Non-negative Tensor Factorization for Single-Channel EEG Artifact Rejection

Abstract : New applications of Electroencephalographic recording (EEG) pose new challenges in terms of artifact removal. In our work, we target informed source separation methods for artifact removal in single-channel EEG recordings by exploiting prior knowledge from auxiliary lightweight sensors capturing artifactual signals. To achieve this, we first propose a method using Non-negative Matrix Factorization (NMF) in a Gaussian source separation that proves competitive against the classic multi-channel Independent Component Analysis (ICA) technique. Additionally, we confront a probabilistic Non-negative Tensor Factorization (NTF) with ICA, both used in an original scheme that jointly processes the EEG and auxiliary signals. The adopted NTF strategy is shown to improve separation accuracy in comparison with the usual multi-channel ICA approach and the single EEG channel NMF method.
Complete list of metadatas

Cited literature [9 references]  Display  Hide  Download

https://hal.inria.fr/hal-00959103
Contributor : Antoine Liutkus <>
Submitted on : Thursday, March 13, 2014 - 11:02:42 PM
Last modification on : Thursday, October 17, 2019 - 12:36:09 PM
Long-term archiving on : Friday, June 13, 2014 - 12:40:30 PM

File

MLSP_V1.pdf
Files produced by the author(s)

Identifiers

Citation

Cécilia Damon, Antoine Liutkus, Alexandre Gramfort, Slim Essid. Non-negative Tensor Factorization for Single-Channel EEG Artifact Rejection. MLSP, Sep 2013, Southampton, United Kingdom. ⟨10.1109/MLSP.2013.6661983⟩. ⟨hal-00959103⟩

Share

Metrics

Record views

815

Files downloads

513