Enhancing Motor Imagery EEG Classification Using a Modified Bidirectional LSTM Network

Authors

  • Iman Hussein AL-Qinani Informatics Institute for Postgraduate Studies, University of Information Technology and Communications, Baghdad, Iraq Department of Computer Science, College of Education, Mustansiriyah University, Baghdad, Iraq Author
  • Yarub Alazzawi Mechatronics Engineering Department, Al-Khwarizmi College of Engineering, University of Baghdad, Baghdad, Iraq Author

DOI:

https://doi.org/10.32628/IJSRSET261306

Keywords:

BiLSTM, BCI, EEG, multiclass, MI

Abstract

Motor imagery (MI) Electroencephalography (EEG) classification is a key step for supporting brain computer interface (BCI) applications, yet high accuracy remains challenging due to inter subject variability and signal noise. This paper uses the BNCI Horizon 2020 dataset under an all subjects together training setting to build general model that learns from all participants. Signal representation is improved through preprocessing scenarios including Normalization and principal component analysis (PCA), followed by two Bidirectional Long-Short-Term Memory (BiLSTM) architectures, a baseline design and a modified design with higher capacity and added batch normalization and dropout to stabilize training and reduce overfitting. Results show that the modified BiLSTM achieves strong multiclass performance, reaching 92.35% training accuracy and 92.23% testing accuracy for the 8-class task, and approximately 99.98% accuracy for both training and testing in the 7-class task. These findings highlight that combining appropriate preprocessing with an improved BiLSTM design can increase the reliability of motor imagery EEG classification for practical BCI use.

Downloads

Download data is not yet available.

References

X. Tang, C. Yang, X. Sun, M. Zou, and H. Wang, “Motor Imagery EEG Decoding Based on Multi-Scale Hybrid Networks and Feature Enhancement,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 31, pp. 1208–1218, 2023, doi: 10.1109/TNSRE.2023.3242280.

E. Quiles, J. Dadone, N. Chio, and E. García, “Cross-Platform Implementation of an SSVEP-Based BCI for the Control of a 6-DOF Robotic Arm,” Sensors, vol. 22, no. 13, 2022, doi: 10.3390/s22135000.

O. Z. Amanuel and Y. Alazzawi, “BCI-Based Smart Room Control using EEG Signals,” Al-Khwarizmi Eng. J., vol. 18, no. 4, pp. 60–72, 2022, doi: 10.22153/kej.2022.09.004.

M. Rashid et al., “Current Status, Challenges, and Possible Solutions of EEG-Based Brain-Computer Interface: A Comprehensive Review,” Front.

Neurorobot., vol. 14, no. June, pp. 1–35, 2020, doi: 10.3389/fnbot.2020.00025.

V. Jayashekar and R. Pandian, “Hybrid Feature Extraction for EEG Motor Imagery Classification Using Multi-Class SVM,” Int. J. Intell. Eng. Syst., vol. 15, no. 4, pp. 20–30, 2022, doi: 10.22266/ijies2022.0831.03.

J. Y. Ng, “Exploring the intersection of brain-computer interfaces and traditional, complementary, and integrative medicine,” Integr. Med. Res., vol. 14, no. 2, p. 101142, 2025, doi: 10.1016/j.imr.2025.101142.

O. Amanuel and Y. Alazzawi, “Design and Implementation of EEG-Based Smart Structure,” Int. J. Intell. Eng. Syst., vol. 16, no. 1, pp. 314–327, 2023, doi: 10.22266/ijies2023.0228.28.

T. Rudroff, “Decoding thoughts, encoding ethics: A narrative review of the BCI-AI revolution,” Brain Res., vol. 1850, no. September 2024, p. 149423, 2025, doi: 10.1016/j.brainres.2024.149423.

M. F. Mridha, S. C. Das, M. M. Kabir, A. A. Lima, M. R. Islam, and Y. Watanobe, “Brain-computer interface: advancement and challenges,” Sensors, vol. 21, no. 17, pp. 1–46, 2021, doi: 10.3390/s21175746.

