Sürdürülebilir Kalkınma Amaçları
Yazarlar
Yayınlar
- MakaleAçık Erişim2026Scopus SJRQ1Forked hybrid architecture combining 1D-CNN and quantum convolutional networks for EEG signal classification
Esmeray, Furkan; Gülten, Arif
Detecting epileptic seizures from electroencephalogram (EEG) signals presents a significant challenge due to the nonlinear and non-stationary nature of brain activity. In this study, we propose a hybrid classification framework that integrates quantum-assisted and classical deep learning techniques to enhance detection accuracy and model interpretability. First, discrete wavelet transform (DWT) is applied to extract multiscale time–frequency features from raw EEG signals. Subsequently, three comparative models are developed: a conventional 1D-CNN model, an IQCNN model incorporating a parametric quantum circuit, and a novel Forked Enhanced Model that processes EEG features simultaneously through both 1D-CNN and IQCNN branches and combines them in a fully connected layer. The proposed hybrid model leverages the expressive power of quantum entanglement while preserving the robustness of classical deep learning. Evaluations using 5-fold stratified cross-validation on a real EEG dataset show that the forked architecture outperforms both classical CNNs and quantum-only based models in terms of accuracy, F1 score, precision, recall, number of incorrectly classified subjects and AUC. In this study, the best result was obtained with the Denoise IQCNNNet hybrid model. The accuracy of this model is 97.25%, precision 92.74%, recall 93.66%, F-1 score 93.15%, AUC 99.54%, number of incorrectly classified subjects are 57. This study demonstrates the feasibility and potential of hybrid quantum-classical networks in biomedical signal processing and provides a foundation for real-time clinical seizure monitoring systems.
- MakaleYalnız künye2020Scopus SJRQ1A deep convolutional neural network model for automated identification of abnormal EEG signals
Yıldırım, Özal; Baloglu, Ulas Baran; Acharya, U. Rajendra
Electroencephalogram (EEG) is widely used to monitor the brain activities. The manual examination of these signals by experts is strenuous and time consuming. Hence, machine learning techniques can be used to improve the accuracy of detection. Nowadays, deep learning methodologies have been used in medical field to diagnose the health conditions precisely and aid the clinicians. In this study, a new deep one-dimensional convolutional neural network (1D CNN) model is proposed for the automatic recognition of normal and abnormal EEG signals. The proposed model is a complete end-to-end structure which classifies the EEG signals without requiring any feature extraction. In this study, we have used the EEG signals from temporal to occipital (T5–O1) single channel obtained from Temple University Hospital EEG Abnormal Corpus (v2.0.0) EEG dataset to develop the 1D CNN model. Our developed model has yielded the classification error rate of 20.66% in classifying the normal and abnormal EEG signals.
AtıfScopus164OpenAlex211
İncele - MakaleYalnız künye2019Scopus SJRQ4CONVOLUTIONAL LONG-SHORT TERM MEMORY NETWORKS MODEL FOR LONG DURATION EEG SIGNAL CLASSIFICATION
Baloglu, Ulas Baran; Yildirim, Ozal
Background and objective: Deep learning structures have recently achieved remarkable success in the field of machine learning. Convolutional neural networks (CNN) in image processing and long-short term memory (LSTM) in the time-series analysis are commonly used deep learning algorithms. Healthcare applications of deep learning algorithms provide important contributions for computer-aided diagnosis research. In this study, convolutional long-short term memory (CLSTM) network was used for automatic classification of EEG signals and automatic seizure detection. Methods: A new nine-layer deep network model consisting of convolutional and LSTM layers was designed. The signals processed in the convolutional layers were given as an input to the LSTM network whose outputs were processed in densely connected neural network layers. The EEG data is appropriate for a model having 1-D convolution layers. A bidirectional model was employed in the LSTM layer. Results: Bonn University EEG database with five different datasets was used for experimental studies. In this database, each dataset contains 23.6 s duration 100 single channel EEG segments which consist of 4097 dimensional samples (173.61 Hz). Eight two-class and three three-class clinical scenarios were examined. When the experimental results were evaluated, it was seen that the proposed model had high accuracy on both binary and ternary classification tasks. Conclusions: The proposed end-to-end learning structure showed a good performance without using any hand-crafted feature extraction or shallow classifiers to detect the seizures. The model does not require filtering, and also automatically learns to filter the input as well. As a result, the proposed model can process long duration EEG signals without applying segmentation, and can detect epileptic seizures automatically by using the correlation of ictal and interictal signals of raw data.
AtıfWoS17OpenAlex19İncele