A signal-processing-based technique for P300 evoked potential detection with the applications into automated character recognition

EURASIP Journal on Advances in Signal Processing

Table 2 Listings of the P300 detection results on the eight-word testing dataset

Words for testing	M = 15	M = 14	M = 13	M = 12	M = 10	M = 8	M = 5	M = 3
FOOD	FOOD	FOOD	FN OD	FN OD	FB OD	FN OD	FONB	FOH D
MOOT	MOOT	MOOT	MOOT	MOOT	MOOT	MOOT	MOOX	MOO4
HAM	HAM	HAM	HAM	HAA	HAM	HAM	B AA	HCQ
PIE	PIE	PIE	PIE	PIE	PIE	PIE	PIE	PIE
CAKE	CAKE	CAKE	CAKE	CAKE	CAKE	CAKE	CAKE	CAKC
TUNA	TUNA	TUNA	TUNA	TUNA	TO NA	TO NA	TO NA	TC NI
ZYGOT	ZYGOT	ZA GOT	ZYA OT	ZYA OT	ZYA OT	ZYA OT	ZYA OT	ZYA ON
4567	4567	4567	4567	4567	4567	458 7	X 58 7	R 58 7
Accuracy%	100.00	96.77	93.55	90.32	90.32	87.10	70.97	64.52

This dataset is for a variety of M values (results on experiment II). Note that each wrong detection character is set in italics.