A novel robust diagnostic model to detect seizures in electroencephalography

Swami, Piyush; Gandhi, Tapan Kumar; Panigrahi, B. K.; Tripathi, Manjari; Anand, Sneh

doi:10.1016/j.eswa.2016.02.040

Cited by 178 publications

(64 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the following paragraphs, we give an overview of the related state-of-the-art techniques, which use different feature extraction and classification methods for classification of epileptic and non-epileptic EEG signals. Swami et al (Swami et al, 2016) extracted hand-crafted features such as Shannon entropy, standard deviation, and energy. They employed the general regression neural network (GRNN) classifier to classify these features and achieved maximum accuracy, i.e., 100% and 99.18% for A-E (non-seizure vs. seizure) and AB-E (normal vs. seizure) cases, respectively on University of Bonn dataset.…”

Section: Literature Reviewmentioning

confidence: 99%

An automated system for epilepsy detection using EEG brain signals based on deep learning approach

Ullah

Hussain

Qazi

et al. 2018

Expert Systems with Applications

490

213

View full text Add to dashboard Cite

Epilepsy is a neurological disorder and for its detection, encephalography (EEG) is a commonly used clinical approach. Manual inspection of EEG brain signals is a time-consuming and laborious process, which puts heavy burden on neurologists and affects their performance. Several automatic techniques have been proposed using traditional approaches to assist neurologists in detecting binary epilepsy scenarios e.g. seizure vs. non-seizure or normal vs. ictal. These methods do not perform well when classifying ternary case e.g. ictal vs. normal vs. inter-ictal; the maximum accuracy for this case by the state-of-the-art-methods is 97±1%. To overcome this problem, we propose a system based on deep learning, which is an ensemble of pyramidal one-dimensional convolutional neural network (P-1D-CNN) models. In a CNN model, the bottleneck is the large number of learnable parameters. P-1D-CNN works on the concept of refinement approach and it results in 60% fewer parameters compared to traditional CNN models. Further to overcome the limitations of small amount of data, we proposed augmentation schemes for learning P-1D-CNN model. In almost all the cases concerning epilepsy detection, the proposed system gives an accuracy of 99.1±0.9% on the University of Bonn dataset.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

An automated system for epilepsy detection using EEG brain signals based on deep learning approach

Ullah

Hussain

Qazi

et al. 2018

Expert Systems with Applications

490

213

View full text Add to dashboard Cite

show abstract

“…As such, automatic epileptic seizure detection has become a hot research topic [1][2][3][4][5]. Recently, an incident report of epilepsy, one of the most common neurological disorders, stated that the prevalence is about 1 to 2% among the global population, and is rapidly increasing in the elderly population [1,[4][5][6]. In the past several decades, although new anti-epileptic drugs had been invented, a third of epileptic patients are still suffering from epileptic seizures.…”

Section: Introductionmentioning

confidence: 99%

“…The significant differences between epileptic seizure and healthy states are generally highlighted as the frequency and patterns of neurons, meaning the spatial-temporal patterns of neurons gradually increase from the normal state to epileptic seizure-free state and then to the epileptic seizure state [7,9]. The World Health Organization (WHO) stipulates that epilepsy is caused by a group of brain cells with unexpected, uncontrolled electrical discharges, termed 'epileptic seizures' [6,9,10]. In 1929, Berger first measured the spontaneous electrical activity in the brain using electrodes, with electroencephalographic (EEG) signals being produced.…”

Section: Introductionmentioning

confidence: 99%

“…In the past and at present, well-trained and experienced neurophysiologists are employed universally to detect epileptic seizures through conventional methods by inspecting EEG signals over a long period [6,9,10,[13][14][15][16]. Practically, to ensure high accuracy, detailed evaluations are essential, such as brain imaging tests like magnetic resonance imaging (MRI), computed tomography (CT), long-term EEG tests, blood tests, and medical history examination [15,[17][18][19][20][21][22][23][24].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cepstrum Coefficient Analysis from Low-Frequency to High-Frequency Applied to Automatic Epileptic Seizure Detection with Bio-Electrical Signals

Ren

Chai

et al. 2018

Applied Sciences

View full text Add to dashboard Cite

This study analyzes bioelectrical signals to achieve automatic epileptic seizure detection. Electroencephalographic (EEG) signals were recorded with electrodes on healthy, epileptic seizure-free, and epileptic seizure patients. The challenges in this field are generally regarded to be the impacts of non-stationarity and nonlinearity in EEG signals. To address these challenges, this study attempts to recognize different brain statuses. The idea originated from a novel hypothesis that considers EEG signals as convolution signals and regards itself as the generation mechanism of EEG signals, to some extent. Based on this hypothesis, the nonlinear problem can be viewed as a deconvolution procedure. As such, the method can be simplified into three parts: eliminating non-stationary is used to catch high-frequency to low-frequency signals, which is followed by a local mean decomposition (LMD) algorithm; these signals are deconvoluted to form ultra-high-dimensional feature sets, which is completely terminated by the mel-frequency cepstrum coefficients (MFCC) algorithm; and several classifiers are combined to achieve highly accurate recognition results and to verify the superiority and reasonableness of this method. The publicly available EEG database from the University of Bonn, Germany is employed to demonstrate the effectiveness and outstanding performance of this method. According to the results, the method has the ability to attain a higher average classification accuracy than other methods in all of the four following cases: healthy (datasets A and B) versus epileptic seizure (dataset E), epileptic seizure-free (datasets C and D) versus epileptic seizure (dataset E), healthy (datasets A and B) versus epileptic seizure-free (datasets C and D) versus epileptic seizure (dataset E), and healthy (dataset A) versus healthy (dataset B) versus epileptic seizure-free (dataset C) versus epileptic seizure-free (dataset D) versus epileptic seizure (dataset E).

show abstract

“…Epilepsy is a chronic brain disorder characterised by recurrent seizures [1], [2]. They are brief stretches of involuntary movement affecting either a part of the body or the entire body and occur due to the excessive electrical discharges in a group of brain cells.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Epileptic Seizures based on Mean Phase Coherence

Aggarwal

Gandhi²

2017

Preprint

Self Cite

View full text Add to dashboard Cite

Abstract-Around 1-2 % of the world's population suffers from epilepsy and 20 % of that vulnerable mass can't be cured through surgery or medicine. Epileptic seizures often occur unpredictably and may cause serious damage to the patient in adverse situations, for e.g. getting a seizure while driving or crossing a road can be fatal. In such a scenario, a reliable mechanism to predict the onset of seizure beforehand is much desirable. In this study, A reliable real-time technique for prediction of epileptic seizures is presented. Mean Phase Coherence (MPC), as a measure of phase synchronization, is used to predict impending seizures in a multi-channel EEG data. It was found that during the pre-ictal stages, MPC values and thus phase synchronization between various channels was found to drop significantly below the level in a non-ictal EEG signal. The range of the prediction horizon for seizures varied from 4-10 mins and prediction of impending seizure attack is possible for 8 out of 10 test cases.

show abstract

A novel robust diagnostic model to detect seizures in electroencephalography

Cited by 178 publications

References 29 publications

An automated system for epilepsy detection using EEG brain signals based on deep learning approach

An automated system for epilepsy detection using EEG brain signals based on deep learning approach

Cepstrum Coefficient Analysis from Low-Frequency to High-Frequency Applied to Automatic Epileptic Seizure Detection with Bio-Electrical Signals

Prediction of Epileptic Seizures based on Mean Phase Coherence

Contact Info

Product

Resources

About