Back to Search
Start Over
Using Deep Learning to Classify Saccade Direction from Brain Activity
- Source :
- ETRA '21 Short Papers: ACM Symposium on Eye Tracking Research and Applications, ETRA Short Papers
- Publication Year :
- 2021
- Publisher :
- ETH Zurich, 2021.
-
Abstract
- We present first insights into our project that aims to develop an Electroencephalography (EEG) based Eye-Tracker. Our approach is tested and validated on a large dataset of simultaneously recorded EEG and infrared video-based Eye-Tracking, serving as ground truth. We compared several state-of-the-art neural network architectures for time series classification: InceptionTime, EEGNet, and investigated other architectures such as convolutional neural networks (CNN) with Xception modules and Pyramidal CNN. We prepared and tested these architectures with our rich dataset and obtained a remarkable accuracy of the left/right saccades direction classification (94.8 %) for the InceptionTime network, after hyperparameter tuning.<br />ETRA '21 Short Papers: ACM Symposium on Eye Tracking Research and Applications<br />ISBN:978-1-4503-8344-8
- Subjects :
- Hyperparameter
Ground truth
Artificial neural network
medicine.diagnostic_test
1707 Computer Vision and Pattern Recognition
Brain activity and meditation
Computer science
business.industry
10093 Institute of Psychology
Deep learning
Pattern recognition
Electroencephalography
2731 Ophthalmology
Convolutional neural network
1709 Human-Computer Interaction
2809 Sensory Systems
Saccade
medicine
Artificial intelligence
business
150 Psychology
Subjects
Details
- Language :
- English
- ISBN :
- 978-1-4503-8344-8
- ISBNs :
- 9781450383448
- Database :
- OpenAIRE
- Journal :
- ETRA '21 Short Papers: ACM Symposium on Eye Tracking Research and Applications, ETRA Short Papers
- Accession number :
- edsair.doi.dedup.....f4650ffdbddcf40f9d7d1783449e422b
- Full Text :
- https://doi.org/10.3929/ethz-b-000490217