Comparison of Classification Methods for P300 Brain-Computer Interface on Disabled Subjects

Manyakov, Nikolay V.; Chumerin, Nikolay; Combaz, Adrien; Hulle, Marc M. Van

doi:10.1155/2011/519868

Cited by 90 publications

(65 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Furthermore, the inclusion of all recorded channels instead of only three pre-selected channels, together with automated channel selection algorithms, might also yield better classification results. The use of non-linear classifiers such as support vector machines (SVMs) that are superior to SWLDA [43] might also be beneficial. However, due to the low number of trials, there is a high risk of overfitting the data when using a non-linear classifier.…”

Section: Discussionmentioning

confidence: 99%

The auditory P300-based single-switch brain–computer interface: Paradigm transition from healthy subjects to minimally conscious patients

Pokorny

Klobassa

Pichler

et al. 2013

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

Objective: Within this work an auditory P300 brain-computer interface (BCI) based on tone stream segregation, which allows for binary decisions, was developed and evaluated. Materials and methods: Two tone streams consisting of short beep tones with infrequently appearing deviant tones at random positions were used as stimuli. This paradigm was evaluated in 10 healthy subjects and applied to 12 patients in a minimally conscious state (MCS) at clinics in Graz, Würzburg, Rome, and Liège. A stepwise linear discriminant analysis (SWLDA) classifier with 10 × 10 cross-validation was used to detect the presence of any P300 and to investigate attentional modulation of the P300 amplitude. Results:The results for healthy subjects were promising and most classification results were better than random. However, for MCS patients only a small number of classification results were above chance level and none of the results were sufficient for communication purposes. Nevertheless, signs of consciousness were detected in most patients, not on a single-trial basis, but after averaging of corresponding data segments and computing significant differences. These significant results, however, strongly varied across sessions and conditions. Conclusion: This work shows the transition of a paradigm from healthy subjects to MCS patients. Promising results with healthy subjects are, however, no guarantee of good results with patients. Therefore, more investigations are required before any definite conclusions about the usability of this paradigm for MCS patients can be drawn. Nevertheless, this paradigm might offer an opportunity to support bedside clinical assessment of MCS patients and eventually, to provide them with a means of communication.

show abstract

Section: Discussionmentioning

confidence: 99%

The auditory P300-based single-switch brain–computer interface: Paradigm transition from healthy subjects to minimally conscious patients

Pokorny

Klobassa

Pichler

et al. 2013

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

show abstract

“…Different research had been studied on the P300 BCI applications to detect the P300 signal using different classification methods either linear or nonlinear such as, LDA, linear support vector machine (SVM), Gaussian kernel support vector machine, and NN [33].…”

Section: Other Approaches For P300 Classificationmentioning

confidence: 99%

EEG subspace analysis and classification using principal angles for Brain-Computer Interfaces

Ashari

Anderson

2014

2014 IEEE Symposium on Computational Intelligence in Brain Computer Interfaces (CIBCI)

View full text Add to dashboard Cite

This dissertation studies and examines different ideas using principal angles and subspaces concepts. It introduces a novel mathematical approach for comparing sets of EEG signals for use in new BCI technology. The success of the presented results show that principal angles are also a useful approach to the classification of EEG signals that are recorded during a BCI typing application. In this application, the appearance of a subject's desired letter is detected by identifying a P300-wave within a one-second window of EEG following the flash of a letter. Smoothing the signals before using them is the only preprocessing step that was implemented in this study. The smoothing process based on minimizing the second derivative in time is implemented to increase the classification accuracy instead of using the bandpass filter that relies on assumptions on the frequency content of EEG. This study examines four different ways of removing outliers that are based on the principal angles and shows that the outlier removal methods did not help in the presented situations.ii One of the concepts that this dissertation focused on is the effect of the number of trials on the classification accuracies. The achievement of the good classification results by using a small number of trials starting from two trials only, should make this approach more appropriate for online BCI applications.In order to understand and test how EEG signals are different from one subject toanother, different users are tested in this dissertation, some with motor impairments. Furthermore, the concept of transferring information between subjects is examined by training the approach on one subject and testing it on the other subject using the training subject's EEG subspaces to classify the testing subject's trials.iii

show abstract

“…This allows to single actions only (such as a keypress) by means of a scanning system. It requires high concentration [12] and is not usable for the moment on a mobile device because it requires too much resources and heavy equipment. Moreover, this system has a high error rate (80% [12]).…”

Section: Related Workmentioning

confidence: 99%

Towards a Communication System for People with Athetoid Cerebral Palsy

Guerrier

Kolski

Poirier

2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract.Communication is an important act in the development and empowerment of human beings. Through language, humans communicate their needs, desires, moods... Unfortunately, many physical and mental disabilities deprive some people of such communication means. Nowadays various Augmentative and Alternative Communication (AAC) systems exist in order to help people with disabilities. Virtual keyboards are the most common AAC systems for physical disabilities. Concerning mental disability, there are tools based on pictograms. This paper is divided into two parts. First, we put forward a critical review of various AAC systems with a focus on users with athetoid cerebral palsy. Second, the paper presents work in progress concerning a communication system for such users.

show abstract

Comparison of Classification Methods for P300 Brain-Computer Interface on Disabled Subjects

Cited by 90 publications

References 30 publications

The auditory P300-based single-switch brain–computer interface: Paradigm transition from healthy subjects to minimally conscious patients

The auditory P300-based single-switch brain–computer interface: Paradigm transition from healthy subjects to minimally conscious patients

EEG subspace analysis and classification using principal angles for Brain-Computer Interfaces

Towards a Communication System for People with Athetoid Cerebral Palsy

Contact Info

Product

Resources

About