线性映射函数对无损颅内压估计的影响

提出了一种基于截断奇异值分解的线性映射函数颅内压无损估计方法。在基于时间序列的数据挖掘框架基础上,分别推导了基于总体最小二乘法的线性映射函数和基于截断奇异值分解法的线性映射函数,通过实验仿真比较证明:不同的线性映射函数对颅内压的预测确实有较为明显的影响,在所采用的方法中,基于截断奇异值分解法的线性映射函数效果明显优于基于总体最小二乘法的线性映射函数。因此,在该数据挖掘框架中,选择合适的线性映射函数对无损颅内压预测精确性的提高有着非常重要的意义。

改进的非下采样Contourlet变换红外弱小目标检测方法

针对存在复杂背景干扰和噪声的红外图像弱小目标检测问题,提出了一种非下采样Contourlet变换(NSCT)的改进的红外弱小目标检测方法。首先对含弱小目标的红外图像进行预处理,然后利用NSCT进行变换,并利用改进的非线性映射函数和能量交叉融合相结合的方法实现了背景杂波的抑制,最后引入Otsu算法进行阈值分割分离出红外弱小目标。通过与同类弱小目标检测算法的对比实验,验证了该方法的有效性。

支持向量回归的颅内压时间系列无损估计方法

在对时间序列数据挖掘框架进行研究时发现:在利用线性映射函数刻画误差和特征间的关系时,不能获得对颅内压力信号的精确估计。为了提高对颅内压估计的精确性,本文采用支持向量回归构建存在于特征和误差间的非线性映射函数,实验结果表明:基于支持向量回归的非线性映射函数预测效果明显优于先前所采用的线性最小二乘法所构成的线性映射函数策略。

基于巢模板的核空间蚁群聚类算法

为了改进蚁群算法因大量引入随机机制所引发的不稳定性,引入巢模板来改进聚类规则,提出一种基于巢模板的核空间蚁群聚类算法,并与原空间上的聚类算法进行比对。该算法用支持向量机的非线性映射函数把数据样本映射到核空间,再用巢模板记忆蚁群群体特征。核空间上的巢模板蚁群聚类算法能较好地处理特征复杂、类别多的数据集,其聚类结果比较接近真实情况,并且效果明显优于原空间上的聚类算法。

基于改进卷积神经网络轴承故障诊断

卷积神经网络(Convolution Neural Network,CNN)是一种常用的智能故障诊断方法。针对卷积神经网络结构中参数较多,训练时间长,并且sigmoid和ReLU激活函数运用带来梯度消失和均值偏移。基于以上问题提出了一种改进非线性映射函数的卷积神经网络模型。把振动信号转换成二维振动图像表示其故障纹理,在卷积层中加入了两层残差神经元。再运用该方法对凯斯西储大学和帕德尔伯恩大学轴承数据集进行分析,分别达到预测精度99.18%和100%。

一种高噪声低照度图像的隐藏特征修复算法

当前的图像隐藏特征修复算法的特征融合过程为单次迭代,且为根据光照情况建立暗适应函数,导致低照度图像隐藏特征修复结果存在失真问题,图像噪声也偏高。为此,提出一种基于交替优化的低照度图像隐藏特征修复算法。模拟低光照对图像环境的自动应变能力,并根据光照情况设计暗适应函数,对隐藏特征像素点实现边缘拉伸及中值滤波操作,提取处理后的隐藏特征分量数值,建立非线性映射函数,交替优化融合特征信息,实现低照度图像隐藏特征的修复。仿真结果证明,所提方法可以有效提高色彩饱和度,并且不易出现失真、特征丢失以及噪声现象,在最大程度上保证原始图像的自身特征属性,实现合理有效的隐藏特征修复。

