A Comparative Study of Canonical Correlation Analysis and Power Spectral Density Analysis for SSVEP Detection
Authors:
- Qingguo WeiQWQingguo Wei
- Meixia XiaoMXMeixia Xiao
- Zongwu LuZLZongwu Lu
- 1 August 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 49, 7-10
Abstract
Steady-state visual evoked potentials (SSVEPs) are widely employed for target detection in brain-computer interfaces (BCIs). Canonical correlation analysis (CCA), which extends ordinary correlation to two sets of variables, is a new method for SSVEP detection. In this paper, the performance of CCA is compared with that of traditional power spectral density analysis (PSDA) in terms of power spectral amplitude, recognition accuracy, information transfer rate and operating speed. The results show that the CCA method outperforms the PSDA in all these technical indexes.Keywords
This publication has 8 references indexed in Scilit:
- An online multi-channel SSVEP-based brain–computer interface using a canonical correlation analysis methodJournal of Neural Engineering, 2009
- Multiple Channel Detection of Steady-State Visual Evoked Potentials for Brain-Computer InterfacesIEEE Transactions on Biomedical Engineering, 2007
- Frequency Recognition Based on Canonical Correlation Analysis for SSVEP-Based BCIsIEEE Transactions on Biomedical Engineering, 2006
- Steady-state visual evoked potential (SSVEP)-based communication: impact of harmonic frequency componentsJournal of Neural Engineering, 2005
- BCI2000: A General-Purpose Brain-Computer Interface (BCI) SystemIEEE Transactions on Biomedical Engineering, 2004
- Design and implementation of a brain-computer interface with high transfer ratesIEEE Transactions on Biomedical Engineering, 2002
- Brain–computer interfaces for communication and controlClinical Neurophysiology, 2002
- EEG-based communication: improved accuracy by response verificationIEEE Transactions on Rehabilitation Engineering, 1998