Quantitative Analysis of EEG Slow Wave Activity Based on MinPeakProminence Method

Abstract

Persistent, unchanging, and non-reactive focal or generalized abnormal Slow Wave (SW) activities in an awake adult patient are examined pathologically. Although these waves in Electroencephalogram (EEG) are much less prominent than transient activities in some areas, it is not possible to understand them easily by looking at the EEG. For this reason, reliable computer programs that can sort out Slow Waves (SWs) correctly are needed. In this study, a new method based on MinPeakProminence that can detect abnormal SW activities was developed. To test the performance of the study, the data collected from Selcuk University Hospital (22 subjects - epilepsy and various neurological diseases) and Bonn Hospital (only normal A dataset) were used. Various statistical performance measurement methods were used to search the results. The results of this analysis revealed that the classification success, sensitivity and specificity values obtained with the SUH dataset were 96.5%, 93.3% and 96.1%, respectively. In the results of the experiments made with the Bonn dataset, 100% classification success was achieved. Besides, according to the analyses, it was found that SWs are frequently seen in the posterior regions of the brain, especially in the parietal and occipital regions in the SUH dataset.

Investigating the Effect of COVID-19 Infection on P300 Based BCI Application Performance

“…P300 waves obtained by averaging the EEG signals This obtained data samples was randomly divided into 70% training, 15% validation, and 15% test partitions for each subject.It should be noted that the aforementioned P300 signal processing procedure is repeated twenty times in order to show the robustness of the method and avoid the problems of the random selections of the training, validation and test sets. The average CA was calculated for the Parietal and Occipital region EEG electrodes, used in this study, as they are related to visual activities[22,23]. Since the inequality between the sample size of the two classes has a negative effect on the classification task success, synthetic data was generated to eliminate this imbalance between the classes.…”