A Multi-View Deep Learning Framework for EEG Seizure Detection

Yuan, Ye; Xun, Guangxu; Jia, Kebin; Zhang, Aidong

doi:10.1109/jbhi.2018.2871678

Cited by 191 publications

(85 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For each training iteration, the sliding window method was used to calculate Pearson's correlation coefficient for 160 ROIs from a subject's brain, which enlarged the total sample size so that the autoencoder could examine the functional connectivity patterns more completely. The autoencoder is an unsupervised learning algorithm that can effectively mine hidden low-dimensional representations from data, which can then be used to reconstruct the original data (Tschannen et al, 2018). In this paper, we used a grid search to set and optimize the learning rate, batch size, epoch and other parameters of the autoencoder (Figure 2).…”

Section: Dnn With Ae Pretrainingmentioning

confidence: 99%

Detecting the Information of Functional Connectivity Networks in Normal Aging Using Deep Learning From a Big Data Perspective

et al. 2020

View full text Add to dashboard Cite

Section: Dnn With Ae Pretrainingmentioning

confidence: 99%

Detecting the Information of Functional Connectivity Networks in Normal Aging Using Deep Learning From a Big Data Perspective

et al. 2020

View full text Add to dashboard Cite

“…As seen, most of the previous works ignored such selection issues and only focus on detection via developing special features or classifiers. Additionally, although several works [46], [47] have performed the selection, they have not provided the details or results about the selected channels and meanwhile, the statistical analysis among different patients was also missing. Hence, by mean of the similarity analysis of the brain rhythm patterns in the proposed sequences, the synchrony of signals has been evaluated and such operation is helpful for selecting the representatives of each patient.…”

Section: Performance Evaluationmentioning

confidence: 99%

Brain Rhythm Sequencing Using EEG Signals: A Case Study on Seizure Detection

Barma

Mak

et al. 2019

IEEE Access

View full text Add to dashboard Cite

A technique based on five brain rhythms (δ, θ, α, β, and γ) presented in the sequence for analyzing Electroencephalography (EEG) signals has been proposed. First, the production of the sequence has been accomplished by selecting the prominent brain rhythm having the maximum instantaneous power at specific timestamp consecutively throughout the EEG. To this purpose, the reassigned smoothed pseudo Wigner-Ville distribution (RSPWVD) has been employed. Then, in order to verify the proposed technique and evaluate its performance, a case study of seizure detection has been implemented. As experimental validation, 93 patients from the Karunya database have been investigated. Moreover, to characterize the brain rhythm sequence for seizure detection, two additional indices derived from the power discharge and synchronous behavior have been applied. Results show that the particular rhythm pattern during the seizure is usually one type (either δ, θ, or α) and it is subject-dependent. Hence, by focusing on the changes of such particular rhythm through the two indices, the time-related occurrences of seizures can be determined in detail. Meanwhile, the representative channels for seizure detection can be found by studying the similarity of sequences, which are helpful to reduce the number of applied channels. Finally, the proposed technique provides an accuracy of 98.9%, which demonstrates it is competent to detect the appearances of abnormal seizures from the EEG signals reliably. Consequently, the brain rhythm sequencing could open a new way to interpret and characterize the EEG in various applications such as for epileptic patients. INDEX TERMS Brain rhythm sequencing, electroencephalography (EEG), time-frequency analysis (TFA), reassigned smoothed pseudo Wigner-Ville distribution (RSPWVD), seizure detection.

show abstract

“…A private database provided by CHUV will be used. The algorithm used for preprocessing and classifying will initially be the most relevant one in the state-of-the-art that use Deep Learning techniques for population-wide analysis [5,6,7].…”

Section: Uc13: Epileptic Seizures Detection (Epfl and Chuv)mentioning

confidence: 99%

Deep-Learning and HPC to Boost Biomedical Applications for Health (DeepHealth)

Caballero

Gómez

Bantouna

2019

2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS)

View full text Add to dashboard Cite

This document introduces the DeepHealth project: "Deep-Learning and HPC to Boost Biomedical Applications for Health". This project is funded by the European Commission under the H2020 framework program and aims to reduce the gap between the availability of mature enough AIsolutions and their deployment in real scenarios. Several existing software platforms provided by industrial partners will integrate state-of-the-art machine-learning algorithms and will be used for giving support to doctors in diagnosis, increasing their capabilities and efficiency. The DeepHealth consortium is composed by 21 partners from 9 European countries including hospitals, universities, large industry and SMEs.

show abstract

A Multi-View Deep Learning Framework for EEG Seizure Detection

Cited by 191 publications

References 58 publications

Detecting the Information of Functional Connectivity Networks in Normal Aging Using Deep Learning From a Big Data Perspective

Detecting the Information of Functional Connectivity Networks in Normal Aging Using Deep Learning From a Big Data Perspective

Brain Rhythm Sequencing Using EEG Signals: A Case Study on Seizure Detection

Deep-Learning and HPC to Boost Biomedical Applications for Health (DeepHealth)

Contact Info

Product

Resources

About