Related Experiment Video
Updated: Aug 5, 2026
07:24
Using Eye-tracking to Assess the Relative Importance of Visual and Vestibular Input to Subcortical Motion Processing in the Roll Plane
Published on: August 22, 2025
Wearable Impedance Oculography: A new method for eye motion classification
Aruna Mondal1, Nafis Adnan Adnan Mondal1, Debeshi Dutta2
1CSIR - Central Mechanical Engineering Research Institute, MG Avenue, Durgapur, 713209, India.
Biomedical Physics & Engineering Express
|August 3, 2026
Summary
Impedance oculography (IOG) offers superior eye movement detection over electrooculography (EOG) by reducing baseline drift and noise. This novel approach accurately classifies various eye movements using a wearable system and deep learning.
Area of Science:
- Biomedical Engineering
- Ophthalmology
- Signal Processing
Background:
- Electrooculography (EOG) faces challenges with baseline drifts and motion artifacts, limiting its accuracy in eye movement detection.
- Existing methods often require complex feature extraction for reliable eye movement classification.
Purpose of the Study:
- To introduce Impedance Oculography (IOG) as a robust alternative to EOG for eye movement classification.
- To develop and validate a wearable system for capturing IOG data.
- To classify various eye movements including blink, saccade, smooth pursuit, vergence, and vestibulo-ocular movements.
Main Methods:
- Collected IOG data using a spectacle-mounted two-electrode system from subjects performing specific eye movements.
- Processed IOG data through baseline drift correction, wavelet filtering, and windowing.
- Employed a Convolutional Neural Network (CNN) with 5-fold cross-validation for eye movement classification, utilizing 80% training and 20% testing data.
Main Results:
- IOG data exhibited uniform baseline drift over extended durations, outperforming EOG.
- The CNN model achieved high class-specific accuracies: 95% (blink), 97% (saccade), 97% (smooth pursuit), 100% (vergence), and 93% (vestibulo-ocular movements).
- The proposed method eliminated the need for explicit feature extraction for IOG signal classification.
Conclusions:
- Impedance Oculography (IOG) provides a more stable and reliable signal for eye movement acquisition compared to EOG.
- The developed wearable system and CNN-based classification demonstrate high efficacy for accurate, real-time eye movement detection in wearable systems.