D. Yadav, S. Yadav, and K. Veer, “A comprehensive assessment of Brain Computer Interfaces: Recent trends and challenges,” J. Neurosci. Methods, vol. 346, no. April, p. 108918, 2020, doi: 10.1016/j.jneumeth.2020.108918.

BNCI Horizon 2020, “Data sets /25. Upper limb movement decoding from EEG (001-2017),” European Commission. Accessed: Nov. 29, 2023. [Online]. Available: http://bnci-horizon-2020.eu/database/data-sets

P. Ofner, A. Schwarz, J. Pereira, and G. R. Müller-Putz, “Upper limb movements can be decoded from the time-domain of low-frequency EEG,” PLoS One, vol. 12, no. 8, pp. 1–24, 2017, doi: 10.1371/journal.pone.0182578.

H. Yadav and S. Maini, Electroencephalogram based brain-computer interface: Applications, challenges, and opportunities, vol. 82, no. 30. Springer US, 2023. doi: 10.1007/s11042-023-15653-x.

G. Zhan et al., “EEG-Based Brain Network Analysis of Chronic Stroke Patients After BCI Rehabilitation Training,” Front. Hum. Neurosci., vol. 16, no. June, 2022, doi: 10.3389/fnhum.2022.909610.

J. Bi and M. Chu, “TDLNet: Transfer Data Learning Network for Cross-Subject Classification Based on Multiclass Upper Limb Motor Imagery EEG,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 31, pp. 3958–3967, 2023, doi: 10.1109/TNSRE.2023.3323509.

J. H. Jeong, B. H. Lee, D. H. Lee, Y. D. Yun, and S. W. Lee, “EEG Classification of Forearm Movement Imagery Using a Hierarchical Flow Convolutional Neural Network,” IEEE Access, vol. 8, no. Mi, pp. 66941–66950, 2020, doi: 10.1109/ACCESS.2020.2983182.

Pal, P. K., Kataria, B., & Jangid, J. (2025). AI-Driven Multimodal Ensemble Framework for Accurate Hardware Failure Detection in Optical Embedded Systems: Eliminating Unnecessary RMAs. Preprints. https://doi.org/10.20944/preprints202512.1937.v1

FNU Pawan Kumar (2025), Scalable Microservices Architecture for High-Volume Order Processing in Cloud Environments. International Journal of Innovative Science and Research Technology (IJISRT) IJISRT25JUN1313, 2542-2548. DOI: 10.38124/ijisrt/25jun1313.

Mishra, Chandan. (2025). Modernizing PeopleSoft Financial Systems: Automation, Cloud Integration, and Workflow Optimization. International Research Journal on Advanced Science Hub. 7. 882-890. 10.47392/IRJASH.2025.097.

I. H. AL-Qinani and Y. Alazzawi, “Improvement of Motor Imagery Classification in Brain-Computer Interface Based on EEG Signals Analysis,” Int. J. Intell. Eng. Syst., vol. 18, no. 4, pp. 403–423, 2025, doi: 10.22266/ijies2025.0531.26.

A. Al Hamoud, A. Hoenig, and K. Roy, “Sentence subjectivity analysis of a political and ideological debate dataset using LSTM and BiLSTM with attention and GRU models,” J. King Saud Univ. - Comput. Inf. Sci., vol. 34, no. 10, pp. 7974–7987, 2022, doi: 10.1016/j.jksuci.2022.07.014.

N. Hassan, A. S. M. Miah, and J. Shin, “A Deep Bidirectional LSTM Model Enhanced by Transfer-Learning-Based Feature Extraction for Dynamic Human Activity Recognition,” Appl. Sci., vol. 14, no. 2, 2024, doi: 10.3390/app14020603.

D. Liu and X. Cheng, “FNN-BiLSTM-Attention-DA: A hybrid fuzzy neural network and BiLSTM with multi-sensor information fusion for water quality monitoring and warning,” Alexandria Eng. J., vol. 124, no. March, pp. 624–639, 2025, doi: 10.1016/j.aej.2025.04.011.

