TY - GEN
T1 - Electroencephalogram signals denoising using various mother wavelet functions
T2 - 2017 International Conference on Imaging, Signal Processing and Communication, ICISPC 2017
AU - Alyasseri, Zaid Abdi Alkareem
AU - Khader, Ahamad Tajudin
AU - Al-Betar, Mohammed Azmi
N1 - Publisher Copyright:
© 2017 Association for Computing Machinery.
PY - 2017/7/26
Y1 - 2017/7/26
N2 - In this paper, various mother wavelet functions are proposed for ElectroEncephaloGram (EEG) signal denoising problem. EEG is a graphical measuring of the brain electrical activity which is recording from the scalp. It represents the voltage fluctuations resulting from ionic current flows within the neurons of the brain. During recording time, there are several artifacts noises can corrupt the original EEG signal such as eye blink, eye movements, muscles activity, and interference of power line. Therefore, the EEG signals should be processed to remove these noises obtaining the efficient EEG features. Several techniques have been proposed for EEG noises reduction in which one of these techniques is an EEG signal denoising using wavelet transform (WT). Selection efficient mother wavelet function (Φ) is considered as a critical parameter in wavelet denoising for non-stationary signal because it will affect the denoised signal. In this paper, four mother wavelet functions (i.e, db4, sym7, bior3.9, and coif3) are tested using standard EEG dataset which is established by Kiern and Aunon. The selected mother wavelet functions evaluation using five criteria which are: Signal-to-Noise-Ration (SNR), SNR improvement, Mean Square Error (MSE), Root Mean Square Error (RMSE), and percentage root mean square difference (PRD. Finally, the coif3 achieves the efficient EEG signal denoising for Power Line Noise (PLN) and Electromyogram (EMG) noise. In addition, sym7 obtained the best result with White Gaussian Noise (WGN).
AB - In this paper, various mother wavelet functions are proposed for ElectroEncephaloGram (EEG) signal denoising problem. EEG is a graphical measuring of the brain electrical activity which is recording from the scalp. It represents the voltage fluctuations resulting from ionic current flows within the neurons of the brain. During recording time, there are several artifacts noises can corrupt the original EEG signal such as eye blink, eye movements, muscles activity, and interference of power line. Therefore, the EEG signals should be processed to remove these noises obtaining the efficient EEG features. Several techniques have been proposed for EEG noises reduction in which one of these techniques is an EEG signal denoising using wavelet transform (WT). Selection efficient mother wavelet function (Φ) is considered as a critical parameter in wavelet denoising for non-stationary signal because it will affect the denoised signal. In this paper, four mother wavelet functions (i.e, db4, sym7, bior3.9, and coif3) are tested using standard EEG dataset which is established by Kiern and Aunon. The selected mother wavelet functions evaluation using five criteria which are: Signal-to-Noise-Ration (SNR), SNR improvement, Mean Square Error (MSE), Root Mean Square Error (RMSE), and percentage root mean square difference (PRD. Finally, the coif3 achieves the efficient EEG signal denoising for Power Line Noise (PLN) and Electromyogram (EMG) noise. In addition, sym7 obtained the best result with White Gaussian Noise (WGN).
KW - Electroencephalogram
KW - Mother wavelet
KW - SNR
KW - Signal denoising
KW - Wavelet Transform
KW - Wavelet parameters
UR - https://www.scopus.com/pages/publications/85034437536
U2 - 10.1145/3132300.3132313
DO - 10.1145/3132300.3132313
M3 - Conference contribution
AN - SCOPUS:85034437536
T3 - ACM International Conference Proceeding Series
SP - 100
EP - 105
BT - Proceedings of 2017 International Conference on Imaging, Signal Processing and Communication, ICISPC 2017
PB - Association for Computing Machinery
Y2 - 26 July 2017 through 28 July 2017
ER -