Hi,
I’m trying to do a project where I use raw EEG (electroencephalogram) data to perform lie detection. The data comes in the form of two channels, each with a sample rate of 256Hz. Thus, the data takes the form as structured time series data with 2 channels. I was wondering how to implement that in the fast.ai library… It seems like CNNs would help, but I’m not sure how to go about using CNNs on structured time series data. Can anyone help me out?
1 Like
Take a look at https://github.com/fastai/fastai/blob/master/courses/dl1/lesson3-rossman.ipynb
This is example for time series data.
The GitHub link is broken, it would be nice if you share again.
Here you go: https://github.com/fastai/course-v3/blob/master/nbs/dl1/lesson6-rossmann.ipynb
Or here for tabular/time series data in much more detail and fastai v2: https://github.com/fastai/fastbook/blob/master/09_tabular.ipynb
1 Like