Clustering time sequences with different lengths using the matlab code
显示 更早的评论
Please allow me to solve this problem with your expertise, sir/ma’am.
I am trying to cluster time sequences with different lengths using the matlab code in https://www.mathworks.com/matlabcentral/fileexchange/54358-jsantarc-dynamic-time-alignment-k-means-kernel-clustering-for-time-sequence-clustering
When I am running the toy data it provids with the selection of 2 clusters, it is working fine.
However, when I increase the number of cluster (like 6, 7 or 8), it takes very very long (many hours).
I cannot use this for my research if it takes this long to cluster samll amount of data like this.
(I have more than 10,000 samples to compute)
Is there a way to improve the computing speed of this code?
If you can show me an alternertive way (other way to cluster), that would be very much appreciated, too.
Thanks a million for sharing your expertise.
Best wishes,
回答（0 个）
类别
在 帮助中心 和 File Exchange 中查找有关 Statistics and Machine Learning Toolbox 的更多信息
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!
Translated by 
