Multiway Canonical Correlation Analysis for Frequency Components Recognition in SSVEP-Based BCIs

Yu, Zhang; Zhou, Guoxu; Zhao, Qibin; Onishi, Akinari; Jin, Jing; Wang, Xingyu; Cichocki, Andrzej

doi:10.1007/978-3-642-24955-6_35

Cited by 125 publications

(134 citation statements)

References 10 publications

Supporting

Mentioning

131

Contrasting

Order By: Relevance

“…The frequency with the maximal PSD value is recognized as the target frequency (i.e., the SSVEP frequency component). Two problems of the PSDA for SSVEP recognition are: 1) PSDA with a single or bipolar channel may be sensitive to noises, and hence obtain a low signal-to-noise ratio (SNR) [11], [12]; 2) a relatively long TW (e.g., is usually required to estimate the spectrum with sufficient frequency resolution, which therefore limits the real-time performance of SSVEP-based BCI to some extent [13], [14]. To overcome drawbacks of the PSDA, several advance approaches have been proposed to improve the SSVEP recognition performance [11]- [13], [15], in which a canonical correlation analysis (CCA) based recognition method, first introduced by Lin et al [11], has aroused more interests of researchers.…”

mentioning

confidence: 99%

“…To this end, we introduce an L1-regularized multiway canonical correlation analysis (L1-MCCA) based on an ingenious combination of the tensor analysis [22]- [25] and the sparse regularization [26]- [28] to solve this problem. An unpenalized MCCA (conference version [14]) is first presented, in which collaborative CCAs are exploited to learn the projection vectors for reference signal optimization alternatingly from the channel-way and trial-way arrays of EEG tensor. In the MCCA, the EEG tensor is constructed by multi-channel EEG from multiple recording trials where some trials may bring more obstruction than contribution to the reference signal optimization.…”

mentioning

confidence: 99%

See 1 more Smart Citation

L1-Regularized Multiway Canonical Correlation Analysis for SSVEP-Based BCI

Zhang

Zhou

Jin

et al. 2013

IEEE Trans. Neural Syst. Rehabil. Eng.

Self Cite

238

151

View full text Add to dashboard Cite

Canonical correlation analysis (CCA) between recorded electroencephalogram (EEG) and designed reference signals of sine-cosine waves usually works well for steady-state visual evoked potential (SSVEP) recognition in brain-computer interface (BCI) application. However, using the reference signals of sine- cosine waves without subject-specific and inter-trial information can hardly give the optimal recognition accuracy, due to possible overfitting, especially within a short time window length. This paper introduces an L1-regularized multiway canonical correlation analysis (L1-MCCA) for reference signal optimization to improve the SSVEP recognition performance further. A multiway extension of the CCA, called MCCA, is first presented, in which collaborative CCAs are exploited to optimize the reference signals in correlation analysis for SSVEP recognition alternatingly from the channel-way and trial-way arrays of constructed EEG tensor. L1-regularization is subsequently imposed on the trial-way array optimization in the MCCA, and hence results in the more powerful L1-MCCA with function of effective trial selection. Both the proposed MCCA and L1-MCCA methods are validated for SSVEP recognition with EEG data from 10 healthy subjects, and compared to the ordinary CCA without reference signal optimization. Experimental results show that the MCCA significantly outperforms the CCA for SSVEP recognition. The L1-MCCA further improves the recognition accuracy which is significantly higher than that of the MCCA.

show abstract

mentioning

confidence: 99%

mentioning

confidence: 99%

L1-Regularized Multiway Canonical Correlation Analysis for SSVEP-Based BCI

Zhang

Zhou

Jin

et al. 2013

IEEE Trans. Neural Syst. Rehabil. Eng.

Self Cite

238

151

View full text Add to dashboard Cite

show abstract

“…by using more than one derivation with Common Spatial Patterns [13], as well as other advanced statistical and signal processing techniques (c.f. [4,14]). …”

Section: Discussionmentioning

confidence: 99%

User-centered design of brain-computer interfaces: OpenBCI.pl and BCI Appliance

Durka¹,

Kuś²,

Żygierewicz³

et al. 2012

Bulletin of the Polish Academy of Sciences: Technical Sciences

View full text Add to dashboard Cite

Abstract. Brain-Computer Interface (BCI) allows for non-muscular communication with external world, which may be the only way of communication for patients in a locked-in state. This paper presents a complete software framework for BCI, a novel hardware solution for stimuli rendering in BCIs based on Steady State Visual Evoked Potentials (SSVEP), and a univariate algorithm for detection of SSVEP in the EEG time series.OpenBCI is a complete software framework for brain-computer interfaces.Owing to an open license and modular architecture, it allows for flexible implementations of different communication channels in the serial or parallel hybrid mode, minimization of costs and improvements of stability and efficiency. Complete software is freely available from http://openbci.pl.BCI Appliance is a hardware solution that allows for dynamic control of menus with stable generation of stimuli for the SSVEP paradigm. The novelty consists of a design, whereby the LCD screen is illuminated from behind using an array of LEDs.Design pioneers also proposed a new line of thought about the user-centered design of BCI systems: a simple box with one on/off button, minimum embedded software, wireless connections to domotic and EEG acquisition devices, and user-controlled mode switching in a hybrid BCI.

show abstract

“…SSVEP has the same frequency (plus higher harmonics) as the stimulus, and can be recorded from the scalp using electroencephalography (EEG) [56]. Based on this mechanism a SSVEP braincomputer interface (BCI) can be designed, which typically depends on the external visual stimuli which are in the form of an array of light sources with different and distinct frequencies [57]. SSVEP BCI can translate the frequency modulation of EEG signals into computer commands, by recognizing the frequency components of the EEG signals recorded during different stimulus presentations [58].…”

Section: Simulationmentioning

confidence: 99%

Fast and unique Tucker decompositions via multiway blind source separation

Zhou¹,

Cichocki²

2012

Bulletin of the Polish Academy of Sciences: Technical Sciences

View full text Add to dashboard Cite

Abstract.A multiway blind source separation (MBSS) method is developed to decompose large-scale tensor (multiway array) data. Benefitting from all kinds of well-established constrained low-rank matrix factorization methods, MBSS is quite flexible and able to extract unique and interpretable components with physical meaning. The multilinear structure of Tucker and the essential uniqueness of BSS methods allow MBSS to estimate each component matrix separately from an unfolding matrix in each mode. Consequently, alternating least squares (ALS) iterations, which are considered as the workhorse for tensor decompositions, can be avoided and various robust and efficient dimensionality reduction methods can be easily incorporated to pre-process the data, which makes MBSS extremely fast, especially for large-scale problems. Identification and uniqueness conditions are also discussed. Two practical issues dimensionality reduction and estimation of number of components are also addressed based on sparse and random fibers sampling. Extensive simulations confirmed the validity, flexibility, and high efficiency of the proposed method. We also demonstrated by simulations that the MBSS approach can successfully extract desired components while most existing algorithms may fail for ill-conditioned and large-scale problems.

show abstract

Multiway Canonical Correlation Analysis for Frequency Components Recognition in SSVEP-Based BCIs

Cited by 125 publications

References 10 publications

L1-Regularized Multiway Canonical Correlation Analysis for SSVEP-Based BCI

L1-Regularized Multiway Canonical Correlation Analysis for SSVEP-Based BCI

User-centered design of brain-computer interfaces: OpenBCI.pl and BCI Appliance

Fast and unique Tucker decompositions via multiway blind source separation

Contact Info

Product

Resources

About