Bayesian common spatial patterns for multi-subject EEG classification

Kang, Hyohyeong; Choi, Seungjin

doi:10.1016/j.neunet.2014.05.012

Cited by 82 publications

(41 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, machine learning-based BCI models were introduced to reduce individual training session for each BCI use, in which a model has to be calibrated based on the data at the beginning of each session (Ramoser et al, 2000;Blankertz et al, 2002). Recent studies have proposed SMR-based BCI without any session-and subject-specific calibration utilizing the concept of transfer learning (Kang et al, 2009;Li et al, 2010;Lu et al, 2010;Niazi et al, 2013;Kang and Choi, 2014;Fazli et al, 2015;Lotte, 2015;Jayaram et al, 2016;Saha et al, 2017aSaha et al, ,b, 2019Fahimi et al, 2018;He and Wu, 2019).…”

Section: Covariate Shift and Transfer Learningmentioning

confidence: 99%

“…Most of the existing transfer learning approaches are based on regularization or inter-session/subject transfer of model parameters, indirectly transferring knowledge pertaining to the sources of intra-and inter-subject variability (Samek et al, 2013;Lotte, 2015). Many works on transfer learning for SMRbased BCI proposed the use of a very few training samples from the target subject (Kang et al, 2009;Lu et al, 2010;Kang and Choi, 2014;Fahimi et al, 2018;He and Wu, 2019). Recent studies have utilized resting EEG from the target subject incorporated into transfer learning model before proceeding to the actual experiment (Suk et al, 2014;Morioka et al, 2015).…”

Section: The Concept Of Inter-subject Associativitymentioning

confidence: 99%

See 1 more Smart Citation

Intra- and Inter-subject Variability in EEG-Based Sensorimotor Brain Computer Interface: A Review

Saha

Baumert

2020

Front. Comput. Neurosci.

154

109

View full text Add to dashboard Cite

Brain computer interfaces (BCI) for the rehabilitation of motor impairments exploit sensorimotor rhythms (SMR) in the electroencephalogram (EEG). However, the neurophysiological processes underpinning the SMR often vary over time and across subjects. Inherent intra-and inter-subject variability causes covariate shift in data distributions that impede the transferability of model parameters amongst sessions/subjects. Transfer learning includes machine learning-based methods to compensate for inter-subject and inter-session (intra-subject) variability manifested in EEG-derived feature distributions as a covariate shift for BCI. Besides transfer learning approaches, recent studies have explored psychological and neurophysiological predictors as well as inter-subject associativity assessment, which may augment transfer learning in EEG-based BCI. Here, we highlight the importance of measuring inter-session/subject performance predictors for generalized BCI frameworks for both normal and motor-impaired people, reducing the necessity for tedious and annoying calibration sessions and BCI training.

show abstract

Section: Covariate Shift and Transfer Learningmentioning

confidence: 99%

Section: The Concept Of Inter-subject Associativitymentioning

confidence: 99%

Intra- and Inter-subject Variability in EEG-Based Sensorimotor Brain Computer Interface: A Review

Saha

Baumert

2020

Front. Comput. Neurosci.

154

109

View full text Add to dashboard Cite

show abstract

“…For example, Wolpaw et al in the early 90's chose weights for the α and µ rhythms and trained participants to modulate the bandpower in these frequency bands in order to control a cursor [1], 3 learning amounts to determining invariant spaces on which to project the data and learning classifiers in these spaces. This line of work has been further extended by Kang et al [17], [18], Lotte and Guan [19], and Devlaminck et al [20]. In these contributions, the authors demonstrate successful subject-to-subject transfer by regularizing spatial filters derived by CSP with data from other subjects, which amounts to attempting to find an invariant subspace on which to project the data of new subjects.…”

Section: Introductionmentioning

confidence: 92%

Transfer Learning in Brain-Computer Interfaces Abstract\uFFFDThe performance of brain-computer interfaces (BCIs) improves with the amount of avail

Jayaram¹,

Alamgir²,

Altün³

et al. 2016

IEEE Comput. Intell. Mag.

324

View full text Add to dashboard Cite

The performance of brain-computer interfaces (BCIs) improves with the amount of available training data; the statistical distribution of this data, however, varies across subjects as well as across sessions within individual subjects, limiting the transferability of training data or trained models between them. In this article, we review current transfer learning techniques in BCIs that exploit shared structure between training data of multiple subjects and/or sessions to increase performance. We then present a framework for transfer learning in the context of BCIs that can be applied to any arbitrary feature space, as well as a novel regression estimation method that is specifically designed for the structure of a system based on the electroencephalogram (EEG). We demonstrate the utility of our framework and method on subject-to-subject transfer in a motor-imagery paradigm as well as on session-to-session transfer in one patient diagnosed with amyotrophic lateral sclerosis (ALS), showing that it is able to outperform other comparable methods on an identical dataset.

show abstract

“…It is the requirement of future ubiquitous application of EEG instruments to capture the underlying consistency and inter-subject variations among EEG pa erns of di erent subjects. Kang et al [12] presented a Bayesian CSP model with Indian Bu et process (IBP) to investigate the shared latent subspace across subjects for EEG classi cation. eir experiments on two EEG datasets containing ve and nine subjects showed the superior performance of approximate 70% accuracy.…”

Section: Related Workmentioning

confidence: 99%

Multi-Person Brain Activity Recognition via Comprehensive EEG Signal Analysis

Zhang

Yao

Zhang

et al. 2018

Proceedings of the 14th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services

View full text Add to dashboard Cite

An electroencephalography (EEG) based brain activity recognition is a fundamental eld of study for a number of signi cant applications such as intention prediction, appliance control, and neurological disease diagnosis in smart home and smart healthcare domains. Existing techniques mostly focus on binary brain activity recognition for a single person, which limits their deployment in wider and complex practical scenarios. erefore, multi-person and multi-class brain activity recognition has obtained popularity recently. Another challenge faced by brain activity recognition is the low recognition accuracy due to the massive noises and the low signal-to-noise ratio in EEG signals. Moreover, the feature engineering in EEG processing is time-consuming and highly relies on the expert experience. In this paper, we a empt to solve the above challenges by proposing an approach which has be er EEG interpretation ability via raw Electroencephalography (EEG) signal analysis for multi-person and multi-class brain activity recognition. Speci cally, we analyze inter-class and inter-person EEG signal characteristics, based on which to capture the discrepancy of inter-class EEG data. en, we adopt an Autoencoder layer to automatically re ne the raw EEG signals by eliminating various artifacts. We evaluate our approach on both a public and a local EEG datasets and conduct extensive experiments to explore the e ect of several factors (such as normalization methods, training data size, and Autoencoder hidden neuron size) on the recognition results. e experimental results show that our approach achieves a high accuracy comparing to competitive state-of-the-art methods, indicating its potential in promoting future research on multi-person EEG recognition.

show abstract

Bayesian common spatial patterns for multi-subject EEG classification

Cited by 82 publications

References 26 publications

Intra- and Inter-subject Variability in EEG-Based Sensorimotor Brain Computer Interface: A Review

Intra- and Inter-subject Variability in EEG-Based Sensorimotor Brain Computer Interface: A Review

Transfer Learning in Brain-Computer Interfaces Abstract\uFFFDThe performance of brain-computer interfaces (BCIs) improves with the amount of avail

Multi-Person Brain Activity Recognition via Comprehensive EEG Signal Analysis

Contact Info

Product

Resources

About