Classification of Non-Time-Locked Rapid Serial Visual Presentation Events for Brain-Computer Interaction Using Deep Learning
Abstract
Deep learning solutions based on deep neural networks (DNN) and deep stack networks (DSN) were investigated for classifying target images in a non-time-Iocked rapid serial visual presentation (RSVP) image target identification task using EEG. Several feature extraction methods associated with this task were implemented and tested for deep learning, where a sliding window method using the trained classifier was used to predict the occurrence of target events in a non-time-locked fashion.. The deep learning algorithms explored based on deep stacking networks were able to improve the error rate by about 5% over existing algorithms such as linear discriminant analysis (LDA) for this task. Initial test results also showed that this method based on deep stacking networks for non-time-Iocked classification can produce an error rate close to that achieved for time-locked classification, thus illustrating the power of deep learning for complex feature spaces.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jul 08, 2014
- Accession Number
- AD1008569
Entities
People
- Brent J. Lance
- Kay Robbins
- Kenneth Ball
- Lenis Mauricio Meriño
- Li Deng
- Vernon J. Lawhern
- Yufei Huang
- Zijing Mao
Organizations
- University of Texas at San Antonio