Hybrid optimization assisted channel selection of EEG for deep learning model-based classification of motor imagery task
-
K. Venu
and
P. Natesan
Abstract
Objectives
To design and develop an approach named HC + SMA-SSA scheme for classifying motor imagery task
Methods
The offered model employs a new method for classifying motor imagery task. Initially, down sampling is deployed to pre-process the incoming signal. Subsequently, “Modified Stockwell Transform (ST) and common spatial pattern (CSP) based features are extracted”. Then, optimal channel selection is made by a novel hybrid optimization model named as Spider Monkey Assisted SSA (SMA-SSA). Here, “Long Short Term Memory (LSTM) and Bidirectional Gated Recurrent Unit (BI-GRU)” models are used for final classification, whose outcomes are averaged at the end. At last, the improvement of SMA-SSA based model is proven over different metrics.
Results
A superior sensitivity of 0.939 is noted for HC + SMA-SSA that was higher over HC with no optimization and proposed with traditional ST.
Conclusions
The proposed method achieved effective classification performance in terms of performance measures.
Acknowledgments
I would like to express my very great appreciation to the co-authors of this manuscript for their valuable and constructive suggestions during the planning and development of this research work.
-
Research ethics: Not applicable.
-
Informed consent: Not applicable.
-
Author contribution: All authors have made substantial contributions to conception and design, revising the manuscript, and the final approval of the version to be published. Also, all authors agreed to be accountable for all aspects of the work in ensuring that questions related to the accuracy or integrity of any part of the work are appropriately investigated and resolved.
-
Competing interest: The authors declare no conflict of interest.
-
Research funding: This research did not receive any specific funding.
References
1. Padfield, N, Ren, J, Murray, P, Zhao, H. Sparse learning of band power features with genetic channel selection for effective classification of EEG signals. Neurocomputing 2021;463:566–79.10.1016/j.neucom.2021.08.067Search in Google Scholar
2. Meng, X, Qiu, S, Wan, S, Cheng, K, Cui, L. A motor imagery EEG signal classification algorithm based on recurrence plot convolution neural network. Pattern Recogn Lett 2021;146:134–41. https://doi.org/10.1016/j.patrec.2021.03.023.Search in Google Scholar
3. Huang, E, Zheng, X, Fang, Y, Zhang, Z. Classification of motor imagery EEG based on time-domain and frequency-domain dual-stream convolutional neural network. IRBM 2022;43:107–13. https://doi.org/10.1016/j.irbm.2021.04.004.Search in Google Scholar
4. Tang, R, Li, Z, Xie, X. Motor imagery EEG signal classification using upper triangle filter bank auto-encode method. Biomed Signal Process Control 2021;68:1–11. https://doi.org/10.1016/j.bspc.2021.102608.Search in Google Scholar
5. Fu, Y, Wang, F, Li, Y, Gong, A, Qian, Q, Su, L, et al.. Real-time recognition of different imagined actions on the same side of a single limb based on the fNIRS correlation coefficient. Biomed Eng/Biomed Tech 2022;67:173–83. https://doi.org/10.1515/bmt-2021-0422.Search in Google Scholar PubMed
6. NorizadehCherloo, M, Amiri, H, Daliri, MR. Ensemble Regularized Common Spatio-Spectral Pattern (ensemble RCSSP) model for motor imagery-based EEG signal classification. Comput Biol Med 2021;135:1–10.10.1016/j.compbiomed.2021.104546Search in Google Scholar PubMed
7. Mirzaei, S, Ghasemi, P. EEG motor imagery classification using dynamic connectivity patterns and convolutional autoencoder. Biomed Signal Process Control 2021;68:1–8. https://doi.org/10.1016/j.bspc.2021.102584.Search in Google Scholar
8. Rajabioun, M. Motor imagery classification by active source dynamics. Biomed Signal Process Control 2020;61:1–8.10.1016/j.bspc.2020.102028Search in Google Scholar
9. Jin, J, Chen, Z, Xu, R, Miao, Y, yu Wang, X, Jung, TP. Developing a novel Tactile P300 BrainComputer interface with a Cheeks-stim paradigm. IEEE Trans Biomed Eng 2020;67:2585–93. https://doi.org/10.1109/tbme.2020.2965178.Search in Google Scholar
10. Liu, Q, Jiao, Y, Miao, Y, Zuo, C, Wang, X, Cichocki, A, et al.. Efficient representations of EEG signals for SSVEP frequency recognition based on deep multiset CCA. Neurocomputing 2020;378:36–44. https://doi.org/10.1016/j.neucom.2019.10.049.Search in Google Scholar
11. Chen, C, Zhang, J, Belkacem, AN, Zhang, S, Xu, R, Hao, B, et al.. G-causality brain connectivity differences of finger movements between motor execution and motor imagery. J Healthc Eng 2019;2019. https://doi.org/10.1155/2019/5068283.Search in Google Scholar PubMed PubMed Central
