现提出一种基于BP神经网络的线性预测系数的求解方法。
In this paper, a method of the calculation of LPC coefficients is proposed by use of BP neural network.
LSP参数可以通过求解一个与线性预测系数(LPC)相关的非线性N阶方程得到。
LSP parameters can be obtained by solving an N-order non-linear equation relating to the linear predictive coding (LPC) coefficients.
计算结果表明，运用预测神经元方法所得到的线性预测系数，精度明显高于传统的杜宾算法和格型算法。
The calculation results indicate that the precision of method based on predictive neuron model is evidently higher than that of conventional Durbin algorithm and lattice algorithm.
本文提出一种基于自适应预测的无损压缩方法，该方法利用神经网络模型自学习的能力，自适应的调整预测器的预测系数。
In this paper, a lossless compression method, based on adaptive prediction, is presented. This method USES neural network model to modify the prediction weight.
本文应用全极点模型，提取语音信号的线性预测系数，并推导出其倒谱系数，获得线性预测倒谱差分，用以描述说话人声道的动态变化。
In this paper, we use full pole model to obtain speech signal LPC, then deduce it's LPCC, and we use the LPCC difference to describe speaker's track dynamic movement.
通过应用全极点模型，提取语音信号的线性预测系数，并推导出其倒谱系数，获得线性预测倒谱差分，用以描述说话人声道的动态变化。
By using full pole model, we obtained speech signal LPC, then deduced it's LPCC, and we used the LPCC difference to describe speaker's track dynamic movement.
设计完成对复合材料的热膨胀系数的计算和预测功能。
Designed to complete the composite coefficient of thermal expansion of the calculation and prediction functions.
提出了利用计算流体力学(CFD)软件(FLUENT)进行涡轮流量传感器仪表系数预测的方法。
The method for prediction the meter factor of the turbine flow meter by the computational fluid dynamics (CFD) software package (FLUENT) is put forward.
结果中学教师自我原因不确定感对其状态焦虑和特质焦虑都有着显著的预测作用，决定系数分别为8.1%和13.0%。
Results Causal-uncertainty of middle school teachers had apparent prediction function to their state and trait anxiety, and the decisive coefficients were 8.1% and 13.0% respectively.
一步相关系数对预测精度的影响不大。
One step self-correlation coefficient has little influence on predicting accuracy.
氧传质理论因存在不确定的参数而不能用来预测河流复氧系数。
The oxygen transfer theory can't be used to predict the reaeration coefficient of the rivers due to some undetermined parameters.
在多变量逻辑回归模型中，开发基于回归系数预测程序的一个简单的临床评分体系。
A simple clinical scoring system was developed on the basis of regression coefficients of predictors in a multivariable logistic regression model.
这里的液流系数是预测值。因此这些数据只是大致的数据，不能用作高流量临界值或压降估计值。
The Fluid Flow factors contained herein are calculated values. They are therefore approximations and cannot be used for highly critical flow or pressure drop calculations.
采用EWMA模型预测动态变化的方差-协方差矩阵，从实证的角度得到更精准的动态迁移相关系数矩阵。
Using EWMA to forecast the portfolio's dynamic transferred variance-covariance matrix, we can get more reasonable and precise dynamic transferred coefficient matrix.
用该方法对不同降雨条件下每种下垫面的径流系数进行了预测，并与传统方法进行了比较。
The runoff coefficient of every underlying surface was forecasted in different rainfall conditions by ANN models and compared with conventional method as well.
并利用测量数据，比较和分析国外三个地面散射系数预测模型的有效性和适用性。
Using this data, the availability and suitability of three predicted models for foreign terrain scattering coefficient are compared and analyzed.
此模型可以对渗透液中d -色氨酸的浓度和分离系数进行较准确的预测。
The model could well predict the concentration of D-tryptophan in the permeated solution and separation factor.
由我们的方法预测的后向散射系数和实验数据的良好吻合，证明了其有效性。
The effectiveness of this proposed method is validated by good agreement between the predicted backscattering coefficients and measurement data.
研究了有关布朗单一参数指数平滑经济预测模型的系数的估计问题，整理并给出了比较完整的证明。
This paper analysized the estimation problem on coefficient of Brown single parameter index smooth economic prediction model followed by giving a complete attestation.
并将优化后的指数平滑系数在我国煤炭产量的预测中得以验证。
The coefficient of exponential smoothing has been proved in the prediction of the coal output in our country.
氧传输理论因存在不确定的参数而不能用来预测河流复氧系数。
The oxygen transfer theory cannot be used to predict the reaeration coefficient in rivers due to some undetermined parameters.
其研究的核心的问题就是如何求出组合预测加权平均系数。
The key problem to be solved is how to obtain weighted averaging coefficients of combination forecasting.
最大熵反褶积是在地震子波为最小相位条件下进行的，其向前预测误差就等于反射系数序列。
The maximum entropy deconvolution is performed under the premise that seismic wavelet is of minimum phase, so the forward prediction error is equivalent to reflection coefficient series.
这种组合预测方法根据以往的全部历史数据，利用数值计算的手段决定组合系数函数中的参数，于是组合系数随时间的推移而变化。
Using all the historical data, this method can decide the parameters of the combinational coefficient function, so that the combinational coefficient varies as the time goes.
应用最优组合预测方法的关键在于怎样确定组合权系数。
The crux of applying the optimal combined forecasting method is to determine the combined weight coefficients.
利用蛋白质中氨基酸组分，通过计算离散增量和离散有限系数预测蛋白质的亚细胞定位。
By use of proteins amino acid composition, the subcellular location of a protein can be predicted by calculating increment of diversity and finite coefficient of diversity.
本文在原有定性分析方法的基础上，提出基于年径流时间序列主周期小波系数加权求和预测周期成分的年径流预测模型。
Based on the primary qualitative method, we propose an annual runoff prediction model using weighted sum of wavelet coefficients of major periods to predict the periodic components.
最后，本文提出用BP神经网络预测混凝土抗冻耐久性系数的方法。
Finally, a new approach (BP Network) to predicting the durability factor of concrete has been proposed here.
混凝土的氯离子扩散系数是预测混凝土中钢筋锈蚀及结构耐久性的重要参数。
The chloride diffusion coefficient of a concrete is an important parameter in predicting the corrosion of steel in a concrete and the durability of the structures.
为此，本研究利用地震反演方法对本区的储层发育情况进行了预测，并利用PCD压力预测方法对地层压力系数进行了预测。
Therefore, this paper focused on the prediction of reservoirs by using seismic inversion and the prognostication of formation pressure by applying PCD method.
应用推荐