Entropy-driven deep learning framework for epilepsy detection using electro encephalogram signals

Neuroscience, Journal Year: 2025, Volume and Issue: unknown

Published: May 1, 2025

Language: Английский

---

Signal to Image Conversion and Convolutional Neural Networks for Physiological Signal Processing: A Review

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 66726 - 66764

Published: Jan. 1, 2024

Physiological signals such as electroencephalography (EEG), electromyography (EMG), and electrocardiography (ECG) provide valuable clinical information but pose challenges for analysis due to their high-dimensional nature. Traditional machine learning techniques, relying on hand-crafted features from fixed windows, can lead the loss of discriminative information. Recent studies have demonstrated effectiveness deep convolutional neural networks (CNNs) robust automated feature raw physiological signals. However, standard CNN architectures require two-dimensional image data input. This has motivated research into innovative signal-to-image (STI) transformation techniques convert one-dimensional time series images preserving spectral, spatial, temporal characteristics. paper reviews recent advances in strategies conversion applications using CNNs processing tasks. A systematic EEG, EMG, ECG signal CNN-based spanning diverse applications, including brain-computer interfaces, seizure detection, motor control, sleep stage classification, arrhythmia more, are presented. Key insights synthesised regarding relative merits different approaches, model architectures, training procedures, benchmark performance. Current promising directions at intersection discussed. review aims catalyse continued innovations effective end-to-end systems clinically relevant extraction multidimensional by providing a comprehensive overview state-of-the-art techniques.

Language: Английский

---

RT-NeuroDDSM: Real-Time EEG-Driven Diagnostic Decision Support Model for Neurological Disorders Using Deep Learning

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 116711 - 116726

Published: Jan. 1, 2024

The Internet of Medical Things (IoMT) has become a pivotal aspect IoT applications, playing crucial role in cutting down healthcare expenses, enhancing access to clinical services, and refining operational efficiency within the domain. An early detection neurological brain disorders continues present formidable challenge. In response, our research endeavors are directed towards IoMT-based system used for real-time diagnosis disorders. this paper, model is developed using systematic deep learning electroencephalogram (EEG) signal (RT-NeuroDDSM). We first introduce time domain, channel spatial attention network (TCSNet) feature extraction which extracts high-level series, features, respectively. TCSNet aims learn more valuable features from input data achieve good classification results. Furthermore, order maximize we create modified normative fish swarm (MNFS) selection algorithm. Next, various problems, including neuro-typical, epilepsy, autism spectrum disorder (ASD), accomplished by applying hinging hyperplane neural (HHNN). To verify performance, publicly accessible EEG datasets University Bonn-Germany, CHB-MIT repository, King Abdul-Aziz University. RT-NeuroDDSM an overall accuracy 99.956%, making it 5.471% compared existing state-of-the-art model.

Language: Английский

---

Speeded up robust features trailed GCN for seizure identification during pregnancy

Journal of Integrated Science and Technology, Journal Year: 2024, Volume and Issue: 12(5)

Published: May 7, 2024

In this work, an efficient computational framework has been designed for seizure identification using MRI analysis. The inputs being brain of pregnant women and corresponding outputs the or no label. is implemented in two phases. First, informative speeded up robust features (SURF) are extracted from MRI. Second, these further mapped to a graph convolutional neural network (GCN). maximal clique generated out intermediate subjected (CNN) architecture classification. acts as tool representing final fine-tuned feature points through combined convolution thus contributes towards validated benchmark dataset images presented by NITRC. Experimental evaluation made on samples 'male', 'female' 'female with pregnancy'. overall rate accuracy stands at 96%, 95%, 95% respectively. URN:NBN:sciencein.jist.2024.v12.810

Language: Английский

---

Comparison of Different Deep Learning Networks to Classify Epilepsy Seizure Based on EEG Signals

Published: May 27, 2024

Language: Английский

---

Hybrid Deep Learning Network with Convolutional Attention for Detecting Epileptic Seizures from EEG Signals

Lecture notes in networks and systems, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 10

Published: Jan. 1, 2024

Language: Английский

---

LMPSeizNet: A Lightweight Multiscale Pyramid Convolutional Neural Network for Epileptic Seizure Detection on EEG Brain Signals

Mathematics, Journal Year: 2024, Volume and Issue: 12(23), P. 3648 - 3648

Published: Nov. 21, 2024

Epilepsy is a chronic disease and one of the most common neurological disorders worldwide. Electroencephalogram (EEG) signals are widely used to detect epileptic seizures, which provide specialists with essential information about brain’s functioning. However, manual screening EEG laborious, time-consuming, subjective. The rapid detection epilepsy seizures important reduce risk seizure-related implications. existing automatic machine learning techniques based on deep characterized by extraction selection features, leading better performance increasing robustness systems. These methods do not consider multiscale nature signals, eventually resulting in poor sensitivity. In addition, complexity models relatively high, overfitting issues. To overcome these problems, we proposed an efficient lightweight convolutional neural network model (LMPSeizNet), performs temporal spatial analysis trial learn discriminative features relevant seizure detection. evaluate method, employed 10-fold cross-validation three evaluation metrics: accuracy, sensitivity, specificity. method achieved accuracy 97.42%, sensitivity 99.33%, specificity 96.51% for inter-ictal ictal classes outperforming state-of-the-art methods. decision-making shows that it learns clearly discriminate two classes. It will serve as useful tool helping neurologists patients.

Language: Английский

---

Brain Waves Decoded: Cutting-Edge Seizure Recognition with Graph Fourier and BrainGNN

International Journal of Scientific Research in Computer Science Engineering and Information Technology, Journal Year: 2024, Volume and Issue: 10(6), P. 2025 - 2032

Published: Dec. 12, 2024

For effective therapy, epileptic seizures, which are characterized by sudden electrical disruptions in the brain, must be identified accurately and promptly. Conventional techniques, such feature extraction EEG signal analysis, have demonstrated limits terms of robustness precision. In order to greatly improve seizure recognition, this paper present a novel method that integrates Brain Graph Neural Networks (BrainGNN) Fourier Transforms (GFT). By transforming brain wave impulses into frequency domain, GFT examines signals reveals complex patterns associated with activity. With great accuracy, BrainGNN––which is optimized for graph-structure data––capture temporal spatial correlations these differentiate between normal states. Our combined BrainGNN outperformed conventional technique significant margin, achieving outstanding test accuracies 99.77%. This sophisticated offers insights neural dynamics seizures enhancing detection abilities. It also emphasizes potential fusing network graph-based techniques neurophysiological disorder diagnostics, could lead more potent, non-invasive tools management epilepsy.

Language: Английский

---