Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Advances in Computer, Signals and Systems
  4. Vol 8, Issue 5, 2024

WPD Combined with One-on-one CSP for Motor Imagery EEG Signal Classification

Download as PDF

DOI: 10.23977/acss.2024.080519 | Downloads: 25 | Views: 877

Author(s)

Hongzhen Ruan 1

Affiliation(s)

1 Department of Biomedical Engineering, Shantou University, Shantou, Guangdong, China

Corresponding Author

Hongzhen Ruan

ABSTRACT

Regarding the EEG (electroencephalogram) signals of motor imagery, existing signal decomposition methods similar to EMD (Empirical Mode Decomposition) are often affected by mode aliasing and mode oscillation, and classifiers are prone to overfitting in high-dimensional data. This article combined WPD (Wavelet Packet Decomposition) and one-to-one CSP (Common Spatial Pattern) to study the classification of motor imagery EEG signals, aiming to provide better time-frequency resolution and improve classification performance. Using the publicly available dataset BCI (Brain-computer Interface) Competition IV 2a as the object: firstly, WPD was used to perform multi-level decomposition on four types of motor imagery EEG signals from nine subjects; next, the covariance matrix of each category of EEG signals in CSP was calculated to extract feature vectors, and the features that best distinguish different categories were selected to reduce dimensionality and avoid overfitting; finally, in the 10-fold cross-validation process, the number of features was optimized to improve the performance of the Random Forest (RF) classifier. The results showed that the method proposed in this article had a mean Maximum Mutual Information (MMI) of 0.67 bits and a maximum classification accuracy of 87.5% for the BCI Competition IV 2a dataset, which was approximately 2.1% higher than the Attention-based Temporal Convolutional Network (ATCNet) model.

KEYWORDS

EEG Signal Classification, Brain-computer Interface, Motor Imagery, Wavelet Packet Decomposition, Common Spatial Pattern

CITE THIS PAPER

Hongzhen Ruan, WPD Combined with One-on-one CSP for Motor Imagery EEG Signal Classification. Advances in Computer, Signals and Systems (2024) Vol. 8: 165-173. DOI: http://dx.doi.org/10.23977/acss.2024.080519.

REFERENCES

[1] Altaheri, Hamdi, Muhammad, Ghulam, Alsulaiman, Mansour, Amin, Syed Umar, Altuwaijri, Ghadir Ali, Abdul, Wadood, et al. (2023). Deep learning techniques for classification of electroencephalogram (EEG) motor imagery (MI) signals: A review. Neural Computing and Applications, 35 (20), 14681-14722. 
[2] Duan, Lijuan, Lian, Zhaoyang, Qiao, Yuanhua, Chen, Juncheng, Miao, Jun, & Li, Mingai. (2024). A Novel Feature Fusion Approach for Classification of Motor Imagery EEG Based on Hierarchical Extreme Learning Machine. Cognitive Computation, 16 (2), 566-580. 
[3] Tiwari, Virendra Kumar, & Singh, Priyanka. (2023). Classification of Motor Imaginary in EEG using feature Optimization and Machine Learning. International Journal of Advanced Networking and Applications (IJANA), India, 15 (02), 5887-5891. 
[4] Samal, Priyadarsini, & Hashmi, Mohammad Farukh. (2023). Ensemble median empirical mode decomposition for emotion recognition using EEG signal. IEEE Sensors Letters, 7 (5), 1-4. 
[5] Zulfikar, Aslan, & Mehmet, Akin. (2022). Empirical mode decomposition and convolutional neural network-based approach for diagnosing psychotic disorders from eeg signals. Applied Intelligence, 52 (11), 12103-12115. 
[6] Dash, Shaswati, Tripathy, Rajesh Kumar, Panda, Ganapati, & Pachori, Ram Bilas. (2022). Automated recognition of imagined commands from EEG signals using multivariate fast and adaptive empirical mode decomposition based method. IEEE Sensors Letters, 6 (2), 1-4. 
[7] Asghar, Muhammad Adeel, Khan, Muhammad Jamil, Rizwan, Muhammad, Shorfuzzaman, Mohammad, & Mehmood, Raja Majid. (2022). AI inspired EEG-based spatial feature selection method using multivariate empirical mode decomposition for emotion classification. Multimedia Systems, 28 (4), 1275-1288. 
[8] Meng, Ming, Dong, Zhichao, Gao, Yunyuan, & She, Qingshan. (2023). Optimal channel and frequency band‐based feature selection for motor imagery electroencephalogram classification. International Journal of Imaging Systems and Technology, 33 (2), 670-679. 
[9] Miao, Minmin, Hu, Wenjun, & Zhang, Wenbin. (2021). A spatial-frequency-temporal 3D convolutional neural network for motor imagery EEG signal classification. Signal, Image and Video Processing, 15 (8), 1797-1804. 
[10] Thuwajit, Punnawish, Rangpong, Phurin, Sawangjai, Phattarapong, Autthasan, Phairot, Chaisaen, Rattanaphon, Banluesombatkul, Nannapas, et al. (2021). EEGWaveNet: Multiscale CNN-based spatiotemporal feature extraction for EEG seizure detection. IEEE Transactions on Industrial Informatics, 18 (8), 5547-5557. 
[11] Fang, Hua, Jin, Jing, Daly, Ian, & Wang, Xingyu. (2022). Feature extraction method based on filter banks and Riemannian tangent space in motor-imagery BCI. IEEE journal of biomedical and health informatics, 26 (6), 2504-2514. 
[12] Sairamya, Nanjappan Jothiraj, Premkumar, M Joel, George, S Thomas, & Subathra, MSP. (2021). Performance evaluation of discrete wavelet transform, and wavelet packet decomposition for automated focal and generalized epileptic seizure detection. IETE journal of Research, 67 (6), 778-798. 
[13] Dash, Deba Prasad, Kolekar, Maheshkumar H, & Jha, Kamlesh. (2022). Surface EEG based epileptic seizure detection using wavelet based features and dynamic mode decomposition power along with KNN classifier. Multimedia Tools and Applications, 81 (29), 42057-42077.  
[14] Amiri, Youkabed, & Omranpour, Hesam. (2024). Efficient space learning based on kernel trick and dimension reduction technique for multichannel motor imagery EEG signals classification. Neural Computing and Applications, 36 (3), 1199-1214. 
[15] Yin, Xu, Meng, Ming, She, Qingshan, Gao, Yunyuan, & Luo, Zhizeng. (2021). Optimal channel-based sparse time-frequency blocks common spatial pattern feature extraction method for motor imagery classification. Mathematical Biosciences and Engineering, 18 (4), 4247-4263. 
[16] Altaheri Hamdi, Muhammad Ghulam, Alsulaiman Mansour. Physics-informed attention temporal convolutional network for EEG-based motor imagery classification. IEEE transactions on industrial informatics, 2022, 19 (2): 2249-2258.
[17] Li Hongli, Liu Haoyu, Chen Hongyu, Zhang Ronghua. Multi-scale feature extraction and classification of motor imagery electroencephalography based on time series data enhancement. Journal of biomedical engineering, 2023, 40 (3): 418-425.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 38553
Visits: 697920

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.