I am doing K means on multidimensional data, how should my plot of Minimum Distortion vs K look like?

1 次查看（过去 30 天）
Tim Robbins
Tim Robbins 2015-10-14
编辑： Tim Robbins 2015-10-14
I'm using 5 x 10000 or 5 x N to represent 5D data. Each 5 x 1 sub-matrice represents one five dimensional point, so 5 x N would represent N 5D points.
I did it and now want to check the result. How should a plot of the minimum distortion (Error which converges for that value of K) vs various values of K look like for 5D data?
I did the same for 1D data and the results look something like this.
PS: I'm not using the inbuilt kmeans() to do this, but rather i'm coding it up manually hence I need to check if my logic is correct.
If this is how it looks like for 1D data, how should it look like for 5D data?

请先登录，再回答此问题。

回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Cluster Analysis and Anomaly Detection 的更多信息

标签

Community Treasure Hunt

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

Start Hunting!

Translated by