Article

Single-trial detection in EEG and MEG: Keeping it linear

Department of Biomedical Engineering, Columbia University, New York, New York, United States
Neurocomputing (Impact Factor: 2.08). 06/2003; 52-54:177-183. DOI: 10.1016/S0925-2312(02)00821-4
Source: DBLP

ABSTRACT

Conventional electroencephalography (EEG) and magnetoencephalography (MEG) analysis often rely on averaging over multiple trials to extract statistically relevant differences between two or more experimental conditions. We demonstrate that by linearly integrating information over multiple spatially distributed sensors within a predefined time window, one can discriminate conditions on a trial-by-trial basis with high accuracy. We restrict ourselves to a linear integration as it allows the computation of a spatial distribution of the discriminating source activity. In the present set of experiments the resulting source activity distributions correspond to functional neuroanatomy consistent with the task (e.g. contralateral sensory-motor cortex and anterior cingulate).

Download full-text

Full-text

Available from: Barak A. Pearlmutter
  • Source
    • "Nowadays the scope of modern neuroscience has been widened to decoding single-trial encephalogram data with respect to the identification of mental states or human intentions. This branch of research is strongly influenced by the development of an effective communication interface connecting the human brain and a computer ([19] [33] [35] [76] [5] [52] [16] [77] [34]), which finally also attracted the machine learning community to the field [6] [69] [27] [47] [11] [50] [7] [8] [74] [49] [67]. In this context the ability to perform single-trial classification of EEG data received much attention. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Analyzing brain states that correspond to event related potentials (ERPs) on a single trial basis is a hard problem due to the high trial-to-trial variability and the unfavorable ratio between signal (ERP) and noise (artifacts and neural background activity). In this tutorial, we provide a comprehensive framework for decoding ERPs, elaborating on linear concepts, namely spatio-temporal patterns and filters as well as linear ERP classification. However, the bottleneck of these techniques is that they require an accurate covariance matrix estimation in high dimensional sensor spaces which is a highly intricate problem. As a remedy, we propose to use shrinkage estimators and show that appropriate regularization of linear discriminant analysis (LDA) by shrinkage yields excellent results for single-trial ERP classification that are far superior to classical LDA classification. Furthermore, we give practical hints on the interpretation of what classifiers learned from the data and demonstrate in particular that the trade-off between goodness-of-fit and model complexity in regularized LDA relates to a morphing between a difference pattern of ERPs and a spatial filter which cancels non task-related brain activity.
    Full-text · Article · May 2011 · NeuroImage
  • Source
    • "To this end, there is often an initial calibration period, in which signals are acquired while the user generates control commands according to cues without receiving feedback. Machine learning algorithms are applied to these labeled data to infer features (e.g., spatial filters, frequency bands) that are optimized for the BCI performance of the individual user (Blankertz et al., 2002, 2007a; Parra et al., 2003; Dornhege et al., 2007a). In Blankertz et al. (2008b) we investigated which proportion of naive subjects could successfully use an SMR-based system in the very first session. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Brain-computer interfacing (BCI) is a steadily growing area of research. While initially BCI research was focused on applications for paralyzed patients, increasingly more alternative applications in healthy human subjects are proposed and investigated. In particular, monitoring of mental states and decoding of covert user states have seen a strong rise of interest. Here, we present some examples of such novel applications which provide evidence for the promising potential of BCI technology for non-medical uses. Furthermore, we discuss distinct methodological improvements required to bring non-medical applications of BCI technology to a diversity of layperson target groups, e.g., ease of use, minimal training, general usability, short control latencies.
    Full-text · Article · Dec 2010 · Frontiers in Neuroscience
  • Source
    • "Nowadays the scope of modern neuroscience has been widened to decoding single-trial encephalogram data with respect to the identification of mental states or human intentions. This branch of research is strongly influenced by the development of an effective communication interface connecting the human brain and a computer ([19] [33] [35] [76] [5] [52] [16] [77] [34]), which finally also attracted the machine learning community to the field [6] [69] [27] [47] [11] [50] [7] [8] [74] [49] [67]. In this context the ability to perform single-trial classification of EEG data received much attention. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Analyzing brain states that correspond to event related potentials (ERPs) on a single trial basis is a hard problem due to the high trial-to-trial variability and the unfavorable ratio between signal (ERP) and noise (artifacts and neural background activity). In this tutorial, we provide a comprehensive framework for decoding ERPs, elaborating on linear concepts, namely spatio-temporal patterns and filters as well as linear ERP classification. However, the bottleneck of these techniques is that they require an accurate covariance matrix estimation in high dimensional sensor spaces which is a highly intricate problem. As a remedy, we propose to use shrinkage estimators and show that appropriate regularization of linear discriminant analysis (LDA) by shrinkage yields excellent results for single-trial ERP classification that are far superior to classical LDA classification. Furthermore, we give practical hints on the interpretation of what classifiers learned from the data and demonstrate in particular that the trade-off between goodness-of-fit and model complexity in regularized LDA relates to a morphing between a difference pattern of ERPs and a spatial filter which cancels non task-related brain activity.
    Full-text · Article · Jan 2010 · NeuroImage
Show more