Intelligent methods for solving inverse problems of backscattering spectra with noise: a comparison between neural networks and simulated annealing

This paper investigates two different intelligent techniques—the neural network (NN) method and the simulated annealing (SA) algorithm for solving the inverse problem of Rutherford backscattering (RBS) with noisy data. The RBS inverse problem is to determine the sample structure information from measured spectra, which can be defined as either a function approximation or a non-linear optimization problem. Early studies emphasized on numerical methods and empirical fitting. In this work, we have applied intelligent techniques and compared their performance and effectiveness for spectral data analysis by solving the inverse problem. Since each RBS spectrum may contain up to 512 data points, principal component analysis is used to make the feature extraction so as to ease the complexity of constructing the network. The innovative aspects of our work include introducing dimensionality reduction and noise modeling. Experiments on RBS spectra from SiGe thin films on a silicon substrate show that the SA is more accurate but the NN is faster, though both methods produce satisfactory results. Both methods are resilient to 10% Poisson noise in the input. These new findings indicate that in RBS data analysis the NN approach should be preferred when fast processing is required; whereas the SA method becomes the first choice should the analysis accuracy be targeted.     

基于径向基函数(RBF)的安徽省GDP增长模拟与预测

本文运用新型非线性径向基函数RBF神经网络模型，对安徽省国内生产总值(GDP)进行了宏观经济模拟预测分析，结果证明与其它经济计量方法相比较，网络模型新颖，具有较好的预测精度及效果，可广泛应用于各种预测研究，有较高的应用推广价值。     

An offset-free neural controller based on a non-extrapolating scheme for approximating the inverse process dynamics

This work presents a novel control scheme based on approximating the inverse process dynamics with a radial basis function (RBF) neural network model, trained with the fuzzy means algorithm. The produced RBF network constitutes an inverse model of the process, which can be applied as an explicit control law. In order to avoid extrapolation in the RBF model predictions, a concept borrowed from chemometrics, namely the applicability domain, is incorporated to the proposed framework. Moreover, an error correction term is added, allowing the inverse neural controller to account for modeling errors and process uncertainty and eliminate offset. The proposed approach is applied to the control of a nonlinear Continuous Stirred Tank Reactor (CSTR) exhibiting multiple equilibrium points, including an unstable one. A comparison with other control schemes on various tests, including set-point tracking, unmeasured disturbance rejection and process uncertainty highlights the advantages of the proposed controller.     

Fast evaluation of neural networks via confidence rating

Neural networks have become very useful tools for input–output knowledge discovery. However, some of the most powerful schemes require very complex machines and, thus, a large amount of calculation. This paper presents a general technique to reduce the computational burden associated with the operational phase of most neural networks that calculate their output as a weighted sum of terms, which comprises a wide variety of schemes, such as Multi-Net or Radial Basis Function networks. Basically, the idea consists on sequentially evaluating the sum terms, using a series of thresholds which are associated with the confidence that a partial output will coincide with the overall network classification criterion. Furthermore, we design some procedures for conveniently sorting out the network units, so that the most important ones are evaluated first. The possibilities of this strategy are illustrated with some experiments on a benchmark of binary classification problems, using RealAdaboost and RBF networks, which show that important computational savings can be achieved without significant degradation in terms of recognition accuracy.     

Improving the generalization performance of RBF neural networks using a linear regression technique

In this paper we present a method for improving the generalization performance of a radial basis function (RBF) neural network. The method uses a statistical linear regression technique which is based on the orthogonal least squares (OLS) algorithm. We first discuss a modified way to determine the center and width of the hidden layer neurons. Then, substituting a QR algorithm for the traditional Gram–Schmidt algorithm, we find the connected weight of the hidden layer neurons. Cross-validation is utilized to determine the stop training criterion. The generalization performance of the network is further improved using a bootstrap technique. Finally, the solution method is used to solve a simulation and a real problem. The results demonstrate the improved generalization performance of our algorithm over the existing methods.     

