Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Signal vs Noise in Eye-tracking Data: Biometric Implications and Identity Information Across Frequencies

Mehedi H. Raju, Lee Friedman, Dillon Lohr, Oleg Komogortsev

TL;DR

The results confirm the “signal” predominantly contains identity-specific information, yet the “noise” also possesses unexpected identity-specific data, and this consistency holds for both short-term and long-term biometric evaluations.

Abstract

Prior research states that frequencies below 75 Hz in eye-tracking data represent the primary eye movement termed ``signal'' while those above 75 Hz are deemed ``noise''. This study examines the biometric significance of this signal-noise distinction and its privacy implications. There are important individual differences in a person's eye movement, which lead to reliable biometric performance in the ``signal'' part. Despite minimal eye-movement information in the ``noise'' recordings, there might be significant individual differences. Our results confirm the ``signal'' predominantly contains identity-specific information, yet the ``noise'' also possesses unexpected identity-specific data. This consistency holds for both short-(approx. 20 min) and long-term (approx. 1 year) biometric evaluations. Understanding the location of identity data within the eye movement spectrum is essential for privacy preservation.

Signal vs Noise in Eye-tracking Data: Biometric Implications and Identity Information Across Frequencies

TL;DR

The results confirm the “signal” predominantly contains identity-specific information, yet the “noise” also possesses unexpected identity-specific data, and this consistency holds for both short-term and long-term biometric evaluations.

Abstract

Prior research states that frequencies below 75 Hz in eye-tracking data represent the primary eye movement termed ``signal'' while those above 75 Hz are deemed ``noise''. This study examines the biometric significance of this signal-noise distinction and its privacy implications. There are important individual differences in a person's eye movement, which lead to reliable biometric performance in the ``signal'' part. Despite minimal eye-movement information in the ``noise'' recordings, there might be significant individual differences. Our results confirm the ``signal'' predominantly contains identity-specific information, yet the ``noise'' also possesses unexpected identity-specific data. This consistency holds for both short-(approx. 20 min) and long-term (approx. 1 year) biometric evaluations. Understanding the location of identity data within the eye movement spectrum is essential for privacy preservation.
Paper Structure (22 sections, 2 figures, 1 table)

This paper contains 22 sections, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Prior Work
  3. Prior Work on EMB
  4. Prior Work on Filtering Eye Movement Data
  5. Methodology
  6. Dataset
  7. Data Preprocessing
  8. Filtering
  9. Data Preprocessing for Embedding Analysis
  10. Velocity Clamping
  11. Eye Know You Too Network architecture
  12. Dataset split and Training procedure
  13. Evaluation
  14. Metrics
  15. Hardware & software
  16. ...and 7 more sections

Figures (2)

  • Figure 1: Signal and Noise comparison: Exemplars. The two plots on the left column of the figure are the raw data collected at 1000 Hz. We refer to these recordings as the "raw" data. The two plots in the middle column of the figure are recordings after a low-pass filter was applied. We refer to these recordings as the "signal" portion of the recording. The two plots on the right column are high-pass filtered recordings from the same subjects. We refer to these as the "noise" portion of the recording. Each row is a different subject.
  • Figure 2: Block diagram of the methodology