Classifying EEG for brain computer interfaces using Gaussian processes

Mingjun Zhong, Fabien Lotte, Mark Girolami, Anatole Lécuyer

Research output: Contribution to journalArticlepeer-review

Abstract

Classifying electroencephalography (EEG) signals is an important step for proceeding EEG-based brain computer interfaces (BCI). Currently, kernel based methods such as the support vector machine (SVM) are considered the state-of-the-art methods for this problem. In this paper, we apply Gaussian process (GP) classification to binary discrimination of motor imagery EEG data. Compared with the SVM, GP based methods naturally provide probability outputs for identifying a trusted prediction which can be used for post-processing in a BCI. Experimental results show that the classification methods based on a GP perform similarly to kernel logistic regression and probabilistic SVM in terms of predictive likelihood, but outperform SVM and K-nearest neighbor (KNN) in terms of 0–1 loss class prediction error.
Original languageEnglish
Pages (from-to)354-359
Number of pages6
JournalPattern Recognition Letters
Volume29
Issue number3
DOIs
Publication statusPublished - 2008

Fingerprint

Dive into the research topics of 'Classifying EEG for brain computer interfaces using Gaussian processes'. Together they form a unique fingerprint.

Cite this