News and Announcements
ARTICLE
Deeplearning based classification of motor imagery EEGsignals us-ing an improved path finder optimizationalgorithm
Vishwesh Jayashekar1 ,
Raviraj Pandian2 ,
Rajashekar Mallajamma Basavarajegowda3
Show Less
1
Assosiate Professor, Department of Computer Science & Engineering,GSSS Institute of Engineering and Technology for Women, Mysuru, Affiliated to VTU, Belagavi, Karnataka,
India
2
Professor, Department of Computer Science & Engineering, GSSS Institute of Engineering and Technology for Women, Mysuru, Affiliated to VTU, Belagavi, Karnataka,
India
3
Assosiate Professor, Department of Computer Science & Engineering, GSSS Institute of Engineering and Technology for Women, Mysuru, Affiliated to VTU, Belagavi, Karnataka,
India
IJOSI 2024 , 8(3), 115–124;
https://doi.org/10.6977/IJoSI.202409_8(3).009
Submitted: 17 April 2024 | Revised: 17 July 2024 | Accepted: 29 July 2024 | Published: 30 December 2024
© 2024 by the Author(s). Licensee AccScience Publishing, USA. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution -Noncommercial 4.0 International License (CC BY-NC 4.0) ( https://creativecommons.org/licenses/by-nc/4.0/ )
Abstract
Motor Imagery Brain-Computer Interfaces (MI-BCIs) are systems based on AI that collect patterns of brain activities in mental movement and translate these movements through external devices. The identification of motor intention by evaluating Electroencephalogram (EEG) signals is an important issue in applications related to Brain-Computer In-terfaces (BCI). In this paper, an Improved Path Finder Optimization Algorithm (IPFOA) is proposed to improve the process of selecting features. The data is collected from the BCI competition IV 2a dataset and the stage of pre-processing takes place through sliding windows and 6th order Butterworth filter. The feature will be extracted from the pre-processed data using the hybrid Convolutional Neural Network (CNN) and Common Spatial Pattern (CSP) method. After this stage, the required features are selected from the extracted features using the proposed IPFOA algorithm. Finally, the classification of EEG signals takes place using a Stacked autoencoder, a classifier based ona Deep Neural Network.The experimental results show that the proposed approach achieved a better accuracy of 98.40% which is comparatively higher than the existing approaches.
Keywords
Brain Computer Interface
Convolutional Neural Networks
Deep Learning
Electroencephalogram
Motor Imagery
Path Finder Optimization
References
- Ang KK, Chin ZY, Wang C, Guan C, Zhang H. (2012). Filter bank common spatial pattern algorithm on BCI competition IV datasets 2a and 2b. Frontiers in Neuroscience. 2012; 6:39. https://doi.org/10.3389/fnins.2012.00039.
- Cherloo MN, Amiri HK, Daliri MR. (2021). Ensemble Regularized Common Spatio-Spectral Pattern (en-semble RCSSP) model for motor imagery-based EEG signal classification. Computers in Biology and Medicine. 2021; 135:104546. DOI:10.1016/j.compbiomed.2021.104546.
- Darvish ghanbar K, Rezaii TY, Farzamnia, A, Saad I. (2021). Correlation-based common spatial pattern (CCSP): A novel extension of CSP for classifica-tion of motor imagery signal. Plos one. 2021; 16(3):e0248511. https://doi.org/10.1371/jour-nal.pone.0248511.
- Dagdevir E, Tokmakci M. (2023) Determination of ef-fective signal processing stages for brain computer interfaceon BCI competition IV data set 2b: a re-view study. IETE Journal of Research. 2023; 69(6):3144-55. DOI:10.17485/IJST/v16i6.2076.
- Gaur P, Gupta H, Chowdhury A, McCreadie K, Pach-ori RB, Wang H. (2021). A sliding window com-mon spatial pattern for enhancing motor imagery classification in EEG-BCI. IEEE Transactions on Instrumentation and Measurement. 2021; 70:4002709. DOI:10.1109/TIM.2021.3051996.
- Halder S, Dora BK, Bhat S. (2022). An Enhanced Pathfinder Algorithm based MCSA for rotor break-age detection of induction motor. Journal of Com-putational Science. 2022; 64:101870. DOI:10.1016/j.jocs.2022.101870.
- Hermosilla DM, Codorniú RT, Baracaldo RL, Zamora RS, Rodriguez DD, Albuerne YL, Álvarez JRN. (2021). Shallow convolutional network excel for classifying motor imagery EEG in BCI applica-tions. IEEE Access. 2021; 9:98275-86. DOI:10.1109/ACCESS.2021.3091399.
- Idowu OP, Adelopo O, Ilesanmi AE, Li X, Samuel OW, Fang P, Li G. (2021). Neuro-evolutionary ap-proach for optimal selection of EEG channels in motor imagery based BCI application. Biomedical Signal Processing and Control. 2021; 68:102621. https://doi.org/10.1016/j.bspc.2021.102621.
- Jin J, Xiao R, Daly I, Miao Y, Wang X, Cichocki A. (2020). Internal feature selection method of CSP based on L1-norm and Dempster–Shafer theory. IEEE transactions on neural networks and learning systems. 2021; 32(11):4814-25. DOI:10.1109/TNNLS.2020.3015505.
- Keerthi KK, Soman KP. (2021). CNN based classifica-tion of motor imaginary using variational mode de-composed EEG-spectrum image. Biomedical Engi-neering Letters. 2021; 11(3):235-47. DOI:10.1007/s13534-021-00190-z.
- Liang Y, Ma Y. (2020). Calibrating EEG features in motor imagery classification tasks with a small amount of current data using multisource fusion transfer learning. Biomedical Signal Processing and Control. 2020; 62:102101.
