Dual Optimization of Deep CNN for Motor Imagery EEG Tasks Classification
Keywords:
Convolutional Neural Network, Cropping, Deep Learning, Electroencephalographic, Genetic Algorithm, Motor ImageryAbstract
The motor imagery (MI) electroencephalographic (EEG) signals are leveraged as control commands to numerus engineering applications, such as operating a wheelchair through thought alone. EEG signals are characterized by their non-stationary nature and high dimensionality, posing noteworthy challenges for building robust identification models with limited data samples. The renewed deep convolutional neural network (CNN) has been harnessed in various fields due to its ability to autonomously extract and select latent features addressing problems across various types of EEG signals. However, CNN architectures comprise a vast parameter and hyperparameter space. Normally, parameters are optimized via the back-propagation algorithm, while hyperparameters are adjusted through a lengthy trial-and-error process. This work mitigates the aforementioned problems by employing the genetic algorithm (GA) as an artificial intelligence optimization tool for optimizing crucial architectural hyperparameters including the number of convolution filters, size of filters, and dropout probability. Furthermore, the two parameters of cropping augmentation, used for boosting the EEG training samples, are also optimized by the GA. The proposed model in this paper (GACNN) that includes dual optimization, achieved both by the back-propagation algorithm and GA, has attained promising results in the analysis of MI EEG signals. Experiments are performed on the known brain-computer interface competition IV 2a dataset (BCIC IV 2a). GACNN has recorded an increment of about 17% in Cohen’s kappa coefficient and a decrement of about 30% in standard deviation (SD) in comparison to state-of-the-art studies.
Downloads
References
S. R. Sreeja, Himanshu, and D. Samanta, “Distance-based weighted sparse representation to classify motor imagery EEG signals for BCI applications,” Multimed Tools Appl, vol. 79, pp. 13775–1379, 2020, doi: 10.1007/s11042-019-08602-0.
W. Zgallai et al., “Deep Learning AI Application to an EEG driven BCI Smart Wheelchair,” in 2019 Advances in Science and Engineering Technology International Conferences (ASET), IEEE, 2019, pp. 1–5.
Z. T. Al-Qaysi, A. Al-Saegh, A. Hussein, and M. A. Ahmed, “Wavelet-based Hybrid Learning Framework for Motor Imagery Classification,” Iraqi Journal for Electrical and Electronic Engineering, vol. 19, no. 1, pp. 47–56, 2023, doi: 10.37917/ijeee.19.1.6.
R. Alazrai, M. Abuhijleh, H. Alwanni, and M. I. Daoud, “A Deep Learning Framework for Decoding Motor Imagery Tasks of the Same Hand Using EEG Signals,” IEEE Access, vol. 7, pp. 109612–109627, 2019, doi: 10.1109/access.2019.2934018.
A. Al-Saegh, “Comparison of Complex-Valued Independent Component Analysis Algorithms for EEG Data,” Iraqi Journal for Electrical and Electronic Engineering, vol. 15, no. 1, pp. 1–12, 2019, doi: 10.37917/ijeee.15.1.1.
H. Raza, H. Cecotti, Y. Li, and G. Prasad, “Adaptive learning with covariate shift-detection for motor imagery-based brain–computer interface,” Soft comput, vol. 20, no. 8, pp. 3085–3096, 2016, doi: 10.1007/s00500-015-1937-5.
H. Wu et al., “A Parallel Multiscale Filter Bank Convolutional Neural Networks for Motor Imagery EEG Classification,” Front Neurosci, vol. 13, no. November, pp. 1–9, 2019, doi: 10.3389/fnins.2019.01275.
G. Ciaparrone, F. Luque Sánchez, S. Tabik, L. Troiano, R. Tagliaferri, and F. Herrera, “Deep learning in video multi-object tracking: A survey,” Neurocomputing, vol. 381, pp. 61–88, 2020, doi: 10.1016/j.neucom.2019.11.023.
J. León et al., “Deep learning for EEG-based motor imagery classification: Accuracy-cost trade-off,” PLoS One, vol. 15, no. 6, pp. 1–30, 2020, doi: 10.1371/journal.pone.0234178.
A. Daood, A. Al-saegh, and A. F. Mahmood, “Handwriting Detection and Recognition of Arabic Numbers and Characters Using Deep Learning Methods,” Journal of Engineering Science and Technology, vol. 18, no. 3, pp. 1581–1598, 2023.
X. Jiang, Z. Hu, S. Wang, and Y. Zhang, “Deep Learning for Medical Image-Based Cancer Diagnosis,” Cancers (Basel), vol. 15, no. 14, 2023, doi: 10.3390/cancers15143608.
