PCA of 6 axis

Hallo, I have 3-axis accelerometer and 3-axis gyroscope, I am planning to reduce these 6 axis to only one or two significant axis that gives more details than others by using PCA

[William Rose]

@hayder al-omairi,

That sounds interesting. If you want some assistance, please post some sample data and an initial attempt at code (even if it does not run) to do the principal component analysis. Good luck!

[hayder al-omairi]

thank you it's working

Answer 1

[Amey Waghmare]

Hi,

As per my understanding, you want to use Principle Component Analysis (PCA) to reduce the dimensionality of your dataset from 6 to 1 or 2 dimensions.

To perform PCA, you can use MATLAB command ‘pca’, which calculates the principal component coefficients for the dataset. You can also specify the number of components to return by using argument ‘NumComponents’.

Assume that the data is stored in variable ‘X’.

[coeff, score] = pca(X, 'NumComponents', 2);

‘coeffs’ are the principal component coefficients, and ‘score’ is the dataset in reduced dimension as specified by the ‘NumComponents’ argument.

For more information on 'pca' command, you can visit the documentation page: https://in.mathworks.com/help/stats/pca.html

Hope this resolves the issue.