RuntimeError: No clean segment found. Please consider updating your rejection thresholds.

šŸ’¬ Support & Discussions
1

Hi, Iā€™m writing code to apply ICA for EEG data , but i got this error ( RuntimeError: No clean segment found. Please consider updating your rejection thresholds.)

this is my code

import numpy as np
import pandas as pd
import mne
from mne.preprocessing import (ICA, create_eog_epochs, create_ecg_epochs,
                               corrmap)
import scipy
from mne.preprocessing.ica import corrmap


path = 'C:/Users/Sar/Desktop/Unicorn config/UnicornHybridBlack-master/UnicornHybridBlack-master/Python Collect/Gentask/Engine/'
data = pd.read_csv(path + 'test2.csv',
                   skiprows=0, usecols=[*range(0, 8)])*1e-6
ch_names = ['EEG1','EEG2','EEG3','EEG4','EEG5','EEG6','EEG7','EEG8']



sfreq = 250
info = mne.create_info(ch_names = ch_names, sfreq = sfreq,ch_types='eeg')
raw = mne.io.RawArray(data.transpose() , info)


method = 'fastica'

n_components = 7 
reject = dict(eeg=40e-6, grad=5000e-13)


start, stop = [0, raw.times[-1]]
intervals = np.linspace(start, stop, 4, dtype=np.float)
icas_from_other_data = list()
raw.pick_types(meg=False, eeg=True)  # take only MEG channels
for ii, start in enumerate(intervals):
    if ii + 1 < len(intervals):
        stop = intervals[ii + 1]
        print('fitting ICA from {0} to {1} seconds'.format(start, stop))
        this_ica = ICA(n_components=n_components, method=method).fit(
            raw, start=start, stop=stop, reject=reject)
        icas_from_other_data.append(this_ica)

Can any one help and tell me what is the right threshold for EEG?

thank you.

2

You rejection threshold is likely too low. I would suggest 150e-6 or 200e-6.

Maybe you can also use autoreject to learn it automatically. See:

https://autoreject.github.io/stable/auto_examples/plot_estimate_global_reject.html#sphx-glr-auto-examples-plot-estimate-global-reject-py
https://autoreject.github.io/stable/auto_examples/plot_autoreject_workflow.html#sphx-glr-auto-examples-plot-autoreject-workflow-py

Mainak