M. Ghanim, A. Mohammed, and A. Sali, “Arabic/English Handwritten Digits Recognition using MLPs, CNN, RF, and CNN-RF,” Al-Rafidain Engineering Journal (AREJ), vol. 28, no. 2, pp. 252–260, 2023, doi: 10.33899/rengj.2023.138592.1236.
A. J. Yousif and M. H. Al-Jammas, “Real-time Arabic Video Captioning Using CNN and Transformer Networks Based on Parallel Implementation,” Diyala Journal of Engineering Sciences, vol. 17, no. 1, pp. 84–93, 2024, doi: 10.24237/djes.xxxx.13301.
N. Y. Abdullah and ad Ahmed Al Kazzaz, “Evaluation of Physiotherapy Exercise by Motion Capturing Based on Artificial Intelligence: A Review,” Al-Rafidain Engineering Journal (AREJ), vol. 28, no. 2, pp. 237–251, 2023, [Online]. Available: http://creativecommons.org/licenses/by/4.0/
M. Ramzan and S. Dawn, “Fused CNN-LSTM deep learning emotion recognition model using electroencephalography signals,” International Journal of Neuroscience, vol. 133, no. 6, pp. 587–597, 2023, doi: 10.1080/00207454.2021.1941947.
C. Zhao, J. Li, and Y. Guo, “Sequence signal reconstruction based multi-task deep learning for sleep staging on single-channel EEG,” Biomed Signal Process Control, vol. 88, p. 105615, 2024, doi: https://doi.org/10.1016/j.bspc.2023.105615.
A. Sawan, M. Awad, R. Qasrawi, and M. Sowan, “Hybrid deep learning and metaheuristic model based stroke diagnosis system using electroencephalogram (EEG),” Biomed Signal Process Control, vol. 87, p. 105454, 2024, doi: https://doi.org/10.1016/j.bspc.2023.105454.
F. Hassan and S. F. Hussain, “Review of EEG Signals Classification Using Machine Learning and Deep-Learning Techniques,” in Advances in Non-Invasive Biomedical Signal Sensing and Processing with Machine Learning, S. M. Qaisar, H. Nisar, and A. Subasi, Eds., Cham: Springer International Publishing, 2023, pp. 159–183. doi: 10.1007/978-3-031-23239-8_7.
K. M. Hossain, M. A. Islam, S. Hossain, A. Nijholt, and M. A. R. Ahad, “Status of deep learning for EEG-based brain–computer interface applications,” Front Comput Neurosci, vol. 16, no. i, 2023, doi: 10.3389/fncom.2022.1006763.
A. Craik, Y. He, and J. L. Contreras-Vidal, “Deep learning for electroencephalogram (EEG) classification tasks: A review,” J Neural Eng, vol. 16, no. 3, 2019, doi: 10.1088/1741-2552/ab0ab5.
H. Wu, P. Judd, X. Zhang, M. Isaev, and P. Micikevicius, “Integer quantization for deep learning inference: Principles and empirical evaluation,” ArXiv, pp. 1–20, 2020.
J. Gao, P. Li, Z. Chen, and J. Zhang, “A Survey on Deep Learning for Multimodal Data Fusion,” Neural Comput, vol. 32, pp. 1–36, 2020, doi: 10.1162/NECO.
M. Hersche, L. Benini, L. Benini, and A. Rahimi, “Binarization Methods for Motor-Imagery Brain–Computer Interface Classificatio,” IEEE J Emerg Sel Top Circuits Syst, 2020, doi: 10.1109/JETCAS.2020.3031698.
B. Li et al., “Mixed-Precision Network Quantization for Infrared Small Target Segmentation,” IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pp. 1–12, 2024, doi: 10.1109/TGRS.2023.3346904.
C. He, J. Liu, Y. Zhu, and W. Du, “Data Augmentation for Deep Neural Networks Model in EEG Classification Task: A Review,” Front Hum Neurosci, vol. 15, no. December, 2021, doi: 10.3389/fnhum.2021.765525.
S. Yun, D. Han, S. Chun, S. J. Oh, J. Choe, and Y. Yoo, “CutMix: Regularization strategy to train strong classifiers with localizable features,” Proceedings of the IEEE International Conference on Computer Vision, vol. 2019-Octob, pp. 6022–6031, 2019, doi: 10.1109/ICCV.2019.00612.
