Name
Abstract | ||
|---|---|---|
The brain-computer interface (BCI) technology provides a potential tool for communication and control in immersive virtual reality (VR) environments. However, implementing a BCI with current VR platforms remains a challenge due to difficulties in system design and electroencephalogram (EEG) analysis. This study aims to explore the feasibility of a steady-state visual evoked potential (SSVEP)-based BCI for applications in room-scale VR with an HTC VIVE headset. A four-class BCI was designed to simulate a cursor control system. Subjects were instructed to perform a cue-guided target selection task during standing or walking on a treadmill at four different speeds (0, 0.45, 0.89, and 1.34 meters per second (m/s)). During the experiment, two fixing modes of visual stimuli (head-fixed and earth-fixed) were presented to the head-mounted display (HMD). The results from a group of 10 subjects indicated that the system worked well regarding classification accuracy. The BCI performance decreased as the walking speed increased. Interestingly, the earth-fixed condition showed significantly higher performance than the head-fixed condition, showing online and offline information transfer rates (ITR5) corresponding to unsupervised and supervised algorithms above 10 bits/min and 21 bits/min, respectively. These results demonstrated the potential of an SSVEP-based BCI for applications in room-scale mobile VR environments. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.3233/ICA-180586 | INTEGRATED COMPUTER-AIDED ENGINEERING |
Keywords | Field | DocType |
Brain-computer interface, electroencephalogram, virtual reality, steady-state visual evoked potential | Computer vision,Virtual reality,Computer science,Brain–computer interface,Human–computer interaction,Artificial intelligence | Journal |
Volume | Issue | ISSN |
26 | 4 | 1069-2509 |
Citations | PageRank | References |
0 | 0.34 | 16 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Zhaolin Yao | 1 | 3 | 1.73 |
| Yijun Wang | 2 | 308 | 46.68 |
| Yang Chen | 3 | 357 | 44.50 |
| Weihua Pei | 4 | 64 | 13.18 |
| Xiaorong Gao | 5 | 598 | 81.99 |
| Hongda Chen | 6 | 99 | 20.06 |