EEG error-related potentials detection with a Bayesian filter

Bollon, Jean-Marc; Chavarriaga, Ricardo; Millán, José del R.; Bessìère, Pierre

doi:10.1109/ner.2009.5109393

Cited by 8 publications

(7 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work we assess, for the first time, single-trial recognition of EEG errorrelated potentials in a complex, realistic task. This contrasts with previously reported experiments where these signals were studied using very simple stimuli, and subjects movements were restricted to minimize motion-related artifacts in the EEG signal [23,19,24]. The difference in the experimental protocol -i.e.…”

Section: Influence Of the Errp Detection Accuracy On The Adaptationmentioning

confidence: 77%

“…Following previous studies [23,19], we perform classification using the time signal of electrodes FCz and Cz as input features for a Bayesian filter [24], since EEG ErrP are characterized by a fronto-central distribution along the midline. EEG potentials were spatially filtered by subtracting from each electrode the average potential (i.e.…”

Section: Eeg-errp Single-trial Recognitionmentioning

confidence: 99%

See 1 more Smart Citation

On the Use of Brain Decoded Signals for Online User Adaptive Gesture Recognition Systems

Förster

Biasiucci

Chavarriaga

et al. 2010

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Activity and context recognition in pervasive and wearable computing ought to continuously adapt to changes typical of open-ended scenarios, such as changing users, sensor characteristics, user expectations, or user motor patterns due to learning or aging. System performance inherently relates to the user's perception of the system behavior. Thus, the user should be guiding the adaptation process. This should be automatic, transparent, and unconscious. We capitalize on advances in electroencephalography (EEG) signal processing that allow for error related potentials (ErrP) recognition. ErrP are emitted when a human observes an unexpected behavior in a system. We propose and evaluate a hand gesture recognition system from wearable motion sensors that adapts online by taking advantage of ErrP. Thus the gesture recognition system becomes self-aware of its performance, and can self-improve through re-occurring detection of ErrP signals. Results show that our adaptation technique can improve the accuracy of a user independent gesture recognition system by 9.58% when ErrP recognition is perfect. When ErrP recognition errors are factored in, recognition accuracy increases by 3.29%. We characterize the boundary conditions of ErrP recognition guaranteeing beneficial adaptation. The adaptive algorithms are applicable to other forms of activity recognition, and can also use explicit user feedback rather than ErrP.

show abstract

Section: Influence Of the Errp Detection Accuracy On The Adaptationmentioning

confidence: 77%

Section: Eeg-errp Single-trial Recognitionmentioning

confidence: 99%

On the Use of Brain Decoded Signals for Online User Adaptive Gesture Recognition Systems

Förster

Biasiucci

Chavarriaga

et al. 2010

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…We rely on a Bayesian filtering technique so as to take into account the time course of the evoked signal, while providing a probabilistic output that can be used as a measure of the reliability of the estimated state [10]. This technique is based on recursive Bayesian estimations, where at each time step the state estimation (i.e.…”

Section: Classification Using Bayesian Filteringmentioning

confidence: 99%

Adaptation of hybrid human-computer interaction systems using EEG error-related potentials

Chavarriaga

Biasiucci

Förster

et al. 2010

2010 Annual International Conference of the IEEE Engineering in Medicine and Biology

Self Cite

View full text Add to dashboard Cite

Abstract-Performance improvement in both humans and artificial systems strongly relies in the ability of recognizing erroneous behavior or decisions. This paper, that builds upon previous studies on EEG error-related signals, presents a hybrid approach for human computer interaction that uses human gestures to send commands to a computer and exploits uses brain activity to provide implicit feedback about the recognition of such commands. Using a simple computer game as a case study, we show that EEG activity evoked by erroneous gesture recognition can be classified in single trials above random levels. Automatic artifact rejection techniques are used, taking into account that subjects are allowed to move during the experiment. Moreover, we present a simple adaptation mechanism, that uses the EEG signal to label newly acquired samples that can be use to re-calibrate the gesture recognition system in a supervised manner. Offline analysis show that, although the achieved EEG decoding accuracy is far from being perfect, these signals convey sufficient information to significantly improve the overall system performance. These studies have been typically performed during control of simulated devices where the subject is asked to limit its movements in order to avoid artifact contamination of the EEG signals. It is therefore, not yet clear whether this type of signals can be detected or exploited in less restrictive conditions. One of the goals of this work is to address precisely this issue. Moreover, the idea of hybrid systemsi.e. based on different communication channels-has been put forward recently as a way to improve the performance and usability of BCI systems and neuroprostheses [7]. We argue that the hybrid approach can exploit the brain activity to convey information about the subject cognitive and perceptual state, while control commands can be delivered using faster,

show abstract

“…In neuroscience, recent approaches evaluating the performance of brain-computer interfaces are trying to find a more direct and intuitive measure of performance in imbalanced cases (Zhang et al, 2007 ; Hohne and Tangermann, 2012 ; Salvaris et al, 2012 ; Feess et al, 2013 ). However, the decision for a single metric is often avoided by keeping the numbers for the two classes separated (e.g., Bollon et al, 2009 ; Kimura et al, 2010 ).…”

Section: Existing Approaches To Deal With Imbalancementioning

confidence: 99%

How to evaluate an agent's behavior to infrequent events?—Reliable performance estimation insensitive to class distribution

Straube

Krell

2014

Front. Comput.. Neurosci.

View full text Add to dashboard Cite

In everyday life, humans and animals often have to base decisions on infrequent relevant stimuli with respect to frequent irrelevant ones. When research in neuroscience mimics this situation, the effect of this imbalance in stimulus classes on performance evaluation has to be considered. This is most obvious for the often used overall accuracy, because the proportion of correct responses is governed by the more frequent class. This imbalance problem has been widely debated across disciplines and out of the discussed treatments this review focusses on performance estimation. For this, a more universal view is taken: an agent performing a classification task. Commonly used performance measures are characterized when used with imbalanced classes. Metrics like Accuracy, F-Measure, Matthews Correlation Coefficient, and Mutual Information are affected by imbalance, while other metrics do not have this drawback, like AUC, d-prime, Balanced Accuracy, Weighted Accuracy and G-Mean. It is pointed out that one is not restricted to this group of metrics, but the sensitivity to the class ratio has to be kept in mind for a proper choice. Selecting an appropriate metric is critical to avoid drawing misled conclusions.

show abstract

EEG error-related potentials detection with a Bayesian filter

Cited by 8 publications

References 8 publications

On the Use of Brain Decoded Signals for Online User Adaptive Gesture Recognition Systems

On the Use of Brain Decoded Signals for Online User Adaptive Gesture Recognition Systems

Adaptation of hybrid human-computer interaction systems using EEG error-related potentials

How to evaluate an agent's behavior to infrequent events?—Reliable performance estimation insensitive to class distribution

Contact Info

Product

Resources

About