识别问题

本文试图解决角度偏离虹膜的识别问题。

We are trying to solve the identification problem of off-angle iris .

尤其较好地解决了高阻抗非线性故障的识别问题。

Especially it solves the identification problem of high impedance fault well .

研究探讨了空中目标作战企图的识别问题

The problem of inferring air target combat intention is discussed .

BP网络参数对模式识别问题影响的研究

The Study of Parameters of BP Network for Pattern Recognition

将该遗传算法与人工神经网络（ANN：Artificialneuralnetwork）技术相结合，应用于油气层的识别问题中。

The proposed method is named as Fitness-Distance Selection Mechanism Based GA and which is integrated with ANN ( Artificial Neural Network ) for the identification of oil gas layer .

该检测算法的核心是将检测问题转化为模式识别问题，首先对接收信号建立AR模型并提取AR模型系数作为特征向量，然后利用人工神经网络对信号进行检测。

The characteristic is extracted by the AR model coefficient and then be employed to detect the target signal with ANN .

研究了亮斑的成因及CCD摄像机特性对彩色图象成像的影响，较好地解决了亮斑的检测和识别问题；

The formation of the highlight areas and the influence of the characters of CCD camera to the formatted color image are studied here .

针对数字信号调制模式识别问题，提出了运用高阶累积量和二叉树支持向量机（SVM）进行自动识别的算法。

Applying high order cumulants and support vector machines ( SVM ), an algorithm is proposed for automatic recognition of digital communication signals .

讨论了PC主机与多台不同类型的从机进行多机通信的通信原理以及通信协议，解决了不同类型从机的地址识别问题。

The principle and protocol of the multicomputer communication between the PC master and the different slaves are discussed , and it solves the address identification between different slaves .

本文以模式识别问题为背景，介绍VC理论的主要内容及支撑矢量机方法。

This paper is a tutorial in which the basic concepts of VC theory and the methodology of SVMs as applied to pattern recognition problems are reviewed .

集合识别问题的D序列和UIO序列的一种推导方法

An Approach to Deriving D-Sequence and UIO-Sequence in the SET-ID Problems

图像检测中对2D图像的长度、面积测量，以及工件的某些指标的计算，常常会遇到顶点识别问题。

We often fall across a problem of vertex recognition in the process of image measure , for example , to detect length of 2D image , area and some workpiece index .

提出了散布矩阵的一种简洁表示方法，这一简洁表示方法适合于一切使用Fisher鉴别准则的模式识别问题。

A concise representation method of between-class scatter matrix and population scatter matrix is proposed , which suits for all the applications of pattern recognition using Fisher criteria .

提出了一种基于模糊c－线性簇聚类算法的Kohonen特征映射算法.这种特征映射克服了Kohonen网存在的一些缺点.对某些识别问题，其计算效率非常高。

A new fuzzy Kohonen feature mapping algorithm ( FLKCN ) based on the fuzzy c linear clustering algorithm is proposed . It can overcome some disadvantages of the original Kohonen network .

试验仿真结果表明，HHT方法能克服部分噪声的影响。第二，依据提取出的特征参数作为特征向量，研究人工神经元网络（Artificialneuralnetwork，ANN）单信号调制模式识别问题。

The results of simulation show that the HHT method can overcome some of noises . Secondly , the parameters extracted as the feature vector to recognize the single signal modulation pattern using ANN ( Artificial Neural Network ) is described in the thesis .

针对分布式多传感器环境下的目标识别问题，提出了一种基于加权D-S证据理论组合规则的决策融合方法。

Dempster-Shafer ( D-S ) evidence theory has been widely used in data fusion systems . A method based on the weighted D-S evidence theory was proposed for target recognition in the distributed multi-sensor system .

之所以选择BP神经网络作为融合技术是因为经简单算子处理后的边缘灰度值与图像的理想边缘灰度值之间的关系是非线性的，而BP神经网络正是善于处理这种非线性的识别问题。

The reason that we selected BP neural net as the fusion technology is that the relation between simple operators ' result of edge gray level and the image 's true edge gray level is nonlinear , while BP neural net is good at solving the nonlinear identification problem .

阶递归最小二乘（LS）算法适用于观察样本个数固定且模型阶数未知时FIR或AR参数的最佳估计和识别问题中。

The recursive in order least-squares ( LS ) algorithms can be applied to estimation and identification of FIR or AR system parameters where a fixed set of input signal samples is available and the order of the model is un - known .

本文将逆虚拟激励法（IPEM）用于求解平稳随机振动的荷载谱识别问题。

In this paper , the inverse pseudo excitation method is used to deal with loading spectra identification problem of stationary random vibration .

PDF凭借着它的种种优势，克服了电子文件共享过程中经常遇到的识别问题，使用户可以在网上自由地浏览文件和方便地交换文件，它成为进行现代电子文档分发的理想格式。

With its many advantages , PDF overcomes the identification problems in the process of electronic files sharing and allows the user to browse tiles freely and exchange files easily online . So it has been the ideal file format for file distribution .

深入研究了模拟调制信号的调制制式的识别问题，成功识别了AM、DSB、SSB和FM四种模拟调制信号。

This dissertation performed the following work based on others ' work : ( 1 ) Studied the modulation identification problem of analogue modulated signals in depth , and successfully identified AM , DSB , SSB , and FM signals .

在物理、生物、医学、地质和工程技术领域都存在着大量的不适定问题，比如参数识别问题、非线性不适定Hammerstein积分方程以及求解第一类Fredholm积分方程等。

There are a lot of ill-posed problems in physics , biology , medicine , geology and engineering technology . For example , parameter identification problems , nonlinear ill-posed Hammerstein integral equation , the solution for the first kind of Fredholm integral equation and so on .

为解决被动声呐目标的特征提取与识别问题，通过对被动声呐目标噪声频谱特性的深入分析，给出了一种基于Welch谱估计的目标特征提取方法。

In order to solve the problem of the underwater target feature extraction and recognition , this paper analyzed the frequency spectrum signature of the passive sonar target noise , and proposed a kind of method to extract the object signature based on Welch power spectrum density estimation .

结构损伤识别问题是力学反问题，可作为一个优化问题来处理。

Structural damage identification can be treated as an optimization problem .

非特定人手语识别问题中的合成数据驱动方法

Synthesized Data Driving : An Approach Toward Signer-Independent Sign Language Recognition

真核基因受体位点识别问题是生物信息学中的重要问题之一。

Recognition of acceptor sites is one of important subjects of bioinformatics .

非线性最优化方法在振动系统模态参数识别问题中的应用

Application of Nonlinear Optimization on Identification of Model Parameters of Vibration System

警报和系统概况指示板，可以快速地识别问题。

Alert and system overview dashboards to quickly identify problems .

本研究课题的主要目的旨在解决金融汉字的自动识别问题。

This paper focuses on the problem of auto-recognition for financial characters .

实验表明这种方法能够有效地解决开曲线的形状识别问题。

Experiments shows it is an effective approach to recognizing open curves .