Browsing by Author "Cura O.K."

Now showing 1 - 7 of 7

Citation - WoS: 9
Citation - Scopus: 17
Abnormal Ecg Beat Detection Based on Convolutional Neural Networks
(Institute of Electrical and Electronics Engineers Inc., 2020) Ozdemir M.A.; Guren O.; Cura O.K.; Akan A.; Onan A.
The heart is the most critical organ for the sustainability of life. Arrhythmia is any irregularity of heart rate that causes an abnormality in your heart rhythm. Clinical analysis of Electrocardiogram (ECG) signals is not enough to quickly identify abnormalities in the heart rhythm. This paper proposes a deep learning method for the accurate detection of abnormal and normal heartbeats based on 2-D Convolutional Neural Network (CNN) architecture. Two channels of ECG signals were obtained from the MIT-BIH arrhythmia dataset. Each ECG signal is segmented into heartbeats, and each heartbeat is transformed into a 2-D grayscale heartbeat image as an input for CNN structure. Due to the success of image recognition, CNN architecture is utilized for binary classification of the 2-D image matrix. In this study, the effect of different CNN architectures is compared based on the classification rate. The accuracies of training and test data are found as 100.00% and 99.10%, respectively for the best CNN model. Experimental results demonstrate that CNN with ECG image representation yields the highest success rate for the binary classification of ECG beats compared to the traditional machine learning methods, and one-dimensional deep learning classifiers. © 2020 IEEE.
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 - Scopus: 2
Classification of Epileptic Eeg Signals Using Dynamic Mode Decomposition
(Institute of Electrical and Electronics Engineers Inc., 2020) Cura O.K.; Pehlivan S.; Akan A.
In the literature, several signal processing techniques have been used to diagnose epilepsy which is a nervous system disease. However most of these techniques fail to analyse EEG signals which are dynamic and non-linear. In this study, an approach which utilizes a data-driven technique called Dynamic Mode Decomposition (DMD) that was originally developed to be used in fluid mechanics was proposed. Features that were belonged to EEG signals were calculated using DMD method and with the help of different classifiers, classification of the preseizure and seizure EEG signals was performed. Obtained results showed that the proposed method presented an alternative to approaches that are based on Empirical Mode Decomposition and its derivatives. © 2020 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.
A Dynamic Mode Decomposition Based Approach for Epileptic Eeg Classification
(European Signal Processing Conference, EUSIPCO, 2021) Cura O.K.; Ozdemir M.A.; Akan A.; Pehlivan S.
Epilepsy is a neurological disorder that affects many people all around the world, and its early detection is a topic of research widely studied in signal processing community. In this paper, a new technique that was introduced to solve problems of fluid dynamics called Dynamic Mode Decomposition (DMD), is used to classify seizure and non-seizure epileptic EEG signals. The DMD decomposes a given signal into the intrinsic oscillations called modes which are used to define a DMD spectrum. In the proposed approach, the DMD spectrum is obtained by applying either multi-channel or single-channel based DMD technique. Then, subband and total power features extracted from the DMD spectrum and various classifiers are utilized to classify seizure and non-seizure epileptic EEG segments. Outstanding classification results are achieved by both the single-channel based (96.7%), and the multi-channel based (96%) DMD approaches. © 2021 European Signal Processing Conference, EUSIPCO. All rights reserved.
Citation - WoS: 1
Citation - Scopus: 2
Epileptic Eeg Classification Using Synchrosqueezing Transform and Machine Learning
(Institute of Electrical and Electronics Engineers Inc., 2020) Cura O.K.; Akan A.
Epilepsy is one of the neurological diseases that occur incidences worldwide. The electroencephalography (EEG) recording method is the most frequently used clinical practice in the diagnosis and monitoring of epilepsy. Many computer-aided analysis methods have been developed in the literature to facilitate the analysis of long-term EEG signals. In the proposed study, the patient-based seizure detection approach is proposed using a high-resolution time-frequency (TF) representation named Synchrosqueezed Transform (SST) method. The SST of two different data sets called the IKCU data set and CHB-MIT data set are obtained, and Higher-order joint TF(HOJ-TF) based and Gray-level co-occurrence matrix (GLCM) based features are calculated using these SSTs. Using some machine learning methods such as Decision Tree (DT), k-Nearest Neighbor (kNN), and Logistic Regression (LR), classification processes are conducted. High patient-based seizure detection success is achieved for both the IKCU data set (94.25%) and the CHB-MIT data set (95.15%). © 2020 IEEE.
Citation - WoS: 2
Citation - Scopus: 4
Epileptic Eeg Classification Using Synchrosqueezing Transform With Machine and Deep Learning Techniques
(European Signal Processing Conference, EUSIPCO, 2021) Cura O.K.; Ozdemir M.A.; Akan A.
Epilepsy is a neurological disease that is very common worldwide. In the literature, patient's electroencephalography (EEG) signals are frequently used for an epilepsy diagnosis. However, the success of epileptic examination procedures from quantitative EEG signals is limited. In this paper, a high-resolution time-frequency (TF) representation called Synchrosqueezed Transform (SST) is used to classify epileptic EEG signals. The SST matrices of seizure and pre-seizure EEG data of 16 epilepsy patients are calculated. Two approaches based on machine learning and deep learning are proposed to classify pre-seizure and seizure signals. In the machine learning-based approach, the various features like higher-order joint moments are calculated and these features are classified by Support Vector Machine (SVM), k-Nearest Neighbor (kNN) and Naive Bayes (NB) classifiers. In the deep learning-based approach, the SST matrix was recorded as an image and a Convolutional Neural Network (CNN)-based architecture was used to classify these images. Simulation results demonstrate that both approaches achieved promising validation accuracy rates. While the maximum (90.2%) validation accuracy is achieved for the machine learning-based approach, (90.3%) validation accuracy is achieved for the deep learning-based approach. © 2021 European Signal Processing Conference, EUSIPCO. All rights reserved.