User menu

Accès à distance ? S'identifier sur le proxy UCLouvain

Inductive Means and Sequences Applied to Online Classification of EEG

Primary tabs

Massart, Estelle M. [UCL] Chevallier, Sylvain

The translation of brain activity into user command, through Brain-Computer Interfaces (BCI), is a very active topic in machine learning and signal processing. As commercial applications and out-of-the-lab solutions are proposed, there is an increased pressure to provide online algorithms and real-time implementations. Electroencephalography (EEG) systems offer lightweight and wearable solutions, at the expense of signal quality. Approaches based on covariance matrices have demonstrated good robustness to noise and provide a suitable representation for classification tasks, relying on advances in Riemannian geometry. We propose to equip the minimum distance to mean (MDM) classifier with a new family of means, based on the inductive mean, for block-online classification tasks and to embed the inductive mean in an incremental learning algorithm for online classification of EEG.

Document type Communication à un colloque (Conference Paper) – Présentation orale avec comité de sélection
Access type Accès interdit
Publication date 2017
Language Anglais
Conference "International Conference on Geometric Science of Information(GSI 2017)"
Peer reviewed yes
Host document "Lecture Notes in Computer Science : Geometric Science of Information"- p. 763-770 (ISBN : 978-3-319-68445-1)
Publisher springer,cham
Publication status Publié
Affiliations UCL - SST/ICTM/INMA - Pôle en ingénierie mathématique
LISV, Université de Versailles Saint-Quentin, Versailles, France
Links
  1. Barachant, A., Andreev, A., Congedo, M.: The Riemannian Potato: an automatic and adaptive artifact detection method for online experiments using Riemannian geometry. In: TOBI Workshop lV, pp. 19–20 (2013)
  2. Barachant Alexandre, Bonnet Stéphane, Congedo Marco, Jutten Christian, Riemannian Geometry Applied to BCI Classification, Latent Variable Analysis and Signal Separation (2010) ISBN:9783642159947 p.629-636, 10.1007/978-3-642-15995-4_78
  3. Clerc, M., Bougrain, L., Lotte, F.: Brain-Computer Interfaces 2: Technology and Applications. Wiley, London (2016)
  4. Ho, J., Cheng, G., Salehian, H., Vemuri, B.: Recursive Karcher expectation estimators and geometric law of large numbers. In: Artificial Intelligence and Statistics, pp. 325–332 (2013)
  5. Kalunga Emmanuel K., Chevallier Sylvain, Barthélemy Quentin, Djouani Karim, Hamam Yskandar, Monacelli Eric, From Euclidean to Riemannian Means: Information Geometry for SSVEP Classification, Lecture Notes in Computer Science (2015) ISBN:9783319250397 p.595-604, 10.1007/978-3-319-25040-3_64
  6. Kalunga Emmanuel K., Chevallier Sylvain, Barthélemy Quentin, Djouani Karim, Monacelli Eric, Hamam Yskandar, Online SSVEP-based BCI using Riemannian geometry, 10.1016/j.neucom.2016.01.007
  7. Kalunga Emmanuel, Djouani Karim, Hamam Yskandar, Chevallier Sylvain, Monacelli Eric, SSVEP enhancement based on Canonical Correlation Analysis to improve BCI performances, 10.1109/afrcon.2013.6757776
  8. Massart Estelle M., Hendrickx Julien M., Absil P.-A., Matrix geometric means based on shuffled inductive sequences, 10.1016/j.laa.2017.05.036
  9. Sagae Masahiko, Tanabe Kunio, Upper and lower bounds for the arithmetic-geometric-harmonic means of positive definite matrices, 10.1080/03081089408818331
  10. Schäferm, J., Strimmer, K.: A shrinkage approach to large-scale covariance matrix estimation and implications for functional genomics. Stat. Appl. Genet. Mol. Biol. 4(1), 32 (2005)
  11. van Erp Jan, Lotte Fabien, Tangermann Michael, Brain-Computer Interfaces: Beyond Medical Applications, 10.1109/mc.2012.107
  12. Yger, F., Berar, M., Lotte, F.: Riemannian approaches in brain-computer interfaces: a review. IEEE TNSRE PP, 1 (2016)
Bibliographic reference Massart, Estelle M. ; Chevallier, Sylvain. Inductive Means and Sequences Applied to Online Classification of EEG.International Conference on Geometric Science of Information(GSI 2017)In: Lecture Notes in Computer Science : Geometric Science of Information, springer,cham2017, p. 763-770
Permanent URL http://hdl.handle.net/2078.1/189747