A Novel Signal Modeling Approach for Classification of Seizure and Seizure-Free EEG Signals

Gupta, Anubha; Singh, Pushpendra; Karlekar, Mandar

doi:10.1109/tnsre.2018.2818123

Cited by 137 publications

(50 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gupta et al [19] developed the automatic seizures detection framework on EEG signals. A multi-rate structure was constructed centered on the vectors of the DCT (discrete cosines transform).…”

Section: Related Workmentioning

confidence: 99%

Hybrid Dragonfly Optimization-Based Artificial Neural Network for the Recognition of Epilepsy

Parthiban¹,

Vijayachitra²,

Dhanapal³

2019

IJCIS

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Hybrid Dragonfly Optimization-Based Artificial Neural Network for the Recognition of Epilepsy

Parthiban¹,

Vijayachitra²,

Dhanapal³

2019

IJCIS

View full text Add to dashboard Cite

“…Electroencephalogram (EEG) is one of the traditional and easiest tool for the identification and diagnosis of seizures [5]. The availability of EEG for common people within their budgetary limits made it a typical method.…”

Section: Introductionmentioning

confidence: 99%

Empirical Mode Decomposition of EEG Signals for the Effectual Classification of Seizures

Ok¹,

Rajesh²

2020

Advances in Neural Signal Processing

View full text Add to dashboard Cite

Empirical mode decomposition (EMD) is a remarkable method for the analysis of nonlinear and non-stationary data. EMD will breakdown the given signal into intrinsic mode functions (IMFs), which can represent natural signals effectively. In this work, the competence of EMD with traditional features to classify the seizure and non-seizure EEG signals is studied. Due to the complex nature of human brain, the EEG signals which are recorded from different regions of brain are nonstationary in nature. Different features such as entropy features (approximate entropy (ApEn), sample entropy (SmEn), Shannon entropy (ShEn), Rényi entropy (RnEn)), fractal dimension features (Petrosian fractal dimension, Higuchi fractal dimension, Katz fractal dimension), statistical features (mean, standard deviation and energy) and exponential energy features are extracted from IMFs and fed to a SVM classifier. The performances of extracted features are studied independently. The result shows that, the EMD method is well suited for complex seizure EEG signal classification.

show abstract

“…Features such as Hurst component and autoregressive moving average (ARMA) parameters were extracted for building Support Vector Machine (SVM) classifier. This is only suitable for small database [5]. The proposed method extracts features using Fourier transform and then Deep learning technique based on multilayer perceptron is applied for classification.…”

Section: Introductionmentioning

confidence: 99%

Performance Analysis of Machine Learning Algorithms for Classification of Electroencephalogram Signals for Detection of Seizures

Garde¹

2020

IJRASET

View full text Add to dashboard Cite

Over fifty million people in the world are affected by a neurological disorder namely Seizures. The seizure occurs due to uncontrolled electrical activities inside the brain. It may cause changes in someone's behaviour, movement, or emotions. Many seizures last for about 30 seconds to two minutes. Electroencephalogram (EEG) signals are used to detect the existence of seizures. The detection of seizures is very important from the patient's point of view. Therefore, there is a need to study and explore machine learning algorithms which may learn various patterns in the EEG datasets and perform accurate classification. In this work, the algorithms like K-nearest neighbour (KNN), Naïve Bayes (NB), Decision tree (DT) and Random forest (RF) are compared for classification of EEG dataset. These algorithms are applied on extracted features which result in the classification of EEG signals and are classified as seizures and non-seizures. After experimentation, it is observed that Random Forest gives best accuracy.

show abstract

A Novel Signal Modeling Approach for Classification of Seizure and Seizure-Free EEG Signals

Cited by 137 publications

References 65 publications

Hybrid Dragonfly Optimization-Based Artificial Neural Network for the Recognition of Epilepsy

Hybrid Dragonfly Optimization-Based Artificial Neural Network for the Recognition of Epilepsy

Empirical Mode Decomposition of EEG Signals for the Effectual Classification of Seizures

Performance Analysis of Machine Learning Algorithms for Classification of Electroencephalogram Signals for Detection of Seizures

Contact Info

Product

Resources

About