DISCRETE BIDIRECTIONAL ASSOCIATIVE MEMORY WITH LEARNING FUNCTION

In this paper we propose a new discrete bidirectional associative memory (DBAM) which is derived from our previous continuous linear bidirectional associative memory (LBAM). The DBAM performs bidirectionally the optimal associative mapping proposed by Kohonen. Like LBAM and NBAM proposed by one of the present authors,the present BAM ensures the guaranteed recall of all stored patterns,and possesses far higher capacity compared with other existing BAMs,and like NBAM, has the strong ability to suppress the noise occurring in the output patterns and therefore reduce largely the spurious patterns. The derivation of DBAM is given and the stability of DBAM is proved. We also derive a learning algorithm for DBAM,which has iterative form and make the network learn new patterns easily. Compared with NBAM the present BAM can be easily implemented by software.

Chinese Fuzzy Ontology Mapping Based on Support Vector Machine

Taking into account that fuzzy ontology mapping has wide application and cannot be dealt with in many fields at present,a Chinese fuzzy ontology model and a method for Chinese fuzzy ontology mapping are proposed.The mapping discovery between two ontologies is achieved by computing the similarity between the concepts of two ontologies.Every concept consists of four features of concept name,property,instance and structure.First,the algorithms of calculating four individual similarities corresponding to the four features are given.Secondly,the similarity vectors consisting of four weighted individual similarities are built,and the weights are the linear function of harmony and reliability.The similarity vector is used to represent the similarity relation between two concepts which belong to different fuzzy ontolgoies.Lastly,Support Vector Machine(SVM) is used to get the mapping concept pairs by the similarity vectors.Experiment results are satisfactory.

Effect of static transmission error on dynamic responses of spiral bevel gears

The effect of static transmission error on nonlinear dynamic response of the spiral bevel gear system combining with time-varying stiffness and backlash was investigated.Firstly,two different control equations of the spiral bevel gear model were adopted,where the static transmission error was expressed in two patterns as predesigned parabolic function and sine function of transmission errors.The dynamic response,bifurcation map,time domain response,phase curve and Poincare map were obtained by applying the explicit Runge-Kutta integration routine with variable-step.A comparative study was carried out and some profound phenomena were detected.The results show that there are many different kinds of tooth rattling phenomena at low speed.With the increase of speed,the system enters into stable motion without any rattling in the region(0.72,1.64),which indicates that the system with predesigned parabolic function of transmission error has preferable capability at high speed.

Weak and strong convergence of an explicit iteration scheme with perturbed mapping for nonexpansive mappings

In this paper, we consider an explicit iteration scheme with perturbed mapping for nonexpansive mappings in real q-uniformly smooth Banach spaces. Some weak and strong convergence theorems for this explicit iteration scheme are established. In particular, necessary and sufficient conditions for strong convergence of this explicit iteration scheme are obtained. At last, some useful corollaries for strong convergence of this explicit iteration scheme are given.

Blow-up of Solution for the Nonlinear Sobolev-Galpern Equation

In this paper,the initial boundary value problems of the nonlinear Sobolev-Galpern equation are studied.The existence,uniqueness of local solution for the problem are obtained by means of a special Green's function and the contraction mapping principle.Finally,the blow-up of solution in finite time under some assumed conditions is proved with the aid of Jensen's inequality.

A unified approach to the weighted Grtzsch and Nitsche problems for mappings of finite distortion

This note deals with the existence and uniqueness of a minimiser of the following Grtzsch-type problem inf f ∈F∫∫_(Q_1)φ(K(z,f))λ(x)dxdyunder some mild conditions,where F denotes the set of all homeomorphims f with finite linear distortion K(z,f)between two rectangles Q_1 and Q_2 taking vertices into vertices,φ is a positive,increasing and convex function,and λ is a positive weight function.A similar problem of Nitsche-type,which concerns the minimiser of some weighted functional for mappings between two annuli,is also discussed.As by-products,our discussion gives a unified approach to some known results in the literature concerning the weighted Grtzsch and Nitsche problems.