12. Yang, Y, Bloch, I, Chevallier, S, Wiart, J. SubjectSpecific Channel Selection using time information for motor imagery brain–computer interfaces. Cogn Comput 2016;8:505–18. https://doi.org/10.1007/s12559-015-9379-z.Search in Google Scholar
13. Jin, J, Miao, Y, Daly, I, Zuo, C, Hu, D, Cichocki, A. Correlation-based channel selection and regularized feature optimization for MI-based BCI. Neural Network 2019;118:262–70. https://doi.org/10.1016/j.neunet.2019.07.008.Search in Google Scholar PubMed
14. Alazrai, R, Alqasem, F, Alaarag, S, Ahmad Yousef, KM, Daoud, MI. A bispectrum-based approach for detecting deception using EEG signals. in 2018 IEEE 20th International Conference on e-Health Networking, Applications and Services (Healthcom), Ostrava; 2018:1–6 pp.10.1109/HealthCom.2018.8531183Search in Google Scholar
15. Sun, L, Feng, Z, Lu, N, Wang, B, Zhang, W. An advanced bispectrum features for EEG-based motor imagery classification. Expert Syst Appl 2019;131:9–19. https://doi.org/10.1016/j.eswa.2019.04.021.Search in Google Scholar
16. Frolov, AA, Mokienko, O, Lyukmanov, R, Biryukova, E, Kotov, S, Turbina, L, et al.. Post-stroke rehabilitation training with a motor-imagery-based brain-computer interface (BCI)-controlled hand exoskeleton: a randomized controlled multicenter trial. Front Neurosci 2017;11:400. https://doi.org/10.3389/fnins.2017.00400.Search in Google Scholar PubMed PubMed Central
17. Belkacem, AN, Nishio, S, Suzuki, T, Ishiguro, H, Hirata, M. Neuromagnetic decoding of simultaneous bilateral hand movements for multidimensional brain‐ machine interfaces. IEEE Trans Neural Syst Rehabil Eng 2018;26:1301–10. https://doi.org/10.1109/tnsre.2018.2837003.Search in Google Scholar
18. Qiu, Z, Jin, J, Lam, HK, Zhang, Y, Wang, X, Cichocki, A. Improved SFFS method for channel selection in motor imagery based BCI. Neurocomputing 2016;207:519–27. https://doi.org/10.1016/j.neucom.2016.05.035.Search in Google Scholar
19. Jin, J, Liu, C, Daly, I, Miao, Y, Li, S, Wang, X, et al.. Bispectrum-based Channel Selection for motor imagery based brain-computer interfacing. IEEE Trans Neural Syst Rehabil Eng 2020;28:2153–63. https://doi.org/10.1109/tnsre.2020.3020975.Search in Google Scholar
20. Thomas, KP, Robinson, N, Vinod, AP. Utilizing subject-specific discriminative EEG features for classification of motor imagery directions. In 2019 IEEE 10th International Conference on Awareness Science and Technology (iCAST); 2019:1–5 pp.10.1109/ICAwST.2019.8923216Search in Google Scholar
21. Varsehi, H, Firoozabadi, SMP. An EEG channel selection method for motor imagery based brain–computer interface and neurofeedback using Granger causality. Neural Network 2021;133:193–206. https://doi.org/10.1016/j.neunet.2020.11.002.Search in Google Scholar PubMed
22. Dong, E, Zhou, K, Tong, J, Du, S. A novel hybrid kernel function relevance vector machine for multi-task motor imagery EEG classification. Biomed Signal Process Control 2020:60.10.1016/j.bspc.2020.101991Search in Google Scholar
23. Miah, MO, RafsanJani, M, Mamun, KAA, Farid, DM, Sharma, A, Dehzangi, A. Prediction of motor imagery tasks from MultiChannel EEG data for brain–computer Interface applications. Research Gate; 2020.10.1101/2020.04.08.032201Search in Google Scholar
24. Batres-Mendoza, P, Ibarra-Manzano, MA, Guerra-Hernandez, EI, Almanza-Ojeda, DL, Montoro-Sanjose, CR, Romero-Troncoso, RJ, et al.. Improving EEG-based motor imagery classification for real-time applications using the QSA method. Comput Intell Neurosci 2017;1903–6. https://doi.org/10.1155/2017/9817305.Search in Google Scholar PubMed PubMed Central
25. Sadiq, MT, Yu, X, Yuan, Z, Aziz, MZ. Identification of motor and mental imagery EEG in two and multiclass subject-dependent tasks using successive decomposition index. Sensors 2020;20:1–24. https://doi.org/10.3390/s20185283.Search in Google Scholar PubMed PubMed Central
26. Shi, B, Wang, Q, Yin, S, Yue, Z, Hua, Y, Wang, J. A binary harmony search algorithm as channel selection method for motor imagery-based BCI. Neurocomputing 2021;443:12–25. https://doi.org/10.1016/j.neucom.2021.02.051.Search in Google Scholar
27. Tlouyamma, J, Velempini, M. Channel selection algorithm optimized for improved performance in cognitive radio networks. Wireless Pers Commun 2021;119:3161–78. https://doi.org/10.1007/s11277-021-08392-5.Search in Google Scholar
28. Mandal, SK, Naskar, MNB. Meta heuristic assisted automated channel selection model for motor imagery brain computer interface. Multimed Tool Appl 2022;81:17111–30. https://doi.org/10.1007/s11042-022-12327-y.Search in Google Scholar
29. http://bnci-horizon-2020.eu/database/data-sets.Search in Google Scholar
