Significant variables extraction of post-stroke EEG signal using wavelet and SOM kohonen

Abstract

Stroke patients require a long recovery. One success of the treatment given is the evaluation and monitoring during recovery. One device for monitoring the development of post-stroke patients is Electroencephalogram (EEG). This research proposed a method for extracting variables of EEG signals for post-stroke patient analysis using Wavelet and Self-Organizing Map Kohonen clustering. EEG signal was extracted by Wavelet to obtain Alpha, beta, theta, gamma, and Mu waves. These waves, the amplitude and asymmetric of the symmetric channel pairs are features in Self Organizing Map Kohonen Clustering. Clustering results were compared with actual clusters of post-stroke and no-stroke subjects to extract significant variable. These results showed that the configuration of Alpha, Beta, and Mu waves, amplitude together with the difference between the variable of symmetric channel pairs are significant in the analysis of post-stroke patients. The results gave using symmetric channel pairs provided 54-74% accuracy.

Detection of EEG Signal Post-Stroke Using FFT and Convolutional Neural Network

“…EEG signal data recording uses Emotiv wireless EEG which was taken from previous research on 50 people, 25 post-stroke patients and 25 no strokes using 128 Hz sampling frequency from 14 channels namely AF3, F7, F3, FC5, T7, P7, O1, O2, P8, T8, FC6, F4, F8, and AF4 [6]. Electrode placement on EEG is carried out by the International Federation of Societies of Electroencephalography standards using the Modified Combinatorial Nomenclature (MCN) system.…”

“…However, the EEG signal is non-stationary, has a small amplitude, so it is not easy in visual observation. The EEG signal consists of wave components based on frequencies, namely Alpha waves (8)(9)(10)(11)(12)(13), Theta waves (4-7 Hz), and Delta waves (0.5-3 Hz) [6]. Therefore, extracting the EEG signal into a frequency component becomes useful [7].…”

Classification of Motor Imagery and Synchronization of Post-Stroke Patient EEG Signal

“…This result is higher than previous studies using the features of Alpha -Beta -Mu -Amplitude -Asymmetric of Alpha -Asymmetric of Beta -Asymmetric of Amplitude that gave 74%. In meanwhile, using all features obtained an accuracy of 70% [4]. However, other study involved emotional variables of post-stroke patients, which used Wavelet, KNN, and Probabilistic Neural Networks provided 82% of accuracy [7]].…”

“…Neurologist usually observes the rhythm or density of waves, amplitude, changes in amplitude, differences in amplitude between symmetric channels, and the presence of low-frequency waves such as Delta, Theta, and Mu [4]. Previous research used motor imagery parameters to identify the motor skills of paralyzed limbs [5].…”

“…Meanwhile, implementation of wavelet transforms for the classification of emotions in post-stroke patients [7] and identifying variables that affect post-stroke patients [4]. EEG signals are also used to detect electrical abnormalities in the brain, such as Epilepsy [8].…”