Integrating dynamic stopping, transfer learning and language models in an adaptive zero-training ERP speller

Kindermans, Pieter Jan; Tangermann, Michael; Müller, Klaus Robert; Schrauwen, Benjamin

doi:10.1088/1741-2560/11/3/035005

Cited by 86 publications

(68 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We employed the widely-used "subsampling approach" (Höhne et al, 2012;Kindermans et al, 2014) for feature extraction: we first epoched the EEG data [− 150 800] ms relative to stimulus onset and baselined them between [−150 0] ms. EEG epochs containing eye artifacts were excluded by an heuristic, cf. Höhne et al (2012).…”

Section: Feature Extraction and Classificationmentioning

confidence: 99%

Analyzing neuroimaging data with subclasses: A shrinkage approach

et al. 2016

Self Cite

View full text Add to dashboard Cite

Section: Feature Extraction and Classificationmentioning

confidence: 99%

Analyzing neuroimaging data with subclasses: A shrinkage approach

et al. 2016

Self Cite

View full text Add to dashboard Cite

“…Especially, we observed that for some users (3,4,8,9, and 10), the proposed method may achieve comparable or higher accuracies than CCA.…”

Section: Discussionmentioning

confidence: 87%

“…Transfer learning may be a possible solution to reduce the calibration requirements [3]. This approach has been applied to event-related potential (ERP) Brain-Computer Interfaces in order to create zero training systems [4]. Transfer learning approaches have also been used to develop collaborative BCI systems with multiple simultaneous users [5,6].…”

Section: Introductionmentioning

confidence: 99%

Transfer Learning for SSVEP Electroencephalography Based Brain–Computer Interfaces Using Learn++.NSE and Mutual Information

Sybeldon

Schmit

Akçakaya

2017

Entropy

View full text Add to dashboard Cite

Brain-Computer Interfaces (BCI) using Steady-State Visual Evoked Potentials (SSVEP) are sometimes used by injured patients seeking to use a computer. Canonical Correlation Analysis (CCA) is seen as state-of-the-art for SSVEP BCI systems. However, this assumes that the user has full control over their covert attention, which may not be the case. This introduces high calibration requirements when using other machine learning techniques. These may be circumvented by using transfer learning to utilize data from other participants. This paper proposes a combination of ensemble learning via Learn++ for Nonstationary Environments (Learn++.NSE)and similarity measures such as mutual information to identify ensembles of pre-existing data that result in higher classification. Results show that this approach performed worse than CCA in participants with typical SSVEP responses, but outperformed CCA in participants whose SSVEP responses violated CCA assumptions. This indicates that similarity measures and Learn++.NSE can introduce a transfer learning mechanism to bring SSVEP system accessibility to users unable to control their covert attention.

show abstract

“…Our Bayesian dynamic stopping algorithm is similar to other algorithms used in the BCI literature, e.g. [42, 43], and so our performance prediction method using the detectability index can be relevant for these algorithms. Other algorithms may require the development of alternative statistical measures to quantify performance levels, as the use of detectability index parameter might not always be suitable.…”

Section: Discussionmentioning

confidence: 99%

Using the detectability index to predict P300 speller performance

Mainsah

Collins²,

Throckmorton³

2016

J. Neural Eng.

View full text Add to dashboard Cite

Objective The P300 speller is a popular brain-computer interface (BCI) system that has been investigated as a potential communication alternative for individuals with severe neuromuscular limitations. To achieve acceptable accuracy levels for communication, the system requires repeated data measurements in a given signal condition to enhance the signal-to-noise ratio of elicited brain responses. These elicited brain responses, which are used as control signals, are embedded in noisy electroencephalography (EEG) data. The discriminability between target and non-target EEG responses defines a user’s performance with the system. A previous P300 speller model has been proposed to estimate system accuracy given a certain amount of data collection. However, the approach was limited to a static stopping algorithm, i.e. averaging over a fixed number of measurements, and the row-column paradigm. A generalized method that is also applicable to dynamic stopping algorithms and other stimulus paradigms is desirable. Approach We developed a new probabilistic model-based approach to predicting BCI performance, where performance functions can be derived analytically or via Monte Carlo methods. Within this framework, we introduce a new model for the P300 speller with the Bayesian dynamic stopping (DS) algorithm, by simplifying a multi-hypothesis to a binary hypothesis problem using the likelihood ratio test. Under a normality assumption, the performance functions for the Bayesian algorithm can be parameterized with the detectability index, a measure which quantifies the discriminability between target and non-target EEG responses. Main results Simulations with synthetic and empirical data provided initial verification of the proposed method of estimating performance with Bayesian DS using the detectability index. Analysis of results from previous online studies validated the proposed method. Significance The proposed method could serve as a useful tool to initially asses BCI performance without extensive online testing, in order to estimate the amount of data required to achieve a desired accuracy level.

show abstract

Integrating dynamic stopping, transfer learning and language models in an adaptive zero-training ERP speller

Cited by 86 publications

References 29 publications

Analyzing neuroimaging data with subclasses: A shrinkage approach

Analyzing neuroimaging data with subclasses: A shrinkage approach

Transfer Learning for SSVEP Electroencephalography Based Brain–Computer Interfaces Using Learn++.NSE and Mutual Information

Using the detectability index to predict P300 speller performance

Contact Info

Product

Resources

About