BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//NextToU//EN
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:a3fa538a-e404-484b-aa40-f9a2cac7a723@nexttoyou
DTSTAMP:20261106T171407Z
DTSTART:20261113T190000Z
DTEND:20261113T200000Z
SUMMARY:Statistics Seminar Series: Pramita Bagchi (GW School of Public Hea
 lth)
LOCATION:Duques Hall 151\, 2201 G Street NW\, Washington DC 20052
DESCRIPTION:Please join the GW Statistics Department for a talk featuring 
 Pramita Bagchi\, Department of Biostatistics and Bioinformatics at the Mi
 lken Institute School of Public Health\, George Washington University.\n\
 nAdaptive Frequency Band Learning of Nonstationary Functional Time Series
 : An Application to High-Dimensional EEG Signals\n\nAbstract:\nFrequency-
 domain properties of high-dimensional electroencephalogram (HD-EEG) signa
 ls contain valuable information about brain activity and functioning. The
 se properties tend to vary over time and are characterized through the ti
 me-varying spectral density. Rather than analyzing the time-varying spect
 ral density directly\, biomedical researchers work with low-dimensional s
 ummary measures by averaging power within pre-specified frequency bands. 
 Partitioning frequencies into bands significantly affects how well freque
 ncy band summary measures characterize the underlying spectral density\, 
 making it an important yet often overlooked analytical consideration. HD-
 EEGs represent an important class of biomedical signals that can be appro
 priately characterized as nonstationary functional time series. We develo
 p a method for learning frequency band structures for functional time ser
 ies that optimally summarize time-varying dynamics. We develop a scan sta
 tistic and scalable search algorithm to detect changes in the frequency d
 omain for adaptive frequency band estimation. We validate its use in prac
 tice by establishing essential theoretical properties and de\n\nhttp://ne
 xt-to-u.app/events/a3fa538a-e404-484b-aa40-f9a2cac7a723
URL:http://next-to-u.app/events/a3fa538a-e404-484b-aa40-f9a2cac7a723
END:VEVENT
END:VCALENDAR