BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
DTSTART:20210314T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20201101T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20210202T021148Z
UID:154DD4D2-809D-41BF-8B4C-57EC07A802BF
DTSTART;TZID=America/New_York:20210118T173000
DTEND;TZID=America/New_York:20210118T183000
DESCRIPTION:Temporal signals emerge in material science from both experimen
 ts and computer simulations to understand a physical phenomenon. For examp
 le\, it is often desirable to collect responses of materials for a particu
 lar loading that changes over time to elicit steady-state or equilibrium b
 ehavior. A characteristic signal is collected for each material of interes
 t and analyzed to extract scientific knowledge about the material. In this
  talk\, we will be discussing a particular characterization technique call
 ed cyclic voltammetry (CV) that characterizes a material in an electrochem
 ical environment such as a battery cell. CV experiment involves sweeping o
 ver a time-varying voltage load applied to the electro-chemical cell and c
 ollecting current output as a temporal response. CV is a critical tool in 
 characterizing and understanding behavior of potential battery materials f
 or clean and efficient energy storage.\n\nWe will be using CV data collect
 ed from hundreds and thousands of experiments that needs to be analyzed in
  a multivariate fashion. Our goal is to compare different materials based 
 on their respective CV signals and develop a method to classify materials 
 based on the shape of the signal. Thus we are interested in the structure 
 of the signal as represented by moment representation i.e. interactions be
 tween output and inputs jointly over time. In particular\, we propose use 
 of the Gaussian process (GP) as a means to identify function space represe
 ntations of CV signals. GPs allows users to obtain mathematical representa
 tions of the data by selecting appropriate basis in the form of kernels (c
 ovariance functions) that can be leveraged to encode physics based constra
 ints on the signals. This talk would cover underlying mathematics of GPs\,
  function spaces and their applications to signal processing. Applying the
 se methods on CV data of materials\, we showcase how machine learning and 
 signal processing can be combined to realize data driven material discover
 y and design.\n\nSpeaker(s): Kiran Vaddi\, \n\nVirtual: https://events.vto
 ols.ieee.org/m/250165
LOCATION:Virtual: https://events.vtools.ieee.org/m/250165
ORGANIZER:anbyrley@buffalo.edu
SEQUENCE:2
SUMMARY:Function space data representation of temporal signals for machine 
 learning
URL;VALUE=URI:https://events.vtools.ieee.org/m/250165
X-ALT-DESC:Description: <br /><div class="gmail_default">Temporal signals e
 merge in material science from both experiments and computer simulations t
 o understand a physical phenomenon. For example\, it is often desirable to
  collect responses of materials for a particular loading that changes over
  time to elicit steady-state or equilibrium behavior. A characteristic&nbs
 p\;signal is collected for each material of interest and analyzed to extra
 ct scientific knowledge about the material. In this talk\, we will be disc
 ussing a particular characterization technique called cyclic voltammetry (
 CV) that characterizes a material in an electrochemical environment such a
 s a battery cell. CV experiment involves sweeping&nbsp\;over a time-varyin
 g voltage load applied to the electro-chemical cell and collecting current
  output as a temporal response. CV is a critical tool in characterizing an
 d understanding behavior of potential battery materials for clean and effi
 cient energy storage.&nbsp\;</div>\n<div class="gmail_default">&nbsp\;</di
 v>\n<div class="gmail_default">We will be using CV data collected from hun
 dreds and thousands of experiments that needs to be analyzed in a multivar
 iate&nbsp\;fashion.&nbsp\; Our goal is to compare different materials base
 d on their respective CV signals and develop a method to classify material
 s based on the shape of the signal. Thus we are interested in the structur
 e of the signal as represented by moment representation i.e. interactions&
 nbsp\;between output and inputs jointly over time. In particular\, we prop
 ose use of the Gaussian process (GP) as a means to identify function space
  representations of CV signals. GPs allows users to obtain mathematical re
 presentations of the data by selecting appropriate&nbsp\;basis in the form
  of kernels (covariance functions) that can be leveraged to encode physics
  based constraints on the signals. This talk would cover underlying mathem
 atics of GPs\, function spaces and their applications to signal processing
 . Applying these methods on CV data of materials\, we showcase how machine
  learning and signal processing can be combined to realize data driven mat
 erial discovery and design.</div>
END:VEVENT
END:VCALENDAR