Dear Ludovica,
Thanks for your reply, I really appreciate it!
Based on your advice I will increase the threshold (>20) and see what happens. If I still wouldn't get any reliable results I will attempt and train FIX specifically on my data.
However, personally hand-labeling components into good and bad ones can be tricky for somebody with very little experience in recognising true and false functional components. Do you have any tips or advice on how one could best recognise/identify bad components in the data by visually checking the data and the components.
Thanks in advance!
Regards,
Mauricio
|