Noninvasive BCIs: Multiway Signal-Processing Array Decompositions

Cichocki, Andrzej; Washizawa, Yoshikazu; Rutkowski, Tomasz M.; Bakardjian, Hovagim; Phan, Anh-Huy; Choi, Seungjin; Lee, Hyekyoung; Zhao, Qibin; Zhang, Liqing; Li, Yuanqing

doi:10.1109/mc.2008.431

Cited by 123 publications

(66 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This example illustrates the analysis of real-world EEG data containing the Event-Related Spectral Perturbation (ERSP) measurements of EEG signals recorded from 62 electrodes during right and left hand motor imageries (MI) [51]. The observed tensor in the timefrequency domain using the complex Morlet wavelet has a size of 62 channels × 25 frequency bins × 1000 time frames × 2 classes (Left/Right).…”

Section: Analysis Of Motor Imagery (Mi) Eeg Datamentioning

confidence: 99%

Extended HALS algorithm for nonnegative Tucker decomposition and its applications for multiway analysis and classification

Phan

Cichocki

2011

Neurocomputing

View full text Add to dashboard Cite

Section: Analysis Of Motor Imagery (Mi) Eeg Datamentioning

confidence: 99%

Extended HALS algorithm for nonnegative Tucker decomposition and its applications for multiway analysis and classification

Phan

Cichocki

2011

Neurocomputing

View full text Add to dashboard Cite

“…It is worth noting that we only consider the spatial and temporal dimensions of EEG signals in this study, since P300 characteristics are relatively more prominent in these two dimensions. The spatial-temporal analysis could be further extended to higher-order analysis by constructing higher-dimensional (i.e., tensor) samples which provide multiway array presentation for the EEG data structure and include more neurophysiological meanings [39], [41]- [43].…”

Section: Multiway Optimizationmentioning

confidence: 99%

Spatial-Temporal Discriminant Analysis for ERP-Based Brain-Computer Interface

Zhang

Zhou

Zhao

et al. 2013

IEEE Trans. Neural Syst. Rehabil. Eng.

123

View full text Add to dashboard Cite

Abstract-Linear discriminant analysis (LDA) has been widely adopted to classify event-related potential (ERP) in brain-computer interface (BCI). Good classification performance of the ERPbased BCI usually requires sufficient data recordings for effective training of the LDA classifier, and hence a long system calibration time which however may depress the system practicability and cause the users resistance to the BCI system. In this study, we introduce a spatial-temporal discriminant analysis (STDA) to ERP classification. As a multiway extension of the LDA, the STDA method tries to maximize the discriminant information between target and nontarget classes through finding two projection matrices from spatial and temporal dimensions collaboratively, which reduces effectively the feature dimensionality in the discriminant analysis, and hence decreases significantly the number of required training samples. The proposed STDA method was validated with dataset II of the BCI Competition III and dataset recorded from our own experiments, and compared to the state-of-the-art algorithms for ERP classification. Online experiments were additionally implemented for the validation. The superior classification performance in using few training samples shows that the STDA is effective to reduce the system calibration time and improve the classification accuracy, thereby enhancing the practicability of ERP-based BCI.Index Terms-Brain-computer interface (BCI), electroencephalogram (EEG), event-related potential (ERP), linear discriminant analysis (LDA), spatial-temporal discriminant analysis (STDA).

show abstract

“…With the development of advanced signal processing technologies, some new features of ERPs can be formulated, for example, the multi-domain feature of an ERP [6], [7] extracted by nonnegative tensor factorization (NTF) [5]. In contrast to an ERP's conventional features which exploit the ERP's information in one or more domains sequentially, the multi-domain feature of the ERP can reveal the properties of the ERP in the time, frequency, and spatial domains simultaneously [4], [5], [6], [7]. Hence, this new feature may be less affected by the heterogeneousness of datasets [7].…”

Section: Introductionmentioning

confidence: 99%

Multi-domain Feature of Event-Related Potential Extracted by Nonnegative Tensor Factorization: 5 vs. 14 Electrodes EEG Data

Cong

Phan

Astikainen

et al. 2012

Latent Variable Analysis and Signal Separation

View full text Add to dashboard Cite

Abstract. As nonnegative tensor factorization (NTF) is particularly useful for the problem of underdetermined linear transform model, we performed NTF on the EEG data recorded from 14 electrodes to extract the multi-domain feature of N170 which is a visual event-related potential (ERP), as well as 5 typical electrodes in occipital-temporal sites for N170 and in frontal-central sites for vertex positive potential (VPP) which is the counterpart of N170, respectively. We found that the multi-domain feature of N170 from 5 electrodes was very similar to that from 14 electrodes and more discriminative for different groups of participants than that of VPP from 5 electrodes. Hence, we conclude that when the data of typical electrodes for an ERP are decomposed by NTF, the estimated multi-domain feature of this ERP keeps identical to its counterpart extracted from the data of all electrodes used in one ERP experiment.

show abstract

Noninvasive BCIs: Multiway Signal-Processing Array Decompositions

Cited by 123 publications

References 15 publications

Extended HALS algorithm for nonnegative Tucker decomposition and its applications for multiway analysis and classification

Extended HALS algorithm for nonnegative Tucker decomposition and its applications for multiway analysis and classification

Spatial-Temporal Discriminant Analysis for ERP-Based Brain-Computer Interface

Multi-domain Feature of Event-Related Potential Extracted by Nonnegative Tensor Factorization: 5 vs. 14 Electrodes EEG Data

Contact Info

Product

Resources

About