Title | ||
---|---|---|
Does frequency resolution affect the classification performance of steady-state visual evoked potentials? |
Abstract | ||
---|---|---|
Multi-target stimulus coding plays an important role in a steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI). In conventional SSVEP-based BCIs, a large interval between two neighboring stimulus frequencies is often used to improve classification accuracy. Although recent progresses in stimulus coding and target identification methods that have significantly improved the accuracy even with a high-frequency resolution (e.g., 0.2 Hz), the effects of frequency resolution on classification performance have not been systematically and statistically explored. This study compared the classification accuracy of SSVEPs with five different frequency resolutions (0.2 Hz, 0.4 Hz, 0.6 Hz, 0.8 Hz, and 1.0 Hz) using three (one unsupervised and two supervised) target identification methods. Eight-class SSVEP data were extracted from a 40-class SSVEP dataset for each condition according to the five frequency resolutions. The results showed no significant difference between frequency resolutions when combining joint frequency-phase modulation (JFPM) coding and template-based target identification methods. The results suggested that the number of commands (i.e., visual stimuli) in an SSVEP-based BCI could be increased without compromising the information transfer rate of the BCI. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/NER.2017.8008360 | 2017 8th International IEEE/EMBS Conference on Neural Engineering (NER) |
Keywords | Field | DocType |
frequency resolution,classification performance,steady-state visual evoked potentials,multitarget stimulus coding,SSVEP based brain-computer interface,unsupervised target identification method,joint frequency-phase modulation coding,template-based target identification methods,visual stimuli | Computer vision,Computer science,Brain–computer interface,Speech recognition,Coding (social sciences),Modulation,Evoked potential,Artificial intelligence,Frequency modulation,Stimulus (physiology),Electroencephalography,Visual perception | Conference |
ISSN | ISBN | Citations |
1948-3546 | 978-1-5090-4604-1 | 0 |
PageRank | References | Authors |
0.34 | 5 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Masaki Nakanishi | 1 | 25 | 4.52 |
Yijun Wang | 2 | 308 | 46.68 |
Yu-Te Wang | 3 | 135 | 17.37 |
Tzyy-Ping Jung | 4 | 1410 | 202.52 |