TY - GEN
T1 - Eeg signal denoising using hybridizing method between wavelet transform with genetic algorithm
AU - Alyasseri, Zaid Abdi Alkareem
AU - Khader, Ahamad Tajudin
AU - Al-Betar, Mohammed Azmi
AU - Abasi, Ammar Kamal
AU - Makhadmeh, Sharif Naser
N1 - Publisher Copyright:
© Springer Nature Singapore Pte Ltd 2021.
PY - 2021
Y1 - 2021
N2 - The most common and successful technique for signal denoising with non-stationary signals, such as electroencephalogram (EEG) and electrocardiogram (ECG) is the wavelet transform (WT). The success of WT depends on the optimal configuration of its control parameters which are often experimentally set. Fortunately, the optimality of the combination of these parameters can be measured in advance by using the mean squared error (MSE) function. In this paper, genetic algorithm (GA) is proposed to find the optimal WT parameters for EEG signal denoising. It is worth mentioning that this is the initial investigation of using optimization method for WT parameter configuration. This paper then examines which efficient algorithm has obtained the minimum MSE and the best WT parameter configurations. The performance of the proposed algorithm is tested using two standard EEG dataset, namely, EEG Motor Movement/Imagery dataset. The results of the proposed algorithm are evaluated using five common criteria: signal-to-noise-ratio (SNR), SNR improvement, mean square error (MSE), root mean square error (RMSE), and percentage root mean square difference (PRD). In conclusion, the results show that the proposed method for EEG signal denoising can produce better results than manual configurations based on ad hoc strategy. Therefore, using metaheuristic approaches to optimize the parameters for EEG signals positively affects the denoising process performance of the WT method.
AB - The most common and successful technique for signal denoising with non-stationary signals, such as electroencephalogram (EEG) and electrocardiogram (ECG) is the wavelet transform (WT). The success of WT depends on the optimal configuration of its control parameters which are often experimentally set. Fortunately, the optimality of the combination of these parameters can be measured in advance by using the mean squared error (MSE) function. In this paper, genetic algorithm (GA) is proposed to find the optimal WT parameters for EEG signal denoising. It is worth mentioning that this is the initial investigation of using optimization method for WT parameter configuration. This paper then examines which efficient algorithm has obtained the minimum MSE and the best WT parameter configurations. The performance of the proposed algorithm is tested using two standard EEG dataset, namely, EEG Motor Movement/Imagery dataset. The results of the proposed algorithm are evaluated using five common criteria: signal-to-noise-ratio (SNR), SNR improvement, mean square error (MSE), root mean square error (RMSE), and percentage root mean square difference (PRD). In conclusion, the results show that the proposed method for EEG signal denoising can produce better results than manual configurations based on ad hoc strategy. Therefore, using metaheuristic approaches to optimize the parameters for EEG signals positively affects the denoising process performance of the WT method.
KW - EEG
KW - Genetic algorithm
KW - Metaheuristic algorithms
KW - Signal denoising
KW - Wavelet transform
UR - https://www.scopus.com/pages/publications/85088534299
U2 - 10.1007/978-981-15-5281-6_31
DO - 10.1007/978-981-15-5281-6_31
M3 - Conference contribution
AN - SCOPUS:85088534299
SN - 9789811552809
T3 - Lecture Notes in Electrical Engineering
SP - 449
EP - 469
BT - Proceedings of the 11th National Technical Seminar on Unmanned System Technology, NUSYS 2019
A2 - Md Zain, Zainah
A2 - Ahmad, Hamzah
A2 - Pebrianti, Dwi
A2 - Mustafa, Mahfuzah
A2 - Abdullah, Nor Rul Hasma
A2 - Samad, Rosdiyana
A2 - Mat Noh, Maziyah
PB - Springer
T2 - 11th National Technical Symposium on Unmanned System Technology, NUSYS 2019
Y2 - 2 December 2019 through 3 December 2019
ER -