- Li Q, Liu Y, Shang Y, Zhang Q, Yan F.(2022).Deep sparse autoencoder and recursive neural network for EEG emotion recognition. Entropy. 2022; 24(9):1187. https://doi.org/10.3390/e24091187.
- Meng X, Qiu S, Wan S, Cheng K, Cui, L. (2021). A motor imagery EEG signal classification algorithm based on recurrence plot convolution neural net-work. Pattern Recognition Letters. 2021; 146:134-41. DOI: 10.1016/j.patrec.2021.03.023.
- Mahapatra AK, Panda N, Pattanayak BK. (2022). An Improved Pathfinder Algorithm (ASDR-PFA) based on Adaptation of Search Dimensional Ratio for solvingconstrained optimization problems and optimal Feature Selection. 2022. DOI:10.21203/rs.3.rs-2115041/v1.
- Musallam YK, AlFassam NI, Ghulam M, Amin SU, Alsulaiman M, Abdul W, Altaheri H, Bencherif MA, Algabri M. (2021). Electroencephalography-based motor imagery classification using temporal convolutional network fusion. Biomedical Signal Processing and Control. 2021; 69:102826. https://doi.org/10.3390/bioengineering9070323.
- Malan NS, Sharma S. (2021). Time window and fre-quency band optimization using regularized neigh-bourhood component analysis for Multi-View Mo-tor Imagery EEG classification. Biomedical Signal Processing and Control. 2021; 67:102550. DOI:10.1016/j.bspc.2021.102550.
- Mirzaei S, Ghasemi P. (2021). EEG motor imagery classification using dynamic connectivity patterns and convolutional autoencoder. Biomedical Signal Processing and Control. 2021; 68:102584. https://doi.org/10.1016/j.bspc.2021.102584.
- Phadikar S, Sinha N, Ghosh R. (2023). Unsupervised feature extraction with autoencoders for EEG based multiclass motor imagery BCI. Expert Sys-tems with Applications. 2023; 213A:118901.https://doi.org/10.1016/j.eswa.2022.118901.
- Rusnac AL, Grigore O. (2022). CNN architectures and feature extraction methods for EEG imaginary speech recognition. Sensors. 2022; 22(13):4679. https://doi.org/10.3390/s22134679.
- Rusnac AL, Grigore O. (2022). Imaginary Speech Recognition Using a Convolutional Network with Long-Short Memory. Applied Sciences. 2022; 12(22):11873. https://doi.org/10.3390/app122211873.
- Saideepthi P, Chowdhury A, Gaur P, Pachori RB. (2023). Sliding Window along with EEGNet based Prediction of EEG Motor Imagery. IEEE Sensors Journal. 2023; 23(15):17703-17713. https://dx.doi.org/10.1109/JSEN.2023.3270281.
- Sun J, Wei M, Luo N, Li Z, Wang H. (2022). Euler common spatial patterns for EEG classification. Medical & Biological Engineering & Computing. 2022; 60(3):753-67. DOI:10.1007/s11517-021-02488-7.
- Song Y, Jia X, Yang L, Xie L. (2021). Transformer-based spatial-temporal feature learning for EEG decoding. arXiv preprint arXiv:2106.11170. 2021.
- Tibrewal N, Leeuwis N, Alimardani M. (2022). Classi-fication of motor imagery EEG using deep learning increases performance in inefficient BCI users. Plos one. 2022; 17(7):e0268880. https://doi.org/10.1371/journal.pone.0268880.
- Tang R, Li Z, Xie X. (2021). Motor imagery EEG sig-nal classification using upper triangle filter bank auto-encode method. Biomedical Signal Processing and Control. 2021; 68:102608. DOI:10.1016/j.bspc.2021.102608.
- Vafaei E, Rahatabad FN, Setarehdan SK, Azadfallah P.(2023).Extracting a Novel Emotional EEG Topo-graphic Map Based on a Stacked Autoencoder Net-work. Journal of Healthcare Engineering. 2023; 2023:9223599. https://doi.org/10.1155/2023/9223599.
- Vishwesh J, Raviraj P.(2023).Improved Differential Evolution with Stacked Auto Encoder for EEG Motor Imagery Classification. Indian Journal of Science and Technology. 2023; 16(6):391-400. DOI:10.17485/IJST/v16i6.2076.
- Wang Y, Qiu S, Li D, Du,C., Lu,B.L., He,H. (2022). Multi-modal domain adaptation variational autoen-coder for eeg-based emotion recognition. IEEE/CAA Journal of AutomaticaSinica. 2022; 9(9):1612-26. DOI:10.1109/JAS.2022.105515.
- Xiao X, Fang Y. (2021). Motor imagery EEG signal recognition using deep convolution neural net-work. Frontiers in Neuroscience. 2021; 15:655599. https://doi.org/10.3389/fnins.2021.655599.
- Yang L, Song Y, Ma K, Xie L. (2021). Motor imagery EEG decoding method based on a discriminative feature learning strategy. IEEE Transactions on Neural Systems and Rehabilitation Engineering. 2021; 29:368-79. DOI: 10.1109/TNSRE.2021.3051958.
- Yu,X., Aziz,MZ, Sadiq, MT, Fan Z, Xiao G. (2021). A new framework for automatic detection of motor and mental imagery EEG signals for robust BCI systems. IEEE Transactions on Instrumentation and Measurement. 2021; 70:1006612. DOI: 10.1109/TIM.2021.3069026.
- Zeng H, Xia N, Tao M, Pan D, Zheng H, Wang C, Xu F, Zakaria W, Dai G. (2023). DCAE: A dual conditional autoencoder framework for the recon-struction from EEG into image. Biomedical Signal Processing and Control. 2023; 81:104440. https://doi.org/10.1016/j.bspc.2022.104440.
