Yahya Alyasseri, Zaid Abdi Alkareem
(2020)
Eeg-Based Person Identification Using Multi-Levelwavelet Decomposition With Multi-Objective Flower Pollination Algorithm.
PhD thesis, Universiti Sains Malaysia.
Abstract
Recently, several studies showed that the brain electrical activity or electroencephalogram (EEG) signals provide unique features that can be considered as user identification techniques. But, it is a challenging task where there are three important things must be addressed carefully in any EEG-based person identification. First, one of the significant challenges concerning
is a signal acquisition, which is performed by placing several electrodes on a
person’s head. However, it is not necessary to put all these electrodes on a persons’
head. Therefore, the most relevant ones for person identification can be identified and then use a smaller number of electrodes. Second, the EEG signals must be processed to obtain efficient EEG features because there are several noises can corrupt the original EEG signal during the recording time. Third, select efficient features that can be extracted from the EEG signal for achieving the highest accuracy rate. For addressing these points, a novel person identification method that is using EEG with multi-level wavelet decomposition and multi-objective flower pollination algorithm is proposed in this thesis. The proposed method is tested using two standard EEG datasets, namely, Kiern’s and Motor Movement/Imagery.
Actions (login required)
 |
View Item |
