Paper Review on Noureddin et. al "Online Removal of Eye Movement and Blink EEGArtifacts Using a High-Speed Eye Tracker"

Paper Review:

Noureddin et. al.

Online Removal of Eye Movement and Blink EEGArtifacts Using a High-Speed Eye Tracker

Presented ByMd Kafiul Islam

A0080155M

Outline• Introduction

Motivation

• Paper Summery Main Contribution: Eye Tracker based OA Removal

Performance Evaluation

Results

• Conclusion• Q & A

Motivation OA Removal from EEG

• High Speed Eye tracker• Both Eye Blink and Eye Movement• No Requirement of EOG electrodes• Online Removal for S-EEG based BI

Limitations of EOG Electrodes – Also contain brain waves– Not suitable for practical daily applications

Eye TrackerEOG Lead Locations

Simultaneous EEG + EOG

Eye Blink Artifacts

Eye Movement Artifacts

Eye Tracking and OA Removal

General approach to OA removal

Overall operation of eye tracker for every image captured.

Areas of eye tracker images used for extracting blink signal

Example of Eye Tracking

Eye tracking versus EOG during (a) simultaneous horizontal (left) and vertical (up) saccade, and (b) blink. Sample eye images are shown above and EOG and eye tracking signals below, with arrows pointing to the time instant each

image was captured. In (a), the x shows the current pupil position, and the dot shows the pupil position at the start of the saccade. In (b), the ellipse shows the area where the intensity value is tracked during the blink.

Performance EvaluationTwo Algorithms for Adaptive Filter:

1) RLS (fast convergence)2) H ∞ (better accuracy)

Reference Inputs (X)1) EOG2) f-EEG3) ET + f-EEG

Z -> BPF (0.5-30 Hz) -> BET

‘R’ Metric for Evaluation

Results

Results (Cont…)

Logarithm of mean R values for (a) RLS and (b) H∞ algorithms during small upward saccades. Electrodes where the difference between means is significant are highlighted with boxes. Amplitudes are scaled the same in both (a) and (b)

to show the relative performance of the algorithms at each electrode.

RLS H∞

Conclusion

First use of a high-speed eye tracker for online OA removal (blink +

movement)

Eliminating EOG electrodes attached to the face is important for practical

daily applications (Combined EEG + Eye tracking for other applications, e.g. saccade-

and fixation-related potentials, fixation control, HCI, fatigue/saliency detection, etc.)

A new algorithm (BSG) for extracting a blink’s time course from eye

tracker images (Calibration-free method)

The performance is tested on real EEG for both RLS and H∞ algorithms

using 1) EOG; 2) f-EEG; and 3) ET with f-EEG and resulted better than conventional

Q & A