特征参数

  • 网络Parameters;Feature Parameters;FeatureParameters;mfcc
特征参数特征参数
  1. 用触摸屏显示阵列的I-V曲线及相关特征参数,并设计软件按钮以实现仪器的操作。

    IV curves and related parameters of features is displayed in touch screen , and the operation of instruments is achieved with software button .

  2. 采用声发射技术,借助三点弯曲试验,对含有初始缺陷的蜂窝夹芯试件进行破坏及损伤分析,建立了三种不同载荷工况下,AE特征参数随加载时间、位置等变化规律。

    Using acoustic emission technique , with the three-point bending test , the damage analysis of honeycomb sandwich with the initial defects was monitored . Variation rules of AE parameters with the load time , different location under three different load conditions were developed .

  3. 湿地松优良半同胞家系光和CO2响应曲线特征参数的变异规律

    The variance rule of character parameters responding to light and CO_2 of slash pine 's half-sib

  4. 重位点阵特征参数TEM测定新方法

    New Method on TEM Determination of CSL Parameters

  5. 基于特征参数化的商品化CAPP系统

    Research on Parameterized Features Based Commercial CAPP System

  6. 选用反向传播神经网络模型(BP网络),网络识别所需要的特征参数能够反映木材缺陷的全部特征。

    Back propagation networks was used to recognize all the characteristic parameters , which can reflect all the characteristics of wood defects .

  7. 特征参数B是无机高分子絮凝剂的重要质量指标,它直接决定着絮凝剂产品的化学结构形态和特性。

    The characteristic parameter B is an important quality index on the inorganic macromolecule flocculant , and it will determine the chemical configuration and speciality of the coagulator .

  8. SF6气体中放电特征参数及机理

    Discharge Characteristic Parameters and Mechanism in SF _ 6 Gas

  9. DEM空间分辨率和重取样方式对流域特征参数的提取会产生重要影响。

    The DEM spatial resolution and sampling method have a great impact on the watershed features .

  10. 试图用BP神经网络建立轴承寿命预测模型,并在该模型上进行多特征参数和多步预测方法的研究。

    The bearing life forecast model based on BP network is researched . The multi step and multi feature forecasts can be realized concurrently .

  11. ESD特征参数与受试设备耦合电压关系实验研究

    Experimental Investigation on the Correlation Between ESD Parameters and Coupling Voltage of Electronic Equipment

  12. 得到的特征参数最后通过动态时间规整(DTW)的模式识别方法进行识别。

    The character parameters than be recognized by DTW .

  13. 利用时域反射技术(TimeDomainReflectometry,TDR),由测量得到的时域反射信号,可以重构出非均匀传输线的一些特征参数。

    With time domain reflectometry technique , characteristic parameters of a nonuniform transmission line can be recovered from the corresponding reflection signal measured in time domain .

  14. 采用基于动态规划方法的动态时间归正技术DTW(DynamicTimewarping),可成功解决语音信号特征参数序列比较时时长不等的问题。

    The dynamic time warping ( DTW ) technology based on the dynamic programming can solve the problem that the characteristic parameters of speech signal are of different lengths in each other .

  15. 同时,依据实验条件,选择Mel参数作为识别特征参数。

    At the same time , according to the experimental conditions , choose Mel parameters as recognition characteristic parameters .

  16. 结合分形理论,给出了定量计算混凝土裂缝的面积、分形维数、长度、宽度等特征参数的算法,并采用MATLAB编写计算混凝土裂缝特征参数的应用程序。

    An algorithm which was derived from fractal theory was proposed and programmed with MATLAB to calculate the characteristic parameters of concrete cracks , such as area , fractal dimension , length and width .

  17. 依据ABC模型的特征参数,将生物单种群的群体划分为九种类型,并以水稻不同处理条件下的茎蘖群体消长为例,进行了演示。

    Then , according to characteristic parameters of ABC-model , authors classified the populations into nine types , and gave examples of different tiller formations of rice for illustrations .