New training strategies for RBF neural networks for X-ray agricultural product inspection

Classification of real-time X-ray images of pistachio nuts is discussed. The goal is to reduce the percentage of infested nuts while not rejecting more than a few percent of the good nuts. Radial basis function (RBF) neural network classifiers are emphasized. New training procedures are developed that allow samples such as those that are near decision boundaries to be treated differently from other samples. New clustering methods and new cluster classes are advanced to select and separately control various RBF parameters. These advancements are shown to be of use in this application.     

MIMLRBF: RBF neural networks for multi-instance multi-label learning

In multi-instance multi-label learning (MIML), each example is not only represented by multiple instances but also associated with multiple class labels. Several learning frameworks, such as the traditional supervised learning, can be regarded as degenerated versions of MIML. Therefore, an intuitive way to solve MIML problem is to identify its equivalence in its degenerated versions. However, this identification process would make useful information encoded in training examples get lost and thus impair the learning algorithm's performance. In this paper, RBF neural networks are adapted to learn from MIML examples. Connections between instances and labels are directly exploited in the process of first layer clustering and second layer optimization. The proposed method demonstrates superior performance on two real-world MIML tasks.     

基于RBF神经网络的网格数据聚类方法

把径向基函数（RBF）神经网络和网格结合起来，提出了一种能够并行处理数据和便于增量计算的智能聚类方法。介绍了网格聚类原理、RBF神经网络神经元的数量和基函数的选择，并针对数据聚集区域的位置辨识、提高分辨率和计算速度等问题，深入讨论了聚类策略与聚类算法。仿真表明了该方法的有效性。     

Artificial neural networks for vibration based inverse parametric identifications: A review

Vibration behavior of any solid structure reveals certain dynamic characteristics and property parameters of that structure. Inverse problems dealing with vibration response utilize the response signals to find out input factors and/or certain structural properties. Due to certain drawbacks of traditional solutions to inverse problems, ANNs have gained a major popularity in this field. This paper reviews some earlier researches where ANNs were applied to solve different vibration-based inverse parametric identification problems. The adoption of different ANN algorithms, input-output schemes and required signal processing were denoted in considerable detail. In addition, a number of issues have been reported, including the factors that affect ANNs’ prediction, as well as the advantage and disadvantage of ANN approaches with respect to general inverse methods Based on the critical analysis, suggestions to potential researchers have also been provided for future scopes.     

Regularization networks for inverse problems: A state-space approach

Linear inverse problems with discrete data are equivalent to the estimation of the continuous-time input of a linear dynamical system from samples of its output. The solution obtained by means of regularization theory has the structure of a neural network similar to classical RBF networks. However, the basis functions depend in a nontrivial way on the specific linear operator to be inverted and the adopted regularization strategy. By resorting to the Bayesian interpretation of regularization, we show that such networks can be implemented rigorously and efficiently whenever the linear operator admits a state-space representation. An analytic expression is provided for the basis functions as well as for the entries of the matrix of the linear system used to compute the weights. The results are illustrated through a deconvolution problem where the spontaneous secretory rate of luteinizing hormone (LH) of the hypophisis is reconstructed from measurements of plasma LH concentrations.     

The automatic model selection and variable kernel width for RBF neural networks

The Orthogonal Least Squares (OLS) algorithm has been extensively used in basis selection for RBF networks, but it is unable to perform model selection automatically because the tolerance ρ must be specified manually. This introduces noise and it is difficult to implement in the parametric complexity of real-time system. Therefore, a generic criterion that detects the optimum number of its basis functions is proposed. In this paper, not only the Bayesian Information Criterion (BIC) method, used for fitness calculation, is incorporated into the basis function selection process of the OLS algorithm for assigning its appropriate number, but also a new method is developed to optimize the widths of the Gaussian functions in order to improve the generalization performance. The augmented algorithm is employed to the Radial Basis Function Neural Networks (RBFNN) for known and unknown noise nonlinear dynamic systems and its performance is compared with the standard OLS; experimental results show that both the efficacy of BIC for fitness calculation and the importance of proper choice of basis function widths are significant.     

