HCC: Hierarchical Cluster Coherence Method

In CarolinaEuan/HMClust: HMClust

Hierarchical Cluster Coherence Method

Description

Compute the hierarchical cluster coherence method for a set of time series X.

Usage

HCC(X,Clustfreq=NULL,freq=1)

Arguments

X	Matrix of time series, the series should be located by column.
Clustfreq	Frequency choosen to perform the clustering. If a interval in provide then clustering is performed based on integrated cluster coherence on the correponding frequency band. If NULL then the disimilarity for all frequencies is returned.
freq	Sampling Frequency. Default value is 1.

Details

Let X_1,X_2,...,X_N be the signal for each channel with length T and sampling frequency F_s. The procedure starts with N clusters, one for each individual channel.

1) Estimate the coherence matrix C(\omega) at frequency \omega.

2) Compute the initial dissimilarity matrix at band \Omega_12.

3) Find the two clusters with the lowest dissimilarity and save this value as a charac- teristic.

4) Merge the signals of the two most similar clusters, reduce the number of clusters by one, i.e., ki = ki−1 − 1, and increase i accordingly , i.e., i = i + 1.

5) Compute the dissimilarity between the new cluster and the existing ones.

6) Repeat steps 2-5 until there is only one cluster left.

Value

A HCC object with the following variables:

Diss.Matrix = Initial dissimilarity matrix.

min.value = trayectory of the minimum value.

Groups = list with the groupping structure at each step.

Author(s)

Carolina Euan.

References

Euan, C., Sun, Y. and Ombao, H. (2017) "Coherence-based Time Series Clustering for Brain Connectivity Visualization".

See Also

cutk

CarolinaEuan/HMClust documentation built on Feb. 18, 2024, 10 p.m.