  18. 应用BP神经网络建立全局图像飞溅特征参数与焊缝宽度之间的数学模型以及新飞溅特征参数与焊缝宽度之间的数学模型。

    The mathematical model of the global image spatters characteristics parameters and the weld bead width and the mathematical model of new spatters characteristics parameters and the weld bead width were established by BP neural network .

  19. 该文提出了一种基于复数帧段输入HMM的语音识别方法,它采用相继的复数帧组成的特征参数向量作为语音识别HMM的输入,能有效地在语音识别HMM中引入帧间相关信息。

    This paper applies segmental unit into HMM for speech recognition . In this model , several successive frames are combined and treated as an input vector .

  20. 实际应用表明,利用计算机技术,可以比常规的手工方式更迅速、更准确地求得变程a、矿块效应系数C0及基台值C三个变异特征参数。

    Among the models the spherical one is widely used in practice . Three variation parameters ( range a , nugget effect C0 and sill C ) can be determined much quicker and more accurately by computer than by the conventional manual way .

  21. 通过矢量散射理论中的微扰法得到不同极化的角散射分布(Angular-ResolvedScattering,即ARS)和总体积分(TotalIntegratedScattering即TIS),利用TIS法计算粗糙表面的特征参数。

    Angular-Resolved Scattering ang Total Integrated Scattering is derived by using the perturbation method of vector scattering theories . Character parameter of rough surfaces is calculated by using TIS .

  22. 实验结果表明:改进后的特征参数比传统Mel频标倒谱系数具有更高的识别率和更好的抗噪性能。

    The experimental results show that the improved feature parameters can achieve higher recognition rate and better anti-noisy performance than the traditional feature parameters .

  23. 本文提出了利用语音短时特征参数和相应距离量度公式来构造隐Markov模型(HMM)观察值概密函数的一种方法。

    The short-time characteristic parameters and the corresponding distance measure formula of speech have been used to construct the density function for observed values of the Hidden Markov Model ( HMM ) .

  24. 分类识别中用模糊统计的方法对大量的样本车型特征参数处理后,构造了隶属函数,最后采用了D-S证据理论对车型进行分类。

    Fuzzy statistical algorithm is adopted to construct membership function after handling a great quantity of vehicle type data , and finally vehicle type is classified by using D-S method .

  25. 为了进一步对滚动轴承的状态和故障类型进行分类,再从若干个包含主要故障信息的IMF分量中提取能量特征参数作为神经网络的输入参数来识别滚动轴承的故障类型。

    To identify roller bearing fault patterns , energy feature parameters extracted from a number of IMFs which contained main fault informations can be served as input parameters of the neural network to identify fault patterns .

  26. 利用Cooper等人推导的井-含水层系统放大因子表达式,分析了井-含水层系统的特征参数与前驱波响应能力之间的关系。

    The relationship between characteristic parameters of well-aquifer system and responding ability to precursors is analyzed by the expression of amplification factor of well-aquifer system induced by Cooper et al .

  27. 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 .

  28. 我们对桥梁故障诊断进行了初步研究,以所检测的参数作为特征参数运用BP神经网络对桥梁的综合质量及其发展趋势作出了初步判断及预测。

    We studied the intelligent fault diagnoses for a bridge , and use the parameter that examined by the instrument as characteristic parameter , then obtain the synthesis quality and the estimate of future synthesis quality of a bridge by BP artificial neural network .

  29. 其一是对聚苯乙烯泡沫塑料(EPS)保温板以及天然路基土层、路堤填料进行了室内试验分析,结合国内外现在的有关科研成果,综合确定其各项特征参数;

    First , I have carried out laboratory text analysis on EPS , roadbed soil layer and embankment packing , combining with present relevant domestic and foreign scientific research achievement , I defined every characteristic parameter .

  30. 孔隙测井特征参数(包括声波时差比K4、密度比K5、中子相对孔隙度K6);

    Porosity parameters , ratio of acoustic wave time difference K4 , ratio of density K5 , neutron relative porosity K6 ;