Skip to Main content Skip to Navigation
New interface
Conference papers

Detecting EEG outliers for BCI on the Riemannian manifold using spectral clustering

Abstract : Automatically detecting and removing Electroencephalogram (EEG) outliers is essential to design robust brain-computer interfaces (BCIs). In this paper, we propose a novel outlier detection method that works on the Riemannian manifold of sample covariance matrices (SCMs). Existing outlier detection methods run the risk of erroneously rejecting some samples as outliers, even if there is no outlier, due to the detection being based on a reference matrix and a threshold. To address this limitation, our method, Riemannian Spectral Clustering (RiSC), detects outliers by clustering SCMs into non-outliers and outliers, based on a proposed similarity measure. This considers the Riemannian geometry of the space and magnifies the similarity within the non-outlier cluster and weakens it between non-outlier and outlier clusters, instead of setting a threshold. To assess RiSC performance, we generated artificial EEG datasets contaminated by different outlier strengths and numbers. Comparing Hit-False (HF) difference between RiSC and existing outlier detection methods confirmed that RiSC could detect outliers significantly better (p < 0.001). In particular, RiSC improved HF difference the most for datasets with the most severe outlier contamination.
Complete list of metadata

Cited literature [12 references]  Display  Hide  Download
Contributor : Fabien Lotte Connect in order to contact the contributor
Submitted on : Monday, May 18, 2020 - 5:43:27 PM
Last modification on : Saturday, July 23, 2022 - 3:53:15 AM


Files produced by the author(s)


  • HAL Id : hal-02611656, version 2


Maria Sayu Yamamoto, Khadijeh Sadatnejad, Toshihisa Tanaka, Md. Rabiul Islam, Yuichi Tanaka, et al.. Detecting EEG outliers for BCI on the Riemannian manifold using spectral clustering. EMBC'2020 - 42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society, Jul 2020, Montréal, Canada. ⟨hal-02611656v2⟩



Record views


Files downloads