Errors are an option…

Mandatory Tasks

2

Basic:

image0.png

Scaled by divison max() for every individual frequency band:

image1.png

3

without preparing the data via /= std:

image2.png

with equalizing the power via /= std (obviously not the best idea in this case):

image3.png

4

Phase Coherence

image4.png

image5.png

Spectral Coherence

image6.png

image7.png

5

Phase Coherence

image10.png

image11.png

Spectral Coherence

image8.png

image9.png

6

Don’t normalize the time series!

i.e. don’t do something like this:

data -= data.mean(axis=1, keepdims=True)
data /= data.std(axis=1, keepdims=True)

Otherwise you will not classify anything.

image12.png

Scaled by divison max() for every individual frequency band (Bad times happen):

image13.png

7

Don’t normalize the time series!

i.e. don’t do something like this:

data -= data.mean(axis=1, keepdims=True)
data /= data.std(axis=1, keepdims=True)

Otherwise you will not classify anything.

image14.png

The source code is Open Source and can be found on GitHub.