EEG-Based Epileptic Seizure Prediction Using Temporal Multi-Channel Transformers

Godoy, Ricardo V.; Reis, Tharik J. S.; Polegato, Paulo H.; Lahr, Gustavo; Saute, Ricardo Lutzky; Nakano, Frederico Nakane; Machado, Hélio Rubens; Sakamoto, Américo Ceiki; Becker, Marcelo; Caurin, Glauco Augusto de Paula

doi:10.2139/ssrn.4191945

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, the performance metrics showed that the inclusion of convolutional layers and attention-based pooling in the model enhances the performance and reduces the number of Transformer encoder layers, significantly reducing the computational complexity. Similarly, [84] explores definitions of preictal and interictal states in the CHB-MIT Scalp EEG Database, evaluating 30 and 60 minutes before seizures. The interictal state spans 4 hours after the last seizure and 4 hours before the next, with a 5minute pre-seizure window for timely alerts.…”

Section: A Seizure Detectionmentioning

confidence: 99%

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

Ch Vidyasagar,

Revanth Kumar,

Anantha Sai

et al. 2024

IEEE Access

View full text Add to dashboard Cite

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

show abstract

Section: A Seizure Detectionmentioning

confidence: 99%

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

Ch Vidyasagar,

Revanth Kumar,

Anantha Sai

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In this sense, our work seeks to follow up on these efforts to understand epilepsy (de Godoy et al. 2022 ; Hramov et al. 2016 ; Mohseni et al.…”

Section: Introductionmentioning

confidence: 99%

A modification to the Kuramoto model to simulate epileptic seizures as synchronization

et al. 2023

View full text Add to dashboard Cite

The Kuramoto model was developed to describe the coupling of oscillators, motivated by the natural synchronization phenomena. We are interested in modeling an epileptic seizure considering it as the synchronization of action potentials using and modifying this model. In this article, we propose to modify this model, changing the constant coupling force for a function with logistic growth to simulate the onset and epileptic seizure level in an adult male rat caused by the administration of lithium–pilocarpine. Later, we select some frequencies and their respective amplitude values using an algorithm based on the fast Fourier transform (FFT) from an electroencephalography signal when the rat is in basal conditions. Then, we take these values as the natural frequencies of the oscillators in the modified Kuramoto model, considering every oscillator as a single neuron to simulate the emergence of an epileptic seizure numerically by increasing the synchronization value in the coupling function. Finally, using Dynamic Time Warping algorithm, we compare the simulated signal by the Kuramoto model with an FFT approximation of the epileptic seizure.

show abstract

EEG-Based Epileptic Seizure Prediction Using Temporal Multi-Channel Transformers

Cited by 2 publications

References 0 publications

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

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

A modification to the Kuramoto model to simulate epileptic seizures as synchronization

Contact Info

Product

Resources

About