搜索资源列表
chafen
- 差分法比较曲线的形状相似度,接着筛选出有用曲线求相位差,给了原始数据,可以直接运行-Difference Method for curve shape similarity, then filter out the demand curve useful in phase, to the raw data, can run
Blind-identification
- 利用现代谱估计中的AR 模型求取仿真噪声信号和真实噪声信号的模型参数,然后利用这些参数求得信号的功率谱图,通过功率谱图定性地描述主噪声源和次噪声源。在利用信号功率谱图定性描述噪声源后,进一步地利用曲线相似度和曲线关联度定量的识别主噪声源和次噪声源-Use of modern spectral estimation of AR model to strike a realistic simulation of the noise signal and noise model parameters,
frechet
- 计算两条曲线的相似度,作为判断两条曲线相似度的依据-to calculate the frechet distance of two curves
sim(Similarity_Analysis)
- 这个程序可以算某个特征时间序列的影响因素的相关性。具体是通过比较两个时间序列的曲线相似度实现的。运行该函数前要先输入特征时间序列和影响序列。-This program can be considered as a characteristic time series of the correlation between the factors. Specifically, by comparing the curve similarity of two time series. Before r
sim(xiangsidu)
- 求算两个时间序列的曲线相似度,相似度的绝对值越接近于1,说明两者的相似度越高。-Calculate the curve of two time series similarity, the similarity of the absolute value is closer to 1, the higher the similarity of the two.
谱聚类11
- 进一步采用基于距离和曲线形态的双尺度相似性度量谱聚类算法进行聚类处理,通过求n 个二次规划问题,就可以求得相似度矩阵W,降低了谱聚类算法对参数的敏感性,使算法更稳定(Furthermore, we use the two-scale similarity measure spectrum clustering algorithm based on distance and curve shape to carry out clustering. By finding n quadratic pr