Optimized Feature Selection for Enhanced Epileptic Seizure Detection

Sivasankari, K.; Thanushkodi, K.; Suguna, N.

doi:10.2174/157340561001140424143814

Cited by 5 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Iasemidis et al calculated the change in Lyapunov's index Lmax during seizures in the preictal, preictal and postictal periods, respectively, and demonstrated that the Lmax values were from small to large in the preictal, preictal and postictal periods, respectively, and that this phenomenon could be used to predict seizures 17 . In addition, to improve the accuracy of epilepsy prediction, combined linear and nonlinear methods have been In 2009, Mirowski et al 18 used a combination of six linear and nonlinear binary features In 2009, and transformed them into feature images to detect interictal EEG and preictal EEG using convolutional neural networks and support vector machines (SVM). In 15 patients, 71% sensitivity was achieved with no false detections.…”

Section: Introductionmentioning

confidence: 99%

A particle swarm algorithm optimization‐based SVM–KNN algorithm for epileptic EEG recognition

Wang

Ling

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

Epilepsy is a disease caused by abnormal discharges in the central nervous system. Automatic detection and accurate identification of epileptic seizures based on electroencephalography (EEG) are significant in the clinical diagnosis and treatment of epilepsy. In this paper, we first decompose the patient's EEG signal into multiple intrinsic modal functions (IMFs) using empirical modal decomposition, then compute the mean, standard deviation, fluctuation index, and sample entropy of IMF1, and finally classify them using a fusion algorithm of support vector machine and K‐nearest neighbor optimized by particle swarm algorithm. The results of validation using the epileptic EEG data set from Bonn University show that the auto‐detection and fast recognition method proposed in this paper can achieve a high seizure accuracy recognition rate (≥95%) with only a small number of training samples, which has a good clinical application value.

show abstract

Section: Introductionmentioning

confidence: 99%

A particle swarm algorithm optimization‐based SVM–KNN algorithm for epileptic EEG recognition

Wang

Ling

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

show abstract

“…Due to this fact, most of the seizure detection methods require a selection phase for the relevant channels to make it feasible for classifiers to learn the features. It was recently shown in Sivasankari, Gowder Thanushkodi, and Suguna (2014) that performing a feature selection using genetic algorithm (GA) can significantly reduce the number of false alarms. In another study, Kolmogorov-Smirnov (K-S) test was taken into account to perform feature selection over extracted fuzzy entropy values of different channels (Xiang et al, 2015).…”

Section: Introductionmentioning

confidence: 99%