络的参数估计方法,即混合递阶遗传算法,该算法是递阶遗传算法和多元线性回归的结合,仿真研究表明该方法逼近精度高,为非线性系统建模提供了一种新方法。     

小波模糊神经网络在非线性函数逼近中的应用

将前馈神经网络与T-S模糊模型相融合构造了一种模糊神经网络,进一步利用小波变换的压缩特性与模糊神经网络相结合构造出一种小波模糊神经网络模型,并应用在非线性函数逼近上。通过仿真,结果表明小波模糊神经网络是最优的。     

基于能量密度的小波神经网络

本文提出了基于能量密度构造单隐层前向小波网络用以逼近复杂非线性函数。在时频定位分析的基础上，引入了能量密度的概念，用其作为选择小波元的标准。在本文中给出了网络构造算法及相应的学习算法，并与其它小波网及ＢＰ网进行了比较。实验结果证明了该方法是可行的，且具有小波元数目相对较少、学习收敛速度快等特点，并就其在实际应用中应注意的问题提出了我们的观点。     

基于小波模糊网络的非线性函数逼近方法的研究

针对非线性函数逼近问题,提出了一种新的融合策略——小波模糊网络;该网络将模糊模型引入小波网络,采用正交最小二乘法筛选小波,利用推广卡尔曼滤波算法调整网络非线性参数,避免陷入局部最优,提高学习速度,并采用最小二乘法修正权值,在不增加小波基函数的基础上提高网络的逼近精度;通过仿真,该网络的准确性和泛化能力都优于传统的小波神经网络,具有广泛的应用前景。     

一种用于函数优化的小波混沌神经网络

混沌神经网络能有效地解决函数优化问题。通过把sigmoid函数转化为墨西哥帽小波函数,而单一化退火因子函数被分段指数模拟退火函数所取代,提出了一种新型的混沌神经网络。与传统的混沌神经网络相比,该网络具有更强的全局寻优能力。仿真结果表明,小波混沌神经网络在搜索全局最优解的速度和精确度上都明显优于传统的混沌神经网络。     

小波神经网络逼近能力及Thau 定理推广

首先提出神经元数目有限的小波神经网络对一大类Ｌｉｐｓｃｈｉｔｚ函数的逼近能力定理;然后对Ｔｈａｕ定理进行推广,得到几个实用性较强的推广定理;最后通过构造一种基于推广Ｔｈａｕ定理的小波神经网络非线性观测器,展示出该逼近定理的应用前景。     

基于小波神经网络的系统辨识方法

神经网络由于具有良好的自学习和自适应能力，在非线性黑箱建模或系统辨识中有着广泛的应用，这些辨识模型有：多层感知器、径向基函数网和反馈网络等等。文中提出了基于小波神经网络模型的系统辨识方法。由于小波变换或分解所表面的良好的时频局部化特性，以及多尺度的功能，我们用规范正交的小波函数作为基函数网络中的基函数，得到所谓的小波神经网络。通过计算机仿真证实了该方法的良好的辨识效果。     

一种新型模糊神经网络函数逼近器

论文提出了一种新型模糊小脑模型神经网络(NFCMAC),它采用模糊隶属度函数作为接收域函数,能够获得较常规CMAC连续性强且有解析微分的复杂函数近似,具有计算量少,学习效率高等优点。同时研究了NFCMAC接受域函数的映射方法、隶属度函数及其参数的选取规律和学习算法。仿真结果表明NFCMAC具有良好的泛化能力和逼近精度,具有较高的收敛速度。     

离散非线性系统Worst-Case辨识--小波逼近法

利用小波逼近的软阈（Ｓｏｆｔ－Ｔｈｒｅｓｈｏｌｄｉｎｇ）方法，研究了离散非线性系统的Ｗｏｒｓｔ－Ｃａｓｅ辨识问题．证明了该算法在Ｗｏｒｓｔ－Ｃａｓｅ误差下的拟最优性和光滑性；估计了该算法的Ｗｏｒｓｔ－Ｃａｓｅ误差：给出了存在鲁棒收敛的辨识算法的充要条件；最后，证明了小波网逼近算法是鲁棒收敛的．     

Software development cost estimation using wavelet neural networks

Software development has become an essential investment for many organizations. Software engineering practitioners have become more and more concerned about accurately predicting the cost and quality of software product under development. Accurate estimates are desired but no model has proved to be successful at effectively and consistently predicting software development cost. In this paper, we propose the use of wavelet neural network (WNN) to forecast the software development effort. We used two types of WNN with Morlet function and Gaussian function as transfer function and also proposed threshold acceptance training algorithm for wavelet neural network (TAWNN). The effectiveness of the WNN variants is compared with other techniques such as multilayer perceptron (MLP), radial basis function network (RBFN), multiple linear regression (MLR), dynamic evolving neuro-fuzzy inference system (DENFIS) and support vector machine (SVM) in terms of the error measure which is mean magnitude relative error (MMRE) obtained on Canadian financial (CF) dataset and IBM data processing services (IBMDPS) dataset. Based on the experiments conducted, it is observed that the WNN-Morlet for CF dataset and WNN-Gaussian for IBMDPS outperformed all the other techniques. Also, TAWNN outperformed all other techniques except WNN.     

From local neural networks to granular neural networks: A study in information granulation

In this study, we are concerned with a construction of granular neural networks (GNNs)—architectures formed as a direct result reconciliation of results produced by a collection of local neural networks constructed on a basis of individual data sets. Being cognizant of the diversity of the results produced by the collection of networks, we arrive at the concept of granular neural network, producing results in the form of information granules (rather than plain numeric entities) that become reflective of the diversity of the results generated by the contributing networks. The design of a granular neural network exploits the concept of justifiable granularity. Introduced is a performance index quantifying the quality of information granules generated by the granular neural network. This study is illustrated with the aid of machine learning data sets. The experimental results provide a detailed insight into the developed granular neural networks.     