30. Miao, M, Wang, A, Liu, F. Application of artificial bee colony algorithm in feature optimization for motor imagery EEG classification. Neural Comput Appl 2017;30:3677–91. https://doi.org/10.1007/s00521-017-2950-7.Search in Google Scholar
31. Assous, S, Boashash, B. Evaluation of the modified S-transform for time frequency synchrony analysis and source localisation. Assous and Boashash EURASIP J Adv Signal Process 2012;49:1–18.10.1186/1687-6180-2012-49Search in Google Scholar
32. Sharma, H, Hazrati, G, Bansal, JC. Spider monkey optimization algorithm. Evolutionary and swarm intelligence algorithms. Stud Comput Intell 2019;779:43–59.10.1007/978-3-319-91341-4_4Search in Google Scholar
33. Xue, J, Shen, B. A novel swarm intelligence optimization approach. Sparrow Search Algorithm 2020:22–34. https://doi.org/10.1080/21642583.2019.1708830.Search in Google Scholar
34. Beno, MM, Valarmathi, IR, Swamy, SM, Rajakumar, BR. Threshold prediction for segmenting tumour from brain MRI scans. Int J Imag Syst Technol 2014;24:129–37. https://doi.org/10.1002/ima.22087.Search in Google Scholar
35. Thomas, R, Rangachar, MJS. Hybrid optimization based DBN for face recognition using low-resolution images. Multimed Res 2018;1:33–43.10.46253/j.mr.v1i1.a5Search in Google Scholar
36. Devagnanam, J, Elango, NM. Optimal resource allocation of cluster using hybrid grey wolf and Cuckoo search algorithm in Cloud computing. J Network Commun Syst 2020;3:31–40.10.46253/jnacs.v3i1.a4Search in Google Scholar
37. Shareef, SKM, Rao, RS. A hybrid learning algorithm for optimal reactive power dispatch under unbalanced Conditions. J Comput Mech, Power Syst Control 2018;1:26–33.10.46253/jcmps.v1i1.a4Search in Google Scholar
38. Tăuțan, AM, Rossi, AC, Ionescu, B. Automatic sleep scoring with LSTM networks: impact of time granularity and input signals. Biomed Eng/Biomed Tech 2022;67:267–81. https://doi.org/10.1515/bmt-2021-0408.Search in Google Scholar PubMed
39. Zhou, X, Lin, J, Zhang, Z, Shao, Z, Liu, H. Improved itracker combined with bidirectional long short-term memory for 3D gaze estimation using appearance cues. Neurocomputing 2019;390:217–25. https://doi.org/10.1016/j.neucom.2019.04.099.Search in Google Scholar
40. Tong, L, Ma, H, Lin, Q, He, J, Peng, L. A novel deep learning Bi-GRU-I model for real-time human activity recognition using inertial sensors. IEEE Sensor J 2022;22:6164–74. https://doi.org/10.1109/jsen.2022.3148431.Search in Google Scholar
© 2023 Walter de Gruyter GmbH, Berlin/Boston
Articles in the same Issue
- Frontmatter
- Review
- Epileptic EEG patterns recognition through machine learning techniques and relevant time–frequency features
- Research Articles
- Hybrid optimization assisted channel selection of EEG for deep learning model-based classification of motor imagery task
- Development of audio-guided deep breathing and auditory Go/No-Go task on evaluating its impact on the wellness of young adults: a pilot study
- Detection of driver drowsiness level using a hybrid learning model based on ECG signals
- A portable household detection system based on the combination of bidirectional LSTM and residual block for automatical arrhythmia detection
- Probabilistic hierarchical clustering based identification and segmentation of brain tumors in magnetic resonance imaging
- Biomechanical comparison of three fixation strategies for radial head fractures: a biomechanical study
- Computer-based analysis of the taper connection strength of different revision head and adapter sleeve designs
- CT-based evaluation of tissue expansion in cryoablation of ex vivo kidney
Articles in the same Issue
- Frontmatter
- Review
- Epileptic EEG patterns recognition through machine learning techniques and relevant time–frequency features
- Research Articles
- Hybrid optimization assisted channel selection of EEG for deep learning model-based classification of motor imagery task
- Development of audio-guided deep breathing and auditory Go/No-Go task on evaluating its impact on the wellness of young adults: a pilot study
- Detection of driver drowsiness level using a hybrid learning model based on ECG signals
- A portable household detection system based on the combination of bidirectional LSTM and residual block for automatical arrhythmia detection
- Probabilistic hierarchical clustering based identification and segmentation of brain tumors in magnetic resonance imaging
- Biomechanical comparison of three fixation strategies for radial head fractures: a biomechanical study
- Computer-based analysis of the taper connection strength of different revision head and adapter sleeve designs
- CT-based evaluation of tissue expansion in cryoablation of ex vivo kidney
