Regularized common spatial patterns with subject-to-subject transfer of EEG signals

Cheng, Minmin; Zhang, Lu; Wang, Haixian

doi:10.1007/s11571-016-9417-x

Cited by 39 publications

(19 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to avoid overfitting and to improve generalization, both the covariance matrices and the objective function of CSP can be regularized towards a more generic filter decomposition by using additional regularization parameters 21 . Regularization of CSP has been found to improve inter-subject classification of EEG data 8 , 21 – 23 , but to our knowledge has not yet been applied to MEG data. Furthermore, the discriminatory power of CSP can be improved with preceding dimensionality reduction using e.g.…”

Section: Introductionmentioning

confidence: 99%

Across-subject offline decoding of motor imagery from MEG and EEG

Halme

Parkkonen

2018

Sci Rep

View full text Add to dashboard Cite

Long calibration time hinders the feasibility of brain-computer interfaces (BCI). If other subjects’ data were used for training the classifier, BCI-based neurofeedback practice could start without the initial calibration. Here, we compare methods for inter-subject decoding of left- vs. right-hand motor imagery (MI) from MEG and EEG. Six methods were tested on data involving MEG and EEG measurements of healthy participants. Inter-subject decoders were trained on subjects showing good within-subject accuracy, and tested on all subjects, including poor performers. Three methods were based on Common Spatial Patterns (CSP), and three others on logistic regression with l1 - or l2,1 -norm regularization. The decoding accuracy was evaluated using (1) MI and (2) passive movements (PM) for training, separately for MEG and EEG. With MI training, the best accuracies across subjects (mean 70.6% for MEG, 67.7% for EEG) were obtained using multi-task learning (MTL) with logistic regression and l2,1-norm regularization. MEG yielded slightly better average accuracies than EEG. With PM training, none of the inter-subject methods yielded above chance level (58.7%) accuracy. In conclusion, MTL and training with other subject’s MI is efficient for inter-subject decoding of MI. Passive movements of other subjects are likely suboptimal for training the MI classifiers.

show abstract

Section: Introductionmentioning

confidence: 99%

Across-subject offline decoding of motor imagery from MEG and EEG

Halme

Parkkonen

2018

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Even though regularization is of specific importance for ill-posed problems such as source reconstruction (Tian et al, 2013), less underdetermined problems can also profit. For CSP, a broad bandwidth of regularization approaches has been published, such as L1-and L2-norm penalties (Wang and Li, 2016;Lotte and Guan, 2011;Arvaneh et al, 2011;Farquhar et al, 2006), regularized transfer learning strategies that accumulate information across multiple sessions and subjects (Cheng et al, 2017;Devlaminck et al, 2011;Samek et al, 2013;Kang et al, 2009;Lotte and Guan, 2010) and variants which favor invariant solutions across sessions/runs under EEG non-stationarities (Arvaneh et al, 2013;Samek et al, 2012Samek et al, , 2014Cho et al, 2015).…”

Section: Introductionmentioning

confidence: 99%

Characterizing Regularization Techniques for Spatial Filter Optimization in Oscillatory EEG Regression Problems

et al. 2018

View full text Add to dashboard Cite

We report on novel supervised algorithms for single-trial brain state decoding. Their reliability and robustness are essential to efficiently perform neurotechnological applications in closed-loop. When brain activity is assessed by multichannel recordings, spatial filters computed by the source power comodulation (SPoC) algorithm allow identifying oscillatory subspaces. They regress to a known continuous trial-wise variable reflecting, e.g. stimulus characteristics, cognitive processing or behavior. In small dataset scenarios, this supervised method tends to overfit to its training data as the involved recordings via electroencephalogram (EEG), magnetoencephalogram or local field potentials generally provide a low signal-to-noise ratio. To improve upon this, we propose and characterize three types of regularization techniques for SPoC: approaches using Tikhonov regularization (which requires model selection via cross-validation), combinations of Tikhonov regularization and covariance matrix normalization as well as strategies exploiting analytical covariance matrix shrinkage. All proposed techniques were evaluated both in a novel simulation framework and on real-world data. Based on the simulation findings, we saw our expectations fulfilled, that SPoC regularization generally reveals the largest benefit for small training sets and under severe label noise conditions. Relevant for practitioners, we derived operating ranges of regularization hyperparameters for cross-validation based approaches and offer open source code. Evaluating all methods additionally on real-world data, we observed an improved regression performance mainly for datasets from subjects with initially poor performance. With this proof-of-concept paper, we provided a generalizable regularization framework for SPoC which may serve as a starting point for implementing advanced techniques in the future.

show abstract

“…Instead, LOSO scores are estimates of the generalization performance of the classifier onto new subjects, and it is therefore an estimate of transfer learning (Cheng et al. 2017 ). The choice of the LOSO validation approach was made to avoid biases in the estimates.…”

Section: Discussionmentioning

confidence: 99%

A cognitive brain–computer interface monitoring sustained attentional variations during a continuous task

2019

View full text Add to dashboard Cite

We introduce a cognitive brain-computer interface based on a continuous performance task for the monitoring of variations of visual sustained attention, i.e. the self-directed maintenance of cognitive focus in non-arousing conditions while possibly ignoring distractors and avoiding mind wandering. We introduce a visual sustained attention continuous performance task with three levels of task difficulty. Pairwise discrimination of these task difficulties from electroencephalographic features was performed using a leave-one-subject-out cross validation approach. Features were selected using the orthogonal forward regression supervised feature selection method. Cognitive load was best predicted using a combination of prefrontal theta power, broad spatial range gamma power, fronto-central beta power, and fronto-central alpha power. Generalization performance estimates for pairwise classification of task difficulty using these features reached 75% for 5 s epochs, and 85% for 30 s epochs.

show abstract

Regularized common spatial patterns with subject-to-subject transfer of EEG signals

Cited by 39 publications

References 28 publications

Across-subject offline decoding of motor imagery from MEG and EEG

Across-subject offline decoding of motor imagery from MEG and EEG

Characterizing Regularization Techniques for Spatial Filter Optimization in Oscillatory EEG Regression Problems

A cognitive brain–computer interface monitoring sustained attentional variations during a continuous task

Contact Info

Product

Resources

About