电力系统小波神经网络负荷频率控制器的研究

将小波网络用于电力系统负荷频率辨识和控制中，建立了非线性的电力系统负荷频率控制LFC模型，用递归NARMA模型的小波网络辩识器对LFC模型进行了辩识，利用Akaike’s的最终预测误差准则FPE和信息准则AIC，进行了隐层节点数目和反馈阶次的计算，用辩识结果建立了NARMA模型的小波网络的控制器，对LFC模型进行控制，理论和仿真表明辩识和控制模型可取得较好效果。     

Differential evolution trained wavelet neural networks: Application to bankruptcy prediction in banks

In this study, differential evolution algorithm (DE) is proposed to train a wavelet neural network (WNN). The resulting network is named as differential evolution trained wavelet neural network (DEWNN). The efficacy of DEWNN is tested on bankruptcy prediction datasets viz. US banks, Turkish banks and Spanish banks. Further, its efficacy is also tested on benchmark datasets such as Iris, Wine and Wisconsin Breast Cancer. Moreover, Garson’s algorithm for feature selection in multi layer perceptron is adapted in the case of DEWNN. The performance of DEWNN is compared with that of threshold accepting trained wavelet neural network (TAWNN) [Vinay Kumar, K., Ravi, V., Mahil Carr, & Raj Kiran, N. (2008). Software cost estimation using wavelet neural networks. Journal of Systems and Software] and the original wavelet neural network (WNN) in the case of all data sets without feature selection and also in the case of four data sets where feature selection was performed. The whole experimentation is conducted using 10-fold cross validation method. Results show that soft computing hybrids viz., DEWNN and TAWNN outperformed the original WNN in terms of accuracy and sensitivity across all problems. Furthermore, DEWNN outscored TAWNN in terms of accuracy and sensitivity across all problems except Turkish banks dataset.     

Application of bacterial foraging technique trained artificial and wavelet neural networks in load forecasting

A new load forecasting (LF) approach using bacterial foraging technique (BFT) trained wavelet neural network (WNN) is proposed in this paper. Artificial neural network (ANN) is combined with wavelet transform called wavelet neural network is applied for LF. The parameters of translation and dilation in the wavelet nodes and the weighting factors in the weighting nodes are tuned using BFT optimization. With the advantages of global search abilities of BFT as well as the multiresolution and localizing natures of wavelets, the networks are constructed which identifies the inherent non-linear characteristics of power system loads. The proposed approach is validated with Tamil Nadu Electricity Board (TNEB) system, India. The comparison of Delta Rule and BFT-based LF for different periods are depicted with their mean absolute percentage errors (MAPE).     

A fast procedure for the training of neural networks

A new training paradigm for artificial neural networks is described. The technique utilizes a polynomial approximation to the sigmoidal processing function and directly integrates principal components analysis (PCA) into the network training philosophy. A major benefit of the new technique is that off-line network training is ‘one-shot’, contrary to the standard iterative techniques available in the literature. Further training may be performed on-line in a recursive fashion, yielding an adaptive neural network. Additionally, the new philosophy incorporates a systematic procedure for determining the number of neurons in the hidden layer of the network. The training procedure is first described and the implications of the training philosophy discussed. Some results, including applications to industrial chemical processes, are then presented to highlight the power of the technique. The systems considered are a continuous stirred tank reactor and a polymerization reactor.     

A class of discrete time recurrent neural networks with multivalued neurons

This paper discusses a class of discrete time recurrent neural networks with multivalued neurons (MVN), which have complex-valued weights and an activation function defined as a function of the argument of a weighted sum. Complementing state-of-the-art of such networks, our research focuses on the convergence analysis of the networks in synchronous update mode. Two related theorems are presented and simulation results are used to illustrate the theory.     

A new watermarking approach based on probabilistic neural network in wavelet domain

A novel scheme of digital image watermarking based on the combination of dual-tree wavelet transform (DTCWT) and probabilistic neural network is proposed in this paper. Firstly, the original image is decomposed by DTCWT, and then the watermark bits are added to the selected coefficients blocks. Because of the learning and adaptive capabilities of neural networks, the trained neural networks can recover the watermark from the watermarked images. Experimental results show that the proposed scheme has good performance against several attacks.     

基于人工神经网络及小波分析的心音诊断方法

由于传统的心音听诊就是凭医生的经验用听觉分析心音信号,不能满足医学上所要求的高精确度性能而且听诊技能要花多年时间才能掌握,针对这些弊端本文提出了一种新的心音诊断方法.它对电子听诊器录制的心音数据,经过去噪预处理后用小波变换进行分析并提取特征值,再将选取的特征值输入到前馈型神经网络进行训练和识别.实验中我们用节点数分别为9,5,5的BP神经网络能成功识别出主动脉关闭不全,主动脉狭窄,二尖瓣关闭不全,二尖瓣狭窄,和正常心音五类心音,能为相应心脏疾病的诊断提供有力的依据,为临床应用提供有效的分析手段.     

Some multistability properties of bidirectional associative memory recurrent neural networks with unsaturating piecewise linear transfer functions

Multistability is an important dynamical property in neural networks in order to enable certain applications where monostable networks could be computationally restrictive. This paper studies some multistability properties for a class of bidirectional associative memory recurrent neural networks with unsaturating piecewise linear transfer functions. Based on local inhibition, conditions for globally exponential attractivity are established. These conditions allow coexistence of stable and unstable equilibrium points. By constructing some energy-like functions, complete convergence is studied.