Spike Detection from EEG Signals with Aid of Morphological Filters and Hybrid GAPSO

Abstract

Listen

Translate article

Studying the behavior of spikes in EEG is important for detecting brain abnormality. In EEG recorded signal contain large amount of spikes, so the spike detection is a technical challenge one. Morphological filters are normally used to separate this spikes from the recorded EEG signal. In existing technique the Gaussian function is used in morphological filter to find out the optimal structuring element. Using this function, it cannot find the accurate optimal structuring element, for that we have intended to propose a spike detection method using morphological filter with optimization technique. In the proposed method, initially the EEG signals noise is removed by the wavelet technique and this preprocessed EEG signals are given to the spike detection process. Morphological filter is used for the spike detection, in which optimal structuring elements are computed by the hybrid optimization technique as GA-PSO. After that, an amplitude threshold should be set to detect the occurrence of individual spikes. Hence, the spikes can be detected more effectively by achieving more number of correctly detected spikes rather than the conventional spike detection algorithms. Moreover our proposed technique performance is compared with the PSO and GA optimization methods.