moabb.datasets.BNCI2014_009#
- class moabb.datasets.BNCI2014_009[source]#
BNCI 2014-009 P300 dataset.
PapersWithCode leaderboard: https://paperswithcode.com/dataset/bnci2014-009-moabb-1
Dataset summary
#Subj
#Chan
#Trials / class
Trials length
Sampling rate
#Sessions
10
16
1440 NT / 288 T
0.8s
256Hz
3
Dataset from [1].
Dataset description
This dataset presents a complete record of P300 evoked potentials using two different paradigms: a paradigm based on the P300 Speller in overt attention condition and a paradigm based used in convert attention condition. In these sessions, 10 healthy subjects focused on one out of 36 different characters. The objective was to predict the correct character in each of the provided character selection epochs. (Note: right now only the overt attention data is available via MOABB)
In the first interface, cues are organized in a 6×6 matrix and each character is always visible on the screen and spatially separated from the others. By design, no fixation cue is provided, as the subject is expected to gaze at the target character. Stimulation consists in the intensification of whole lines (rows or columns) of six characters.
Ten healthy subjects (10 female, mean age = 26.8 ± 5.6, table I) with previous experience with P300-based BCIs attended 3 recording sessions. Scalp EEG potentials were measured using 16 Ag/AgCl electrodes that covered the left, right and central scalp (Fz, FCz, Cz, CPz, Pz, Oz, F3, F4, C3, C4, CP3, CP4, P3, P4, PO7, PO8) per the 10-10 standard. Each electrode was referenced to the linked earlobes and grounded to the right mastoid. The EEG was acquired at 256 Hz, high pass- and low pass-filtered with cutoff frequencies of 0.1 Hz and 20 Hz, respectively. Each subject attended 4 recording sessions. During each session, the subject performed three runs with each of the stimulation interfaces.
References
- 1
P Aricò, F Aloise, F Schettini, S Salinari, D Mattia and F Cincotti (2013). Influence of P300 latency jitter on event related potential- based brain–computer interface performance. Journal of Neural Engineering, vol. 11, number 3.
Notes
Note
BNCI2014_009
was previously namedBNCI2014009
.BNCI2014009
will be removed in version 1.1.
Examples using moabb.datasets.BNCI2014_009
#
Within Session P300 with Learning Curve
Within Session P300 with Learning Curve