C. Rommel, J. Paillard, T. Moreau, and A. Gramfort, “Data augmentation for learning predictive models on EEG: a systematic comparison,” J Neural Eng, vol. 19, no. 6, p. 66020, Nov. 2022, doi: 10.1088/1741-2552/aca220.
A. Al-Saegh, S. A. Dawwd, and J. M. Abdul-Jabbar, “CutCat: An augmentation method for EEG classification,” Neural Networks, vol. 141, no. September 2021, pp. 433–443, 2021, doi: https://doi.org/10.1016/j.neunet.2021.05.032.
R. T. Schirrmeister et al., “Deep learning with convolutional neural networks for EEG decoding and visualization,” Hum Brain Mapp, vol. 38, no. 11, pp. 5391–5420, 2017, doi: 10.1002/hbm.23730.
C. Yaacoub, G. Mhanna, and S. Rihana, “A genetic-based feature selection approach in the identification of left/right hand motor imagery for a brain-computer interface,” Brain Sci, vol. 7, no. 1, 2017, doi: 10.3390/brainsci7010012.
J. S. Kirar and R. K. Agrawal, “A combination of spectral graph theory and quantum genetic algorithm to find relevant set of electrodes for motor imagery classification,” Appl Soft Comput, vol. 97, no. xxxx, p. 105519, 2020, doi: 10.1016/j.asoc.2019.105519.
Z. A. A. Alyasseri, A. T. Khader, M. A. Al-Betar, A. K. Abasi, and S. N. Makhadmeh, “EEG Signals Denoising Using Optimal Wavelet Transform Hybridized with Efficient Metaheuristic Methods,” IEEE Access, vol. 8, pp. 10584–10605, 2020, doi: 10.1109/ACCESS.2019.2962658.
M. Z. Alom et al., “A state-of-the-art survey on deep learning theory and architectures,” Electronics (Switzerland), vol. 8, no. 3, pp. 1–67, 2019, doi: 10.3390/electronics8030292.
I. M. Coelho, V. N. Coelho, E. J. da S. Luz, L. S. Ochi, F. G. Guimarães, and E. Rios, “A GPU deep learning metaheuristic based model for time series forecasting,” Appl Energy, vol. 201, no. Sep 2017, pp. 412–418, 2017, doi: 10.1016/j.apenergy.2017.01.003.
K. Zhang et al., “Data augmentation for motor imagery signal classification based on a hybrid neural network,” Sensors (Switzerland), vol. 20, no. 16, pp. 1–20, 2020, doi: 10.3390/s20164485.
P. Gaur, R. B. Pachori, H. Wang, and G. Prasad, “A multi-class EEG-based BCI classification using multivariate empirical mode decomposition based filtering and Riemannian geometry,” Expert Syst Appl, vol. 95, pp. 201–211, 2018, doi: 10.1016/j.eswa.2017.11.007.
T. Schneider, X. Wang, M. Hersche, L. Cavigelli, and L. Benini, “Q-EEGNet: An energy-efficient 8-bit quantized parallel EEGNet implementation for edge motor-imagery brain-machine interfaces,” in 2020 IEEE International Conference on Smart Computing (SMARTCOMP), Bologna, Italy: IEEE, 2020, pp. 284--289. doi: 10.1109/smartcomp50058.2020.00065.
S. U. Amin, M. Alsulaiman, G. Muhammad, M. A. Mekhtiche, and M. Shamim Hossain, “Deep Learning for EEG motor imagery classification based on multi-layer CNNs feature fusion,” Future Generation Computer Systems, vol. 101, pp. 542–554, 2019, doi: 10.1016/j.future.2019.06.027.
X. Zhang, M. Lei, and Y. Li, “An amplitudes-perturbation data augmentation method in convolutional neural networks for EEG decoding,” in 2018 5th International Conference on Information, Cybernetics, and Computational Social Systems (ICCSS), IEEE, 2018, pp. 231–235.
B. Du, Y. Liu, and G. Tian, “Improving Motor Imagery EEG Classification by CNN with Data Augmentation,” in 2020 IEEE 19th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC), Beijing, China: IEEE, 2020, pp. 111–118. doi: 10.1109/iccicc50026.2020.9450227.
T. Z. et Al., “Subject-specific EEG channel selection using non-negative matrix factorization for lower-limb motor imagery recognition,” J Neural Eng, p. https://doi.org/10.1088/1361-6463/aad7de, 2020.
Published
How to Cite
Issue
Section
Copyright (c) 2024 Ali Al-Saegh, Amar Daood, Mohammad H. Ismail
This work is licensed under a Creative Commons Attribution 4.0 International License.
