Seizure detection with single-channel EEG using Extreme Learning Machine

Ammar, Sabrina; Sarwat, Mohamed

doi:10.1109/sta.2016.7952088

Cited by 19 publications

(14 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where Ψ (t) signifies the wavelet. WT was carried out to extract temporal measures in which spectral and temporal measures where the temporal features like mean, normalized coefficient of variation (NCOV), STD, skewness, kurtosis, spectral characteristics, mean PSD, and peak PSD were extracted [49]. DWT is used for the characterization of a signal as an infinite set of wavelets on an orthonormal basis [86].…”

Section: Continuous Wavelet Transform (Cwt)mentioning

confidence: 99%

“…Epileptic seizure detection was performed with wavelet-based feature and time domain features employing the SVM classifier [48]. Time-frequency domain feature extraction was done, and an ELM classifier was utilized to distinguish seizures from non-seizures [49]. Three features were extracted, and classification was provided by six well-known classifiers, namely RF classifier, Functional tree (FT) classifier, K-NN, C4.5 classifier, NB, and Bayes Net [50].…”

Section: Classificationmentioning

confidence: 99%

“…The patientindependent and patient-dependent classification was developed by investigating wavelet characteristics with an SVM classifier, achieving an overall precision of 96.87% [48]. Temporal and spectral characteristics were extracted using WT, and these characteristics were given to ELM for automated epilepsy classification, which achieved 94.85% classification accuracy [49]. The low-complexity seizure prediction technique was explored for the use of attractor state analysis where the linear spectral characteristic was evaluated, resulting in a sensitivity of 86.67% [50].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automated Epileptic Seizure Detection in Pediatric Subjects of CHB-MIT EEG Database—A Survey

Prasanna

Subathra

Mohammed

et al. 2021

JPM

View full text Add to dashboard Cite

Epilepsy is a neurological disorder of the brain that causes frequent occurrence of seizures. Electroencephalography (EEG) is a tool that assists neurologists in detecting epileptic seizures caused by an unexpected flow of electrical activities in the brain. Automated detection of an epileptic seizure is a crucial task in diagnosing epilepsy which overcomes the drawback of a visual diagnosis. The dataset analyzed in this article, collected from Children’s Hospital Boston (CHB) and the Massachusetts Institute of Technology (MIT), contains long-term EEG records from 24 pediatric patients. This review paper focuses on various patient-dependent and patient-independent personalized medicine approaches involved in the computer-aided diagnosis of epileptic seizures in pediatric subjects by analyzing EEG signals, thus summarizing the existing body of knowledge and opening up an enormous research area for biomedical engineers. This review paper focuses on the features of four domains, such as time, frequency, time-frequency, and nonlinear features, extracted from the EEG records, which were fed into several classifiers to classify between seizure and non-seizure EEG signals. Performance metrics such as classification accuracy, sensitivity, and specificity were examined, and challenges in automatic seizure detection using the CHB-MIT database were addressed.

show abstract

Section: Continuous Wavelet Transform (Cwt)mentioning

confidence: 99%

Section: Classificationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automated Epileptic Seizure Detection in Pediatric Subjects of CHB-MIT EEG Database—A Survey

Prasanna

Subathra

Mohammed

et al. 2021

JPM

View full text Add to dashboard Cite

show abstract

“…Traditionally, Digital filters are used to remove noise from the observed signal and to reduce its undesirable frequency components [3]. Single channel EEG signals were analysed for seizure detection in [6] and [7]. An accuracy of over 90% was achieved in the former after experimenting with multiple classification primitives and SVM ensemble parameters.…”

Section: Figmentioning

confidence: 99%

“…Extreme Learning Machines [7] and Support Vector Machine ensembles [6], which were used with single channel EEG signals can be applied to multi-channel EEG signals as a part of further research. Whether or not using the leaky ReLU activation function along with the BRNN can lead to further improvement in training stage is another area for further research.…”

Section: Potential For Further Researchmentioning

confidence: 99%

A Proposal to Automate Seizure Detection based on a Comparative Study of EEG Signal Analysis

Telang¹,

More²,

Modi³

et al. 2017

IJCA

View full text Add to dashboard Cite

Epilepsy is a chronic neurological disorder which is characterized by recurrent and sudden seizures. People with epilepsy suffer from multiple types of seizures and Electroencephalography is an important clinical tool for diagnosing, monitoring and managing neurological disorders related to epilepsy. EEG signals are most often used to diagnose epilepsy, as seizures cause anomalies in EEG readings. In today's world where adult life expectancy is rising and humans are living longer than ever before, the healthcare system generates vast amounts of data, including EEG signals. This paper examines the prospects and challenges faced in utilizing this data in order to optimize seizure detection in order to improve the patients' quality of life. This paper also explores how Machine Learning can be applied to extract features and analyze the EEG signals and propose methods to achieve high classification accuracy.

show abstract

Epileptic Seizure Detection Using Deep Recurrent Neural Networks in EEG Signals

Janghel

2020

Advances in Biomedical Engineering and Technology

View full text Add to dashboard Cite

Seizure detection with single-channel EEG using Extreme Learning Machine

Cited by 19 publications

References 10 publications

Automated Epileptic Seizure Detection in Pediatric Subjects of CHB-MIT EEG Database—A Survey

Automated Epileptic Seizure Detection in Pediatric Subjects of CHB-MIT EEG Database—A Survey

A Proposal to Automate Seizure Detection based on a Comparative Study of EEG Signal Analysis

Epileptic Seizure Detection Using Deep Recurrent Neural Networks in EEG Signals

Contact Info

Product

Resources

About