1) predicting coefficient
预测系数
1.
For designing predicting coefficients of SGWT, the sum of squared detail components are taken as an objective function, and the coefficients are solved by least square method with constraint of vanishing moment number for predicting.
在设计预测系数时,以小波分解的细节信号的平方和最小为目标函数,使预测满足一定的消失矩,通过最小二乘法确定预测系数,使预测系数能够反映分析数据的特征。
3) LPC
线性预测系数
1.
An identification method based on HMM was established to separate mixing acoustic targets through extracting LPC characteristics.
建立已知声目标的HMM,实现混叠声目标盲分离,提取的线性预测系数作为声目标识别参数,通过K均值聚类得到训练和识别特征向量,通过Viterbi解码判断声目标的类别。
2.
With ICA to realize the blind separation from mixing vibration targets,An identification method based on GMM is proposed through extracting LPC characteristic.
建立已知振动目标的GMM,然后实现混叠振动目标自适应盲源分离,提取了振动目标的线性预测系数作为目标识别的参数,产生了训练和识别所用的特征向量。
3.
A recognition method based on HMM and K-means cluster is proposed through extracting LPC characteristic from acoustic target.
在该方法中,建立声信号的HMM,提取了声信号的线性预测系数(LPC)作为目标识别的参数,用K-均值算法对参数进行聚类,产生了训练和识别所用的特征向量。
4) Prediction of function express
预测函数关系
6) predicting coefficient of permeability
渗透系数预测
补充资料：发育进度预测法(见发生期预测)
发育进度预测法(见发生期预测)
发育进度预测法见发生期预测。
说明：补充资料仅用于学习参考，请勿用于其它任何用途。
参考词条