Mean shrinkage improves the classification of ERP signals by exploiting additional label information
- 1 June 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Abstract
Linear discriminant analysis (LDA) is the most commonly used classification method for single trial data in a brain-computer interface (BCI) framework. The popularity of LDA arises from its robustness, simplicity and high accuracy. However, the standard LDA approach is not capable to exploit sublabel information (such as stimulus identity), which is accessible in data from event related potentials (ERPs): it assumes that the evoked potentials are independent of the stimulus identity and dependent only on the users' attentional state. We question this assumption and investigate several methods which extract subclass-specific features from ERP data. Moreover, we propose a novel classification approach which exploits subclass-specific features using mean shrinkage. Based on a reanalysis of two BCI data sets, we show that our novel approach outperforms the standard LDA approach, while being computationally highly efficient.Keywords
This publication has 12 references indexed in Scilit:
- Classifying P300 responses to vowel stimuli for auditory brain-computer interface2013
- Natural stimuli improve auditory BCIs with respect to ergonomics and performanceJournal of Neural Engineering, 2012
- A Bayesian Model for Exploiting Application Constraints to Enable Unsupervised Training of a P300-based BCIPLOS ONE, 2012
- Introduction to machine learning for brain imagingNeuroImage, 2011
- Single-trial analysis and classification of ERP components — A tutorialNeuroImage, 2011
- Listen, You are Writing! Speeding up Online Spelling with a Dynamic Auditory BCIFrontiers in Neuroscience, 2011
- A novel 9-class auditory ERP paradigm driving a predictive text entry systemFrontiers in Neuroscience, 2011
- The Berlin Brain–Computer Interface: Non-Medical Uses of BCI TechnologyFrontiers in Neuroscience, 2010
- (C)overt attention and visual speller design in an ERP-based brain-computer interfaceBehavioral and Brain Functions, 2010
- A well-conditioned estimator for large-dimensional covariance matricesJournal of Multivariate Analysis, 2004