2014
DOI: 10.1016/j.asoc.2014.01.029
|View full text |Cite
|
Sign up to set email alerts
|

Genetic algorithms tuned expert model for detection of epileptic seizures from EEG signatures

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
25
0
1

Year Published

2015
2015
2021
2021

Publication Types

Select...
4
4
1

Relationship

0
9

Authors

Journals

citations
Cited by 61 publications
(26 citation statements)
references
References 37 publications
0
25
0
1
Order By: Relevance
“…Ahila et al [27] present a PSO method for tuning Extreme Learning Machines (ELM) and for FS in the classification of power system disturbances. Dhiman et al [28] propose a hybrid approach with wavelet packet decomposition and a GA-SVM scheme for FS and MPO to obtain classification models capable of detecting epileptic seizures from background electroencephalogram signals. Castillo et al [29,30] optimize membership functions of complex fuzzy controllers with ant colony optimization (ACO).…”
Section: Related Research On Parsimonious Modeling With Soft Computingmentioning
confidence: 99%
“…Ahila et al [27] present a PSO method for tuning Extreme Learning Machines (ELM) and for FS in the classification of power system disturbances. Dhiman et al [28] propose a hybrid approach with wavelet packet decomposition and a GA-SVM scheme for FS and MPO to obtain classification models capable of detecting epileptic seizures from background electroencephalogram signals. Castillo et al [29,30] optimize membership functions of complex fuzzy controllers with ant colony optimization (ACO).…”
Section: Related Research On Parsimonious Modeling With Soft Computingmentioning
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%
“…Once the features are extracted, these features are processed for classification. The final step employs different classifiers, such as adaptive neuro‐fuzzy inference system classifiers (Güler et al, ), neural networks (Alam & Bhuiyan, ; Guo, Rivero, Dorado, et al, ; Guo, Rivero, & Pasos, ; Kumar et al, ; Pachori & Patidar, ; Srinivasan et al, ; Übeyli, ; Übeyli, ), and support vector machines (Dhiman et al, ; Fu et al, ; Joshi, Pachori, & Vijesh, ; Parvez & Paul, ; Sharma & Pachori, ; Xiang et al, ). Feature analysis is often ambiguous and computationally complex.…”
Section: Introductionmentioning
confidence: 99%
“…Frequency analysis typically employs Fourier transform, although Fourier transform is now often replaced by time/frequency analyses. For time/frequency analyses, the time series signal is transformed through wavelet transforms/wavelet packet decompositions (Chen, 2014;Dhiman et al, 2014;Güler, Übeyli, & Güler, 2005;Guo, Rivero, Dorado, Rabunal, & Pasos, 2010b;Guo, Rivero, & Pasos, 2010a;Kumar, Dewal, & Anand, 2012a;Ocak, 2009;Wang, Miao, & Xie, 2011). The features are then extracted through transformations in each selected subband using energy, entropies, or a modified mixture of methods.…”
mentioning
confidence: 99%