期刊
NEURAL NETWORKS
卷 57, 期 -, 页码 39-50出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.neunet.2014.05.012
关键词
Brain-computer interface; Common spatial patterns; EEG classification; Indian Buffet processes; Nonparametric Bayesian methods
资金
- National Research Foundation (NRF) of Korea [NRF-2013R1A2A2A01067464]
- IT R&D Program of MSIP/KEIT [14-824-09-014]
- Korea Evaluation Institute of Industrial Technology (KEIT) [B0101-14-0307] Funding Source: Korea Institute of Science & Technology Information (KISTI), National Science & Technology Information Service (NTIS)
Multi-subject electroencephalography (EEG) classification involves algorithm development for automatically categorizing brain waves measured from multiple subjects who undergo the same mental task. Common spatial patterns (CSP) or its probabilistic counterpart, PCSP, is a popular discriminative feature extraction method for EEG classification. Models in CSP or PCSP are trained on a subject-by-subject basis so that inter-subject information is neglected. In the case of multi-subject EEG classification, however, it is desirable to capture inter-subject relatedness in learning a model. In this paper we present a non-parametric Bayesian model for a multi-subject extension of PCSP where subject relatedness is captured by assuming that spatial patterns across subjects share a latent subspace. Spatial patterns and the shared latent subspace are jointly learned by variational inference. We use an infinite latent feature model to automatically infer the dimension of the shared latent subspace, placing Indian Buffet process (IBP) priors on our model. Numerical experiments on BCI competition III IVa and IV 2a dataset demonstrate the high performance of our method, compared to PCSP and existing Bayesian multi-task CSP models. (C) 2014 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据