Article

Nonnegative tensor factorization for continuous EEG classification.

Department of Computer Science, Pohang University of Science and Technology, San 31 Hyoja-dong, Nam-gu, Pohang 790-784, Republic of Korea.
International Journal of Neural Systems (Impact Factor: 6.06). 09/2007; 17(4):305-17. DOI: 10.1142/S0129065707001159
Source: PubMed

ABSTRACT In this paper we present a method for continuous EEG classification, where we employ nonnegative tensor factorization (NTF) to determine discriminative spectral features and use the Viterbi algorithm to continuously classify multiple mental tasks. This is an extension of our previous work on the use of nonnegative matrix factorization (NMF) for EEG classification. Numerical experiments with two data sets in BCI competition, confirm the useful behavior of the method for continuous EEG classification.

Download full-text

Full-text

Available from: Lee Hyekyoung, Jun 24, 2014
0 Followers
 · 
170 Views
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: New applications of Electroencephalographicrecording (EEG) require light and easy-to-handle equipment involving powerful algorithms of artifact removal. In our work, we exploit informed source separation methods for artifact removal in EEG recordings with a low number of sensors, especially in the extreme case of single-channel recording, by exploiting prior knowledge from auxiliary lightweight sensors capturing artifactual signals. To achieve this, we propose a method using Non-negative Tensor Factorization (NTF) in a Gaussian source separation framework that proves competitive against the classic Independent Component Analysis (ICA) technique. Additionally the both NTF and ICA methods are used in an original scheme that jointly processes the EEG and auxiliary signals. The adopted NTF strategy is shown to improve the source estimates accuracy in comparison with the usual multi-channel ICA approach.
    IEEE International Workshop on Machine Learning for Signal Processing; 09/2013
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This study explores an approach for analysing the mirror (reflective) symmetry of 3D shapes with tensor based sparse decomposition. The approach combines non-negative tensor decomposition and directional texture synthesis, with symmetry information about 3D shapes that is represented by 2D textures synthesised from sparse, decomposed images. This technique requires the center of mass of 3D objects to be at the origin of the coordinate system. The decomposition of 3D shapes and analysis of their symmetry are useful for image compression, pattern recognition, as well as there being an emerging interest in the medical community due to its potential to find morphological changes between healthy and pathological structures. This paper postulates that sparse texture synthesis can be used to describe the decomposed basis images acting as symmetry descriptors for a 3D shape. We apply the theory of non-negative tensor decomposition and sparse texture synthesis, deduce the new representation, and show some application examples.
    Computer methods and programs in biomedicine 11/2012; 108(2):629-643. DOI:10.1016/j.cmpb.2011.10.007 · 1.09 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Tensor factorization has exciting advantages to analyze EEG for simultaneously exploiting its information in the time, frequency and spatial domains as well as for sufficiently visualizing data in different domains concurrently. Event-related potentials (ERPs) are usually investigated by the group-level analysis, for which tensor factorization can be used. However, sizes of a tensor including time-frequency representation of ERPs of multiple channels of multiple participants can be immense. It is timeconsuming to decompose such a tensor. The low-rank approximation based sequential nonnegative Tucker decomposition (LraSNTD) has been recently developed and shown to be computationally efficient with respect to some benchmark datasets. Here, LraSNTD is applied to decompose a fourth-order tensor representation of ERPs. We find that the decomposed results from LraSNTD and a benchmark nonnegative Tucker decomposition algorithm are very similar. So, LraSNTD is promising for ERP studies.
    IEEE Workshop on Machine Learning for Signal Processing (MLSP) 2012; 09/2012