Algorithm 1. Reading XLtek EEG Data Algorithm.
	Input: An EEG signal and the size of window in seconds
	Output: Array of EEG data samples that constitute the epochs
1	FUNCTION get_epoch(s, min_secs = 10)
2		// Extracting signal start time, sample rate, channel names, and number of samples
3		start_time, s_rate, ch_names, n_samples ← s.return_hdr()
4		s_rate ← int(round(s_rate))
5		// Extracting the creation time for the erd file that holds the raw data
6		erd_time ← s.return_hdr() [−1][‘creation_time’]
7		// Excluding samples between the start time of recording and the actual acquisition
8		stc_erd_diff ← (erd_time–start_time). total_seconds()
9		// Computing the number of samples required from each channel
10		stride ← min_secs ∗ s_rate
11		start_index ← int(stc_erd_diff) ∗ s_rate
12		end_index ← start_index + stride
13		findings ← [ ]
14		WHILE end_index ≤ n_samples DO
15			t ← s.return_dat ([1], start_index, end_index)
16			// Excluding the epochs that may contain NaN values
17			IF ! np.any(np.isnan(t), axis = 1) THEN
18				data ← s.return_dat(range(len(ch_names)), start_index, end_index)
19				IF s_rate > 256 THEN
20					data ← decimate(data, q = 2)
21				ENDIF
22				// Converting numpy array to a pandas data frame
23				df ← pd.DataFrame(data = data.T, columns = ch_names)
24				findings.append(montage(df, model_modified_channels))
25			ENDIF
26			start_index ← start_index + stride
27			end_index ← end_index + stride
28		ENDWHILE
29	return findings
30	ENDFUNCTION