Browsing by Author "Yilmaz G.C."

Now showing 1 - 2 of 2

Classification of Dementia Eeg Based on Sub-Bands Using Time-Frequency Approaches
(Institute of Electrical and Electronics Engineers Inc., 2022) Cura O.K.; Yilmaz G.C.; Ture H.S.; Akan A.
Alzheimer's dementia is a highly prevalent disorder among all neurological disorders. In this study, a new method based on time-Frequency (TF) representations such as Short Time Fourier Transform (STFT) and Synchrosqueezing Transform (SST) is proposed to classify EEG segments of AD patients and control subjects. Previous studies have shown that there are distinctive differences in the EEG signals of control subjects and AD patients in the low-frequency EEG subbands. Hence, in the proposed method TF representations of all EEG subbands are used for feature calculation separately. TF energy distributions obtained by SST and STFT approaches are used to calculate 13 TF features to gather distinctive information between EEG segments of control subjects and AD patients. Various classification techniques are utilized to distinguish feature sets of two the groups. Simulation results demonstrate that the proposed method achieve outstanding validation accuracy rates. © 2022 IEEE.
Citation - WoS: 3
Citation - Scopus: 4
Classification of Psychogenic Non-Epileptic Seizures Using Synchrosqueezing Transform of Eeg Signals
(European Signal Processing Conference, EUSIPCO, 2021) Cura O.K.; Yilmaz G.C.; Türe H.S.; Akan A.
Psychogenic non-epileptic seizures (PNES) are mostly associated with psychogenic factors, where the symptoms are often confused with epilepsy. Since electroencephalography (EEG) signals maintain their normal state in PNES cases, it is not possible to diagnose using the EEG recordings alone. Therefore, long-term video EEG records and detailed patient history are needed for reliable diagnosis and correct treatment. However, the video EEG recording method is more expensive than the classical EEG. Therefore, it has great importance to distinguish PNES signals from normal epileptic seizure (ES) signals using only the EEG recordings. In the proposed study, using the Synchrosqueezed Transform (SST) that gives high-resolution time-frequency representations (TFR), inter-PNES, PNES, and Epileptic seizure EEG classification is introduced. 17 joint TF features are calculated from the TFRs, and various classifiers are used for classification processes. Classification problems with three classes (inter-PNES, PNES, and ES) and two classes (inter-PNES and PNES) are considered. Experimental results indicated that both three-class and two-class classification approaches achieved encouraging validation performances (three-class problem: 95.8% ACC, 86.9% SEN, 91.4% PRE, and 8.6% FDR; two-class problem: 96.4% ACC, 96.8% SEN, 97.3% PRE, and FDR lower than 10%). © 2021 European Signal Processing Conference. All rights reserved.