纳税人诚信的判别分析研究

纳税评估工作的核心是判别纳税人的诚信水平,为了弥补现有技术解决手段的缺乏,在建立科学的纳税评估指标体系基础上,应用多元统计判别分析方法,建立纳税人诚信判别函数,并收集实际数据作实证研究,对模型进行参数估计和预测,证实了该判别分析是识别纳税人诚信的有力工具。     

一类基于谱方法的强化学习混合迁移算法

在状态空间比例放大的迁移任务中, 原型值函数方法只能有效迁移较小特征值对应的基函数, 用于目标任务的值函数逼近时会使部分状态的值函数出现错误. 针对该问题, 利用拉普拉斯特征映射能保持状态空间局部拓扑结构不变的特点, 对基于谱图理论的层次分解技术进行了改进, 提出一种基函数与子任务最优策略相结合的混合迁移方法. 首先, 在源任务中利用谱方法求取基函数, 再采用线性插值技术将其扩展为目标任务的基函数; 然后, 用插值得到的次级基函数(目标任务的近似Fiedler特征向量)实现任务分解, 并借助改进的层次分解技术求取相关子任务的最优策略; 最后, 将扩展的基函数和获取的子任务策略一起用于目标任务学习中. 所提的混合迁移方法可直接确定目标任务部分状态空间的最优策略, 减少了值函数逼近所需的最少基函数数目, 降低了策略迭代次数, 适用于状态空间比例放大且具有层次结构的迁移任务. 格子世界的仿真结果验证了新方法的有效性.     

Cloud basis function neural network: A modified RBF network architecture for holistic facial expression recognition

The paper presents novel modifications to radial basis functions (RBFs) and a neural network based classifier for holistic recognition of the six universal facial expressions from static images. The new basis functions, called cloud basis functions (CBFs) use a different feature weighting, derived to emphasize features relevant to class discrimination. Further, these basis functions are designed to have multiple boundary segments, rather than a single boundary as for RBFs. These new enhancements to the basis functions along with a suitable training algorithm allow the neural network to better learn the specific properties of the problem domain. The proposed classifiers have demonstrated superior performance compared to conventional RBF neural networks as well as several other types of holistic techniques used in conjunction with RBF neural networks. The CBF neural network based classifier yielded an accuracy of 96.1%, compared to 86.6%, the best accuracy obtained from all other conventional RBF neural network based classification schemes tested using the same database.     

Radial basis functions as surrogate models with a priori bias in comparison with a posteriori bias

In order to obtain a robust performance, the established approach when using radial basis function networks (RBF) as metamodels is to add a posteriori bias which is defined by extra orthogonality constraints. We mean that this is not needed, instead the bias can simply be set a priori by using the normal equation, i.e. the bias becomes the corresponding regression model. In this paper we demonstrate that the performance of our suggested approach with a priori bias is in general as good as, or even for many test examples better than, the performance of RBF with a posteriori bias. Using our approach, it is clear that the global response is modelled with the bias and that the details are captured with radial basis functions. The accuracy of the two approaches are investigated by using multiple test functions with different degrees of dimensionality. Furthermore, several modeling criteria, such as the type of radial basis functions used in the RBFs, dimension of the test functions, sampling techniques and size of samples, are considered to study their affect on the performance of the approaches. The power of RBF with a priori bias for surrogate based design optimization is also demonstrated by solving an established engineering benchmark of a welded beam and another benchmark for different sampling sets generated by successive screening, random, Latin hypercube and Hammersley sampling, respectively. The results obtained by evaluation of the performance metrics, the modeling criteria and the presented optimal solutions, demonstrate promising potentials of our RBF with a priori bias, in addition to the simplicity and straight-forward use of the approach.     

Two classes linear discrimination A min-max approach

In this paper we propose a new dichotomic linear discrimination algorithm based on a criterion recursively defined from the min and max functions. This criterion allows us, using a gradient algorithm, to find two hyperplanes which split two classes in an optimal way. We give two examples of the possibilities of the method.     

Non-linear systems identification using radial basis functions

This paper investigates the identification of discrete-time non-linear systems using radial basis functions. A forward regression algorithm based on an orthogonal decomposition of the regression matrix is employed to select a suitable set of radial basis function centers from a large number of possible candidates and this provides, for the first time, fully automatic selection procedure for identifying parsimonious radial basis function models of structure-unknown non-linear systems. The relationship between neural networks and radial basis functions is discussed and the application of the algorithms to real data is included to demonstrate the effectiveness of this approach.     

修正指数曲线在电力负荷预测中的应用

在现有文献研究的基础上，对修正指数曲线预测法作了进一步研究，给出了修正指数曲线参数估计的一种新方法。该方法将最优化方法与回归方法结合在一起，利用最优化理论中的区间搜索和一维搜索得到一系列 值，利用回归方法可求得与其相对应的一系列a和b的值，当 取最优 时，a和b 便得到最优值 和 。经示例计算表明，这种改进的预测方法具有较高的精度。     

An adaptive fuzzy model using orthonormal basis functions based on multifractal characteristics applied to network traffic control

In this paper, we present an adaptive predictive orthonormal basis functions (OBF)-fuzzy model that considers the multifractal behavior of network traffic flows. To this end, we model the traffic flows using orthonormal basis functions obtained through multifractal analysis. We insert the orthonormal basis functions into a fuzzy model trained with an adaptive clustering algorithm. Further, we propose a predictive flow control scheme for broadband networks. Also, using the fuzzy model parameters, we derive an expression for the optimal traffic source rate. Comparisons to other predictive control schemes prove the efficiency of the proposed adaptive OBF-fuzzy based control and training algorithm.     

Test Function-based Design of Robust Systems for Nonparametric Detection and Discrimination of Information Signals in White Gaussian Noise

Methods of structural and structural-parametric design of complex nonlinear systems were developed on the basis of the method of test functions using the robust statistics and the Fokker-Plank-Kolmogorov equation. Systems of this kind that are often encountered in various control systems are intended for signal processing under nonparametric uncertainty in the problems of detection and discrimination in white Gaussian noise.     

Optimal control of linear time-varying systems via piecewise-linear polynomial functions

A linear time-varying optimal control system with a quadratic performance index is solved by using piecewise-linear polynomial functions. Only a small number of basis functions are needed to produce a satisfactory result, and the outcome is much better than the solutions obtained by using Walsh functions, block-pulse functions or Taylor polynomial series. Owing to the available recursive formula, the computational work is convenient and straightforward.