BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:8341@i2m.univ-amu.fr
DTSTART;TZID=Europe/Paris:20140613T140000
DTEND;TZID=Europe/Paris:20140613T150000
DTSTAMP:20241120T210342Z
URL:https://www.i2m.univ-amu.fr/evenements/j-spinnato-i2m-finding-eeg-spac
 e-time-scale-localized-features-using-matrix-based-penalized-discriminant-
 analysis/
SUMMARY: (...): J. Spinnato (I2M) : Finding EEG Space-time-scale localized 
 features using Matrix-based penalized discriminant analysis
DESCRIPTION:: Finding EEG Space-time-scale localized features using Matrix-
 based penalized discriminant analysis\nBy Juliette Spinnato\\\, I2M\n\nIn 
 this talk we will explain a new method for constructing and selecting of d
 iscriminant space-time-scale features for electroencephalogram\n(EEG) sign
 al classification\\\, suitable for Error Related Potentials (ErrP) detecti
 on in brain-computer interface (BCI). The method rests\non a new variant o
 f matrix-variate Linear Discriminant Analysis (LDA)\\\, and differs from p
 reviously proposed approaches in mainly\nthree ways.\nFirst\\\, a discrete
  wavelet expansion is introduced for mapping time-courses to time-scale co
 efficients\\\, yielding time-scale localized features.\nSecond\\\, the mat
 rix-variate LDA is modified in such a way that it yields an interesting du
 ality property\\\, that makes interpretation easier.\nThird\\\, a space pe
 nalization is introduced using a surface Laplacian\\\, so as to enforce sp
 atial smoothness.\nThe proposed approaches\\\, termed D-MLDA and D-MPDA ar
 e tested on EEG signals\\\, with the goal of detecting ErrP. Numerical res
 ults\nshow that D-MPDA outperforms D-MLDA and other matrix-variate LDA tec
 hniques. In addition this method produces relevant features\nfor interpret
 ation in ErrP signals.
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:DAYLIGHT
DTSTART:20140330T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR