Detection of Epileptic Seizure Based on ReliefF Algorithm and Multi-support Vector Machine

Praveena, Hirald Dwaraka; Subhas, C.; Naidu, K. Rama

doi:10.1007/978-981-15-1451-7_2

Cited by 3 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 3 illustrates how to evaluate time and frequency resolutions when using the wavelet transform approach. Signals can be analyzed using the wavelet transform as a linear combination of the mother wavelet and the sum of the wavelet coefficients, which does not add any extra information to the original signal [4][5]. However, signal denoising greatly depends on the choice of an appropriate wavelet function and thresholding technique.…”

Section: Wavelet Transformmentioning

confidence: 99%

Comprehensive Time-Frequency Analysis of Noisy ECG Signals – A Review

Praveena¹,

Sudha²,

P.³

et al. 2022

View full text Add to dashboard Cite

This article is based on a comparison of various time-frequency analysis techniques for reducing noise in an ECG signal. Noise continuously degrades the quality of the ECG signal. Due to the ECG signal’s time-varying nature, ECG noise reduction is extremely challenging. The diagnosis of heart disorders requires an ECG signal of high quality. This study presents a survey of several techniques and noise types that can distort the ECG signal. The signal is denoised using effective denoising techniques such as the Wavelet Transform, Empirical Mode Decomposition (EMD), Empirical Wavelet Transform (EWT), Short Time Fourier Transform (STFT), Ensemble and Empirical Mode Decomposition (EEMD). Compared to previous de-noising approaches, the EWT de-noising methodology is more effective and has a lower computing complexity.

show abstract

Section: Wavelet Transformmentioning

confidence: 99%

Comprehensive Time-Frequency Analysis of Noisy ECG Signals – A Review

Praveena¹,

Sudha²,

P.³

et al. 2022

View full text Add to dashboard Cite

show abstract

“…However, even though they were not directly impacted by the seizures, non-focal epilepsy has an impact on numerous brain regions. [9][10]. Therefore, they need surgical interference to treat the seizures as well as reduce the risks accompanied by International Journal of Intelligent Engineering and Systems, Vol.…”

Section: Introductionmentioning

confidence: 99%

Improved Artificial Bee Colony Based Feature Selection for Epileptic Seizure Detection

2023

IJIES

View full text Add to dashboard Cite

According to WHO, 6 million people are affected by an epileptic seizure every year as per a survey carried out in 2019. At the moment, doctors use direct observation of the electroencephalogram (EEG) signal to determine the presence of an epileptic seizure. However, epileptic detection in most of the previous research works suffers from low accuracy and is unsuitable for processing large datasets. In this work, the seizure EEG signal is effectively detected and enhanced using Chebyshev normalization. Additionally, the signals are decomposed by applying fast empirical mode decomposition (EMD). Then, entropy features are extracted and effective selection is obtained by using the improved artificial bee colony (ABC) optimization algorithm. Finally, a stacked autoencoder (SAE) is used for better EEG classification. The existing researches such as MCAFF, CNN-RNN, ESSA, SVM and 1D-CNN are used for comparing the IABC-SAE method. The proposed IABC-SAE method gained better performance in seizure EEG signal identification and achieves higher classification accuracy (CA) of 99.98% in TUH-EEG database compared to the existing ESSA.

show abstract