Evoked potentials (EPs) in response to stimuli are recorded from a hum
an scalp contaminated with noise. To improve the signal-to-noise ratio
, averaging methods have been widely used for the recorded data. Howev
er, when the waveforms of EP for each stimulus are not identical, the
average waveform of the EP deteriorates. Variation of the EP waveform
to each stimulus itself is important information for the EP. In this p
aper, a recording method for single somatosensory evoked potential (SE
P) waveform is proposed, in which three kinds of band-pass filters wer
e selectively used during three specific time sectors for each interst
imulus interval. For the late section of the interval, an EEG waveform
prediction method was applied to eliminate contaminated alpha rhythm
components. By using the proposed method, we were successful in detect
ing the single SEP waveform.