Application of radial basis function neural network for differential relaying of a power transformer

Function approximation has been found in many applications. The radial basis function network is one of the approaches which has shown a great promise in this sort of problems because of its faster learning capacity. The application of RBF neural network for differential relaying of power transformer is presented in this paper. Performance of this model is compared with feed-forward neural network (FFNN). The proposed method of power transformer protection is evaluated using simulation performed with EMTP package. The proposed model requires less training time and is more accurate in prediction as compared to FFNN.     

A new structure adaptation algorithm for RBF networks and its application

An adaptation algorithm is developed for radial basis function network (RBFN) in this paper. The RBFN is adapted on-line for both model structure and parameters with measurement data. When the RBFN is used to model a non-linear dynamic system, the structure is adapted to model abrupt change of system operating region, while the weights are adapted to model the incipient time varying parameters. Two new algorithms are proposed for adding new centres while the redundant centres are pruned, which is particularly useful for model-based control. The developed algorithm is evaluated by modelling a numerical example and a chemical reactor rig. The performance is compared with a non-adaptive model.     

Neural networks and the inverse kinematics problem

Inverse kinematics is a fundamental problem in robotics. Past solutions for this problem have been realized through the use of various algebraic or algorithmic procedures. In this paper the use of feedforward neural networks to solve the inverse kinematics problem is examined for three different cases. A closed kinematic linkage is used for mapping input joint angles to output joint angles. A three-degree-of-freedom manipulator in 3D space is used to test mappings from both cartesian and spherical coordinates to manipulator joint coordinates. A majority of the results have average errors which fall below 1% of the robot workspace. The accuracy indicates that neural networks are an alternate method for performing the inverse kinematics estimation, thus introducing the fault-tolerant and high-speed advantages of neural networks to the inverse kinematics problem.This paper also shows the use of a new technique which reduces neural network mapping errors with the use of error compensation networks. The results of the work are put in perspective with a survey of current applications of neural networks in robotics.     

Speech recognition using pulse-coupled neural networks with a radial basis function

We have developed a novel pulse-coupled neural network (PCNN) for speech recognition. One of the advantages of the PCNN is in its biologically based neural dynamic structure using feedback connections. To recall the memorized pattern, a radial basis function (RBF) is incorporated into the proposed PCNN. Simulation results show that the PCNN with a RBF can be useful for phoneme recognition. This work was presented in part at the 7th International Symposium on Artificial Life and Robotics, Oita, Japan, January 16–18, 2002     

基于RBF网络的信息融合在机器人足球中的应用

机器人足球系统是综合性的人工智能研究平台。决策在机器人足球比赛中起着至关重要的作用。通过对机器人足球系统的分析,论证了信息融合应用于机器人足球系统的可行性。针对机器人足球比赛决策中的实际问题,提出了基于径向基函数(RBF)神经网络的信息融合方法,并设计了足球机器人射门实验。实验结果证明该方法有助于提高整个系统决策的准确性。     

基于RBF神经网络的非线性时间序列在线预测

针对非线性非高斯时间序列, 提出观测噪声服从隐马尔可夫模型(HMM)的径向基函数(RBF)神经网络(RBF-HMM)预测模型, 其特点在于模型输入包含误差反馈项、RBF网络隐含层节点数的可变性和观测噪声的隐马尔可夫性; 并采用序列蒙特卡罗(SMC)方法实现基于RBF-HMM模型的时间序列在线预测. 最后采用太阳黑子数平滑月均值数据和CRU国际钢材价格指数月数据进行实证研究, 结果表明该模型的有效性.     

混沌系统的RBF神经网络非线性补偿控制

设计RBF神经网络非线性补偿控制器,提出了混沌系统线性状态反馈的复合控制方法,将可调系统混沌行为镇定到期望目标位置或者变成周期运动.用Lorenz方程作仿真实验,结果证明了该方法的有效性.     

基于RBF 神经网络的单元机组负荷系统建模研究

采用径向基函数(RBF)神经网络进行多变量系统的建模研究。将正规化正交最小二乘(ROLS)算法扩展到多输入多输出系统，建立多变量系统的RBF神经网络模型。对电厂单元机组负荷系统进行建模仿真研究的结果表明，用该方法建立的多变量热工系统的非线性模型是有效的，具有较高的辨识精度和较好的泛化能力。