Skip to main content
Register
Springer Professional
SEARCH
Menu 1 2 3 4
Top

Hint

Swipe to navigate through the articles of this issue

Published in: Neural Processing Letters 5/2021

29-06-2021

Common Spatial Pattern with L21-Norm

Authors: Jingyu Gu, Mengting Wei, Yiyun Guo, Haixian Wang

Published in: Neural Processing Letters | Issue 5/2021

Login to get access
share
SHARE

Abstract

As one of the most commonly used algorithms in the field of feature extraction, common spatial pattern (CSP) has a good effect on multichannel electroencephalogram (EEG) signal classification, especially for motor imagery-based signals. However, the formulation of the conventional CSP based on the L2-norm is sensitive to outliers. Whereas the L1-norm-based common spatial pattern (CSP-L1) proposed in recent years can seek robust spatial filters to effectively alleviate the impact of outliers, the L1-norm is unable to characterize the geometric structure of the data well. To further improve the robustness of CSP, in this paper, we propose a new extension to CSP called the L21-norm-based common spatial pattern (CSP-L21), which is formulated by using the L21-norm rather than the L2-norm. Moreover, CSP-L21 has the advantages of rotational invariance and geometric structure characterization. We provide a non-greedy iterative algorithm to maximize the objective function of CSP-L21. Experiments on a toy example and three popular data sets of BCI competitions illustrate that the proposed method can efficiently extract discriminative features.
previous article Finite Time Synchronization of Delayed Quaternion Valued Neural Networks with Fractional Order
next article PU Active Learning for Recommender Systems
Literature
1.
Blankertz B, Tomioka R, Lemm S et al (2008) Optimizing spatial filters for robust EEG single-trial analysis. IEEE Signal Process Mag 25(1):41–56 CrossRef
2.
Chaudhary U, Birbaumer N, Ramos-Murguialday A (2016) Brain-computer interfaces for communication and rehabilitation. Nat Rev Neurol 12(9):513–525 CrossRef
3.
Grosse-Wentrup M, Liefhold C, Gramann K et al (2009) Beamforming in noninvasive brain–computer interfaces. IEEE Trans Biomed Eng 56(4):1209–1219 CrossRef
4.
Dornhege G, Blankertz B, Curio G et al (2004) Boosting bit rates in non-invasive EEG single-trial classifications by feature combination and multi-class paradigms. IEEE Trans Biomed Eng 51(6):993–1002 CrossRef
5.
Wang H, Tang Q, Zheng W (2012) L1-norm-based common spatial patterns. IEEE Trans Biomed Eng 59(3):653–662 CrossRef
6.
Fang N, Wang H (2017) Generalization of local temporal correlation common spatial patterns using Lp-norm (0<p<2). In: International Conference on Neural Information Processing, pp 769–777
7.
Wang H, Zheng W (2008) Local temporal common spatial patterns for robust single-trial EEG classification. IEEE Trans Neural Syst Rehabil Eng 16(2):131–139 CrossRef
8.
Ding C, Zhou D, He X et al (2006) R1-PCA: rotational invariant L1-norm principal component analysis for robust subspace factorization. In: International Conference on Machine Learning, pp 281–288
9.
Yang Y, Shen H, Ma Z et al (2011) L2, 1-norm regularized discriminative feature selection for unsupervised learning. In: International Joint Conference on Artificial Intelligence, pp 1589–1594
10.
Liao S, Gao Q, Yang Z et al (2018) Discriminant analysis via joint Euler transform and ℓ2,1-norm. IEEE Trans Image Process 27(11):5668–5682 MathSciNetCrossRef
11.
Liu Y, Gao Q, Gao X et al (2018) L2,1-norm discriminant manifold learning. IEEE Access 6:40723–40734 CrossRef
12.
Nie F, Huang H, Cai X et al (2010) Efficient and robust feature selection via joint l2, 1-norms minimization. In: Proceedings of the Conference on Neural Information Processing Systems, pp 1813–1821
13.
Luo M, Nie F, Chang X et al (2016) Avoiding optimal mean robust PCA/2DPCA with non-greedy L1-norm maximization. In: Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, pp 1802–1808
14.
Blankertz B, Kawanabe M, Tomioka R et al (2008) Invariant common spatial patterns: Alleviating nonstationarities in brain-computer interfacing. In: Proceedings of the Conference on Neural Information Processing Systems, pp 113–120
