2021: Demystifying Independent Component Analysis (ICA) (Plenary)

in an easy to digest manner for those who are less mathematically inclined. ICA is increasingly gaining popularity in the EEG-processing community, yet not many industry professionals truly understand what the analysis is doing “under the hood”. This has led to a multitude of debates on whether or not ICA should be utilized for the EEG at all [Friston, 1998]. This talk aims to provide concrete information about the theory and usage of ICA with respect to the EEG. To begin, this talk will go over the basic matrix equation that ICA algorithms attempt to solve: S = WX (where S is the matrix of independent components, W is the “Mixing matrix”, and X is the raw EEG) [Langlois et al, 2010]. Then the talk will discuss the 5 key assumptions that provide the foundation of ICA and discuss whether the EEG is a suitable subject for independent component analysis under these assumptions [Ullsperger & Debener, 2010]. The 5 assumptions are as follows: 1 – Statistical independence between each source, 2 – The mixing matrix must be square and full rank, 3 – No external noise, 4 – Data must be centered, and 5 – Source signals must not be gaussian. The gaussian assumption is difficult to truly prove when it comes to an EEG, so we will discuss why that is and how ICA can still be implemented [Onton & Makeig, 2006]. After understanding the general ICA assumptions, we will compare the unique underlying procedures and assumptions of the three most widely used ICA algorithms in the field: Infomax, fast-ICA, and AMICA [Palmer at al, 2011]. These comparisons will be accompanied by ICA examples created in EEGLAB, ISync, and WinEEG. To conclude, the presentation will go over some important clinical considerations for those who want to implement ICA, such as the amount of data required for a good recording, how to maximize the accuracy of your results, and when ICA may fail.
Presented by: Kody Newman

Category:

$30.00

in an easy to digest manner for those who are less mathematically inclined. ICA is increasingly gaining popularity in the EEG-processing community, yet not many industry professionals truly understand what the analysis is doing “under the hood”. This has led to a multitude of debates on whether or not ICA should be utilized for the EEG at all [Friston, 1998]. This talk aims to provide concrete information about the theory and usage of ICA with respect to the EEG. To begin, this talk will go over the basic matrix equation that ICA algorithms attempt to solve: S = WX (where S is the matrix of independent components, W is the “Mixing matrix”, and X is the raw EEG) [Langlois et al, 2010]. Then the talk will discuss the 5 key assumptions that provide the foundation of ICA and discuss whether the EEG is a suitable subject for independent component analysis under these assumptions [Ullsperger & Debener, 2010]. The 5 assumptions are as follows: 1 – Statistical independence between each source, 2 – The mixing matrix must be square and full rank, 3 – No external noise, 4 – Data must be centered, and 5 – Source signals must not be gaussian. The gaussian assumption is difficult to truly prove when it comes to an EEG, so we will discuss why that is and how ICA can still be implemented [Onton & Makeig, 2006]. After understanding the general ICA assumptions, we will compare the unique underlying procedures and assumptions of the three most widely used ICA algorithms in the field: Infomax, fast-ICA, and AMICA [Palmer at al, 2011]. These comparisons will be accompanied by ICA examples created in EEGLAB, ISync, and WinEEG. To conclude, the presentation will go over some important clinical considerations for those who want to implement ICA, such as the amount of data required for a good recording, how to maximize the accuracy of your results, and when ICA may fail.
Presented by: Kody Newman

We’ve Moved…

To accommodate the organization’s growing needs, we have decided to move our office to a new location.

2146 Rosewell RoadSuite

Suite 108, PMB 736

Marietta, GA 30062

USA

2021: Demystifying Independent Component Analysis (ICA) (Plenary)
Scroll to Top

Are you having problems clicking next on the membership form?

You must have 3rd party cookies set to “Always Accept.”

Internet Explorer 7 on Windows

  • Click the “Tools” menu
  • Click “Internet Options”
  • Select the “Privacy” tab
  • Option 1: To enable third-party cookies for all sites
  • Click “Advanced”
  • Select “Override automatic cookie handling”
  • Select the “Accept” button under “Third-party Cookies” and click “OK”

Firefox 3 on Windows

  • Click the “Tools” menu
  • Click “Options…”
  • Select the “Privacy” menu
  • Make sure “Keep until” is set to “they expire”
  • Option 1: To enable third party cookies for ALL sites: Make sure “Accept third-party cookies” is checked

Safari on Apple OS X:

  • Click the “Safari” menu
  • Click “Preferences…”
  • Click the “Security” menu
  • For “Cookies and website data” unselect “Block all cookies”
  • For “Website tracking”, unselect “Prevent cross-site tracking”
Safari enable cookies for membership purchase.

Firefox 3 on Apple OS X:

  • Click the “Firefox” menu
  • Click Preferences…
  • Click the Privacy menu
  • Make sure “Keep until” is set to “they expire”
  • Option 1: To enable third-party cookies for ALL sites: Make sure “Accept third-party cookies” is checked

Google Chrome on Windows

  • Select the Wrench (spanner) icon at the top right
  • Select “Options”
  • Select the “Under the Hood” tab
  • Select “Allow all cookies” under “Cookie Settings” and click “Close”

Internet Explorer 6 on Windows

  • Click the “Tools” menu
  • Click “Internet Options”
  • Select the “Privacy” tab
  • Move the settings slider to “Low” or “Accept all cookies”
  • Click “OK”

Opera 9 on Windows

  • Click the “Tools” menu
  • Click “Preferences…”
  • Click the “Advanced” tab
  • Select “Cookies” on the left list
  • Make sure “Accept cookies” is selected and uncheck “Delete new cookies when exiting Opera”
  • Click “OK”