Epilepsy detection by using scalogram based convolutional neural network from eeg signals
Özerdem, Mehmet Siraç
MetadataShow full item record
CitationTürk, Ö. ve Özerdem, M. S. (2019). Epilepsy detection by using scalogram based convolutional neural network from eeg signals. Brain Sciences, 9(5), 115.
The studies implemented with Electroencephalogram (EEG) signals are progressing veryrapidly and brain computer interfaces (BCI) and disease determinations are carried out at certainsuccess rates thanks to new methods developed in this field. The effective use of these signals,especially in disease detection, is very important in terms of both time and cost. Currently, ingeneral, EEG studies are used in addition to conventional methods as well as deep learningnetworks that have recently achieved great success. The most important reason for this is that inconventional methods, increasing classification accuracy is based on too many human efforts asEEG is being processed, obtaining the features is the most important step. This stage is based onboth the time-consuming and the investigation of many feature methods. Therefore, there is a needfor methods that do not require human effort in this area and can learn the features themselves.Based on that, two-dimensional (2D) frequency-time scalograms were obtained in this study byapplying Continuous Wavelet Transform to EEG records containing five different classes.Convolutional Neural Network structure was used to learn the properties of these scalogram imagesand the classification performance of the structure was compared with the studies in the literature.In order to compare the performance of the proposed method, the data set of the University of Bonnwas used. The data set consists of five EEG records containing healthy and epilepsy disease whichare labeled as A, B, C, D, and E. In the study, A-E and B-E data sets were classified as 99.50%, A-Dand B-D data sets were classified as 100% in binary classifications, A-D-E data sets were 99.00% intriple classification, A-C-D-E data sets were 90.50%, B-C-D-E data sets were 91.50% in quaternaryclassification, and A-B-C-D-E data sets were in the fifth class classification with an accuracy of93.60%.