Y. Wang, T. Sasamura, A. Mustafa, and T. Morita, “Real-time torque prediction for ultrasonic motors using an attention-based BiLSTM model and improved differential evolution algorithm,” Meas. J. Int. Meas. Confed., vol. 251, no. March, 2025, doi: 10.1016/j.measurement.2025.117266.

H. S. Sharma and K. J. Singh, “A Conv-BiLSTM Sandwich Network for DDoS Attack Detection,” Procedia Comput. Sci., vol. 258, pp. 3324–3332, 2025, doi: 10.1016/j.procs.2025.04.590.

Y. Wu and Y. Xing, “Efficient Machine Translation with a BiLSTM-Attention Approach,” 2024, [Online]. Available: http://arxiv.org/abs/2410.22335

V. S. Rathod, A. Tiwari, and O. G. Kakde, “Wading corvus optimization based text generation using deep CNN and BiLSTM classifiers,” Biomed. Signal Process. Control, vol. 78, no. September, pp. 1–9, 2022, doi: 10.1016/j.bspc.2022.103969.

X. Wang, V. Liesaputra, Z. Liu, Y. Wang, and Z. Huang, “An in-depth survey on Deep Learning-based Motor Imagery Electroencephalogram (EEG) classification,” Artif. Intell. Med., vol. 147, no. October 2023, p. 102738, 2024, doi: 10.1016/j.artmed.2023.102738.

M. Pagan, M. Zarlis, and A. Candra, “Investigating the impact of data scaling on the k-nearest neighbor algorithm,” Comput. Sci. Inf. Technol., vol. 4, no. 2, pp. 135–142, 2023, doi: 10.11591/csit.v4i2.pp135-142.

G. Biagetti, P. Crippa, L. Falaschetti, S. Luzzi, and C. Turchetti, “Classification of Alzheimer’s disease from EEG signal using robust-PCA feature extraction,” Procedia Comput. Sci., vol. 192, no. 2019, pp. 3114–3122, 2021, doi: 10.1016/j.procs.2021.09.084.

H. Xu, W. Haider, M. Z. Aziz, Y. Sun, and X. Yu, “Transforming Motor Imagery Analysis: A Novel EEG Classification Framework Using AtSiftNet Method,” Sensors, vol. 24, no. 19, pp. 1–32, 2024, doi: 10.3390/s24196466.

M. B. G. Gowda, N. K. Boraiah, V. Eshappa, and G. K. Chandrashekara, “Classification of Epileptic EEG Signals Using Improved Atomic Search Optimization Algorithm,” Int. J. Intell. Eng. Syst., vol. 16, no. 6, pp. 134–144, 2023, doi: 10.22266/ijies2023.1231.12.

S. K. Jarallah and S. A. Mahmood, “Query-Based Video Summarization System Based on Light Weight Deep Learning Model,” Int. J. Intell. Eng. Syst., vol. 15, no. 6, pp. 247–262, 2022, doi: 10.22266/ijies2022.1231.24.

S. Chaabene, B. Bouaziz, A. Boudaya, A. Hökelmann, A. Ammar, and L. Chaari, “Convolutional neural network for drowsiness detection using eeg signals,” Sensors, vol. 21, no. 5, pp. 1–19, 2021, doi: 10.3390/s21051734.

Downloads

Published

05-03-2026

Issue

Vol. 13 No. 2 (2026): March-April

Section

Research Articles

License

Copyright (c) 2026 International Journal of Scientific Research in Science, Engineering and Technology

Creative Commons License

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

How to Cite

[1]
Iman Hussein AL-Qinani and Yarub Alazzawi, “Enhancing Motor Imagery EEG Classification Using a Modified Bidirectional LSTM Network”, Int J Sci Res Sci Eng Technol, vol. 13, no. 2, pp. 01–17, Mar. 2026, doi: 10.32628/IJSRSET261306.