%A Trung Thanh Le
%A Thi Anh Dao Nguyen
%A Viet Dung Nguyen
%A Linh Trung Nguyen
%A Karim Abed-Meraim
%O UET-AVITECH-2019002
%T Simultaneous tensor decomposition for EEG epileptic spike detection
%X Objective: Epilepsy is one of the most common brain disorders. For epilepsy diagnosis or treatment, the neurologist needs to observe epileptic spikes from electroencephalography (EEG) data. Since multi-channel EEG records can be naturally represented by multi-way tensors, it is of interest to see whether tensor decomposition is able to analyze EEG epileptic spikes.
Approach: In this report, we first proposed the problem of simultaneous multilinear low-rank approximation of tensors (SMLRAT) and proved that SMLRAT can obtain local optimum solutions by using two well-known tensor decomposition algorithms (HOSVD and Tucker-ALS). Second, we presented a new system for automatic epileptic spike detection based on SMLRAT.
Main results: We compared the proposed tensor analysis method with other common tensor methods in analyzing EEG signal and compared the proposed feature extraction method with Phan’s method. Experimental results indicated that our proposed method is able to detect epileptic spikes with good performance.
Significance: To suitably deal with EEG spikes, we developed a local solution for nonnegative SMLRAT. For practical implementation, we proposed the generalized SMLRAT algorithm to effectively solve the SMLRAT and nonnegative SMLRAT problems. An efficient EEG feature extraction framework was proposed, based on estimating the “eigenspikes” from the nonnegative generalized SMLRAT algorithm.
%D 2019
%C Hanoi, Vietnam
%R UET-AVITECH-2019002
%I University of Engineering and Technology, Vietnam National University
%L SisLab3444