RBF neural networks for solving the inverse problem of backscattering spectra

This paper investigates a new method to solve the inverse problem of Rutherford backscattering (RBS) data. The inverse problem is to determine the sample structure information from measured spectra, which can be defined as a function approximation problem. We propose using radial basis function (RBF) neural networks to approximate an inverse function. Each RBS spectrum, which may contain up to 128 data points, is compressed by the principal component analysis, so that the dimensionality of input data and complexity of the network are reduced significantly. Our theoretical consideration is tested by numerical experiments with the example of the SiGe thin film sample and corresponding backscattering spectra. A comparison of the RBF method with multilayer perceptrons reveals that the former has better performance in extracting structural information from spectra. Furthermore, the proposed method can handle redundancies properly, which are caused by the constraint of output variables. This study is the first method based on RBF to deal with the inverse RBS data analysis problem.     

一种优化的RBF神经网络模型用于网络流量预测

采用径向基RBF神经网络对网络流量数据的时间序列进行建模与预测。采用传统的学习算法对RBF网络训练时,对网络流量数据容易出现过拟合现象,提出了自适应量子粒子群优化AQPSO算法,用于训练RBF神经网络的基函数中心和宽度,并结合最小二乘法计算网络权值,改善了RBF神经网络的泛化能力。实验结果表明,采用AQPSO算法获得的RBF神经网络模型具有泛化能力强、稳定性良好的特点,在网络流量预测中有一定的实用价值。     

项目教学法在Flash动画设计教学中的应用

该文探讨了如何在高等职业技术教育的FLASH动画设计这门课程中使用项目教学法进行教学的主要方法及在此过程中应该注意的问题。它结合实际教学中的具体实例进行了阐述,提供了对FLASH动画设计这门课程进行项目教学的主要方法和步骤,以及在具体实施中需要解决的问题。     

医学院校中计算机基础教学面临的问题及建议

论述了在医学院校中计算机文化基础教学中存在的一些问题,就如何提高教学效果、培养学生的能力,对大学计算机基础教学模式提出了一些切实可行的探索。从教学对象、教学方式等几个方面给出一些建议,力争提高计算机基础课程的教学质量和教学效果。     

基于主动形状模型的双目识别系统的设计与实现

给出了一种基于统计形状模型的双目识别系统实现方法.该系统根据识别目标在场景中的姿态有一定规律性的特点,用先验的样本信息指导识别的过程,并采用径向对齐约束的方法对摄像头内外参数进行标定,利用图像识别结果中特征点的顺序性完成特征匹配,进而获得目标的三维信息.     

基于自适应小生境递阶遗传算法的RBF均衡器

递阶遗传算法(HGA)一次只能确定一个最优个体。采用小生境递阶遗传算法,依据进化信息自适应调整小生境区域,在均衡数据误比特率最低,隐层中心聚类有效性最佳的基础上,可以从多个进化优解中确定出最佳结构的径向基(RBF)神经网络均衡器。仿真结果验证了算法的有效性和稳定性。     

基于SMITH预估的神经网络再热汽温控制

电厂锅炉的再热汽温是机组安全、经济运行的重要参数之一,必须控制在一定范围内.而电厂再热汽温被控对象是具有大惯性、大滞后,并且常规PID控制难以取得良好的控制效果.针对这一特点,提出了一种RBF--Smith预估控制算法,该算法利用了基于RBF整定的PID控制提高对被控对象参数变化的自适应能力和Smith预估控制能够克服被控对象的大迟延特性,并对RBF--Smith预估控制用Matlab在不同工况下进行仿真试验,仿真结果表明所设计的控制系统的性能较常规PID控制有较大的提高,证明了控制方案的有效性.     

基于K0honen网络和OLS算法的RBFNN中心选择方法

提出了一种优化选择径向基神经网络数据中心的算法,该算法结合了Kohonen网络的模式分类能力,将初步分类结果用作RBFNN的初始数据中心,然后采用OLS算法进行优化,对比仿真实验表明该算法效果比单独使用OLS算法生成的RBFNN性能更好。     

Transient response of Bouc–Wen hysteretic system under random excitation via RBFNN method

Hysteresis normally exhibited by mechanical systems and materials is so prevalent that its response prediction under random excitation has been extensively investigated for decades. Nevertheless, the transient solution of the response, which is crucial for assessing the system’s reliability, is still a challenging topic that requires additional development. To this regard, this work proposes a semi-analytical method using the radial basis function neural network (RBFNN) to attain the transient probability density distribution of the randomly excited Bouc–Wen system. Specifically, the trial solution of the corresponding FPK equation is configured as the RBFNN with undetermined time-varying weight coefficients. By discretizing the time derivative with the Euler difference method, a loss function with time recurrence is derived and minimized to yield the time-varying optimal weight coefficients through the optimization method. Additionally, an optimized sampling strategy is adopted to reduce the burden of calculation. Finally, the Bouc–Wen hysteretic systems with softening and hardening nonlinearity are considered to investigate the performance of the adopted technique. The numerical results have shown that the evaluation process of the probability density functions(PDFs) can be captured well with sufficient accuracy and efficiency. The proposed efficient sampling technique can provide considerable efficiency improvement for the medium dimension system. The work of the paper will contribute to the reliability design of hysteretic structures in engineering.     

独立学院本科计算机应用基础课程教改研究

为了提高教育质量,独立学院必须从自身的条件出发,进行深入的教学改革。针对计算机应用基础课程的特点,文章提出以社会需求为导向,改革教学内容;从实际出发,改进教学方法;发挥网络优势,构建立体化教学环境;加强教师队伍建设,为课程改革夯实基础。经过实践,这种做法取得了优良的效果。