Single-Trial Classification of Multi-User P300-Based Brain-Computer Interface Using Riemannian Geometry

Louis Korczowski; Marco Congedo; Christian Jutten

Single-Trial Classification of Multi-User P300-Based Brain-Computer Interface Using Riemannian Geometry

Louis Korczowski ¹ Marco Congedo ¹ Christian Jutten ¹

1 GIPSA-VIBS - VIBS

GIPSA-DIS - Département Images et Signal

Abstract : The classification of electroencephalographic (EEG) data recorded from multiple users simultaneously is an important challenge in the field of Brain-Computer Interface (BCI). In this paper we compare different approaches for classification of single-trials Event-Related Potential (ERP) on two subjects playing a collaborative BCI game. The minimum distance to mean (MDM) classifier in a Riemannian framework is extended to use the diversity of the inter-subjects spatio-temporal statistics (MDM-hyper) or to merge multiple classifiers (MDM-multi). We show that both these classifiers outperform significantly the mean performance of the two users and analogous classifiers based on the step-wise linear discriminant analysis. More importantly, the MDM-multi outperforms the performance of the best player within the pair.

Keywords : Coherence in biomedical signal processing Multivariate signal processing Machine Learning Biosignals classification Electroencephalography Multi-User BCI Hyperscanning Minimum To Mean Distance Riemannian Geometry Classification EEG Brain-Computer Interface Biomedical signal classification BCI

Document type :

Conference papers

Domain :

Statistics [stat] / Machine Learning [stat.ML]

Mathematics [math] / Differential Geometry [math.DG]

Engineering Sciences [physics] / Signal and Image processing

Cognitive science / Neuroscience

Mathematics [math] / Metric Geometry [math.MG]

Complete list of metadatas

Cited literature [11 references] Display Hide Download

https://hal.archives-ouvertes.fr/hal-01191913
Contributor : Louis Korczowski <>
Submitted on : Thursday, September 3, 2015 - 5:16:29 PM
Last modification on : Tuesday, July 9, 2019 - 1:21:25 AM
Long-term archiving on : Friday, December 4, 2015 - 10:27:28 AM

KORCZOWSKI_CONGEDO_JUTTEN_EMBC...

Files produced by the author(s)

Single-Trial Classification of Multi-User P300-Based Brain-Computer Interface Using Riemannian Geometry

File

Identifiers

Collections

Citation

Export

Metrics

1053

462

Contact

Single-Trial Classification of Multi-User P300-Based Brain-Computer Interface Using Riemannian Geometry

File

Identifiers

Collections

Citation

Export

Share

Metrics

1053

462

Contact