DocumentCode :
2173394
Title :
Sequential nonnegative tucker decomposition on multi-way array of time-frequency transformed event-related potentials
Author :
Cong, Fengyu ; Zhou, Guoxu ; Zhao, Qibin ; Wu, Qiang ; Nandi, Asoke K. ; Ristaniemi, Tapani ; Cichocki, Andrzej
Author_Institution :
Dept. of Math. Inf. Technol., Univ. of Jyvaskyla, Jyvaskyla, Finland
fYear :
2012
fDate :
23-26 Sept. 2012
Firstpage :
1
Lastpage :
6
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 time-consuming 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.
Keywords :
approximation theory; electroencephalography; matrix decomposition; medical signal processing; signal representation; tensors; time-frequency analysis; EEG analysis; ERP; LraSNTD; fourth-order tensor representation decomposition; group-level analysis; low-rank approximation based sequential nonnegative Tucker decomposition; multiway array; sequential nonnegative Tucker decomposition algorithm; spatial domains; tensor factorization; time-frequency representation; time-frequency transformed event-related potentials; Algorithm design and analysis; Approximation methods; Electroencephalography; Feature extraction; Signal processing algorithms; Tensile stress; Time frequency analysis; event-related potential; low rank approximation; sequential nonnegative Tucker decomposition; tensor; time-frequency representation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Machine Learning for Signal Processing (MLSP), 2012 IEEE International Workshop on
Conference_Location :
Santander
ISSN :
1551-2541
Print_ISBN :
978-1-4673-1024-6
Electronic_ISBN :
1551-2541
Type :
conf
DOI :
10.1109/MLSP.2012.6349788
Filename :
6349788
Link To Document :
بازگشت