clustering based on correlation coefficient

2 visualizaciones (últimos 30 días)
Alberto Menichetti
Alberto Menichetti el 14 de Feb. de 2017
Hi,
I have a quite big set of timeseries data (about 3000) regarding the same temporal interval. I need to group these timeseries data on different sets based on pearson's correlation cofficient. A timeseries can be part of a specific set if and only the absolute value of his correlation with the others timeseries in the same set is greater than 0.9; in the worst case I will have only one time-series for each set (so a number of sets equal to the number of timeseries).
Unfortunately I don't know the subject, but maybe clustering algorithms could be useful for that problem?
Thank you.

Respuestas (0)

Categorías

Más información sobre Large Files and Big Data en Help Center y File Exchange.

Productos

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by