15.
Lotte F, Guan C (2011) Regularizing common spatial patterns to improve BCI designs: unified theory and new algorithms. IEEE Trans Biomed Eng 58(2):355–362 CrossRef
16.
Kawanabe M, Vidaurre C (2009) Improving BCI performance by modified common spatial patterns with robustly averaged covariance matrices. In: World Congress on Medical Physics and Biomedical Engineering, pp 279–282
17.
Ledoit O, Wolf M (2004) A well-conditioned estimator for large-dimensional covariance matrices. J Multivar Anal 88(2):365–411 MathSciNetCrossRef
18.
Li X, Wang H (2013) Smooth spatial filter for common spatial patterns. In: International Conference on Neural Information Processing, pp 315–322
19.
Li X, Lu X, Wang H (2016) Robust common spatial patterns with sparsity. Biomed Signal Process Control 26:52–57 CrossRef
20.
Wang H, Li X (2016) Regularized filters for L1-norm-based common spatial patterns. IEEE Trans Neural Syst Rehabil Eng 24(2):201–211 CrossRef
21.
Deng Y, Li Z, Wang H et al (2020) Local temporal joint recurrence common spatial patterns for MI-based BCI. In: 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference, pp 813–816
22.
Yong X, Ward R, Birch G (2008) Robust common spatial patterns for EEG signal preprocessing. In: 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp 2087–2090
23.
Aljalal M, Djemal R, Ibrahim S (2019) Robot navigation using a brain computer interface based on motor imagery. J Med Biol Eng 39(4):508–522 CrossRef
24.
Webb A (1999) Statistical Pattern Recognition. United Kingdom, London MATH
25.
Wolpaw J, Birbaumer N, McFarland D et al (2002) Brain-computer interfaces for communication and control. Clin Neurophysiol 113(6):767–791 CrossRef
26.
Parra L, Spence C, Gerson A et al (2005) Recipes for linear analysis of EEG. Neuroimage 28(2):326–341 CrossRef
27.
Pfurtscheller G, Silva F (1999) Event-related EEG/MEG synchronization and desynchronization: basic principles. Clin Neurophysiol 110(11):1842–1857 CrossRef
28.
Zhao Y, Han J, Chen Y et al (2018) Improving generalization based on L1-norm regularization for EEG-based motor imagery classification. Front Neurosci 12:272 CrossRef
29.
Tang Q, Wang J, Wang H (2014) L1-norm based discriminative spatial pattern for single-trial EEG classification. Biomed Signal Process Control 10(3):313–321 CrossRef
30.
Huang L, Gu J, Li R et al (2013) A novel BCI classifier based on autoregressive model and support vector machine. Adv Mater Res 694–697:2522–2525 CrossRef
31.
Aboy M, McNames J, Márquez O et al (2004) Power spectral density estimation and tracking nonstationary pressure signals based on Kalman filtering. The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 1:156–159
32.
Adeli H, Zhou Z, Dadmehr N (2003) Analysis of EEG records in an epileptic patient using wavelet transform. J Neurosci Methods 123(1):69–87 CrossRef
33.
Delorme A, Sejnowski T, Makeig S (2007) Enhanced detection of artifacts in EEG data using higher-order statistics and independent component analysis. Neuroimage 34(4):1443–1449 CrossRef
Metadata
Title
Common Spatial Pattern with L21-Norm
Authors
Jingyu Gu
Mengting Wei
Yiyun Guo
Haixian Wang
Publication date
29-06-2021
Publisher
Springer US
Published in
Neural Processing Letters / Issue 5/2021
Print ISSN: 1370-4621
Electronic ISSN: 1573-773X
DOI
https://doi.org/10.1007/s11063-021-10567-x

Other articles of this Issue 5/2021

Neural Processing Letters 5/2021 Go to the issue

OriginalPaper

Combining Embeddings of Input Data for Text Classification

OriginalPaper

Named Entity Recognition by Using XLNet-BiLSTM-CRF

OriginalPaper

Progressive Transfer Learning Approach for Identifying the Leaf Type by Optimizing Network Parameters

OriginalPaper

Continuous-Time Varying Complex QR Decomposition via Zeroing Neural Dynamics

Correction

Correction to: Modeling Axonal Plasticity in Artificial Neural Networks

OriginalPaper

Finite/Fixed-Time Synchronization of Delayed Inertial Memristive Neural Networks with Discontinuous Activations and Disturbances