Poster No:
1350
Submission Type:
Abstract Submission
Authors:
Raana Nouri1, Russell Butler2
Institutions:
1Bishop's University, Oakville, Ontario, 2Bishop's University, Sherbrooke, Quebec
First Author:
Co-Author:
Introduction:
Electroencephalography (EEG)-based brain-computer interfaces represent a promising frontier in human-computer interaction, particularly in gaming and therapeutic applications (Nicolas-Alonso & Gomez-Gil, 2012). Despite significant advances, achieving reliable realtime action decoding remains a complex challenge. This study investigated the feasibility of decoding specific motor actions during gameplay using EEG signals, with a focus on developing robust classification methods that can generalize across subjects (He & Wu, 2019).
Methods:
The study involved thirteen participants engaging in a structured Tetris gaming task while 32-channel EEG data was recorded using a BioSemi ActiveTwo system. The experimental protocol included initial baseline recording, active gameplay sessions totaling 45 minutes, and regular rest intervals.
A comprehensive processing pipeline was implemented, incorporating advanced artifact removal techniques using Independent Component Analysis (ICA) and sophisticated frequency-based feature extraction methods (Delorme & Makeig, 2004). Particular attention was paid to beta band (15-25 Hz) activity, known for its association with motor control and planning (Makeig et al., 2004).
The study evaluated three distinct classification approaches: Random Forest, Gradient Boosting, and Support Vector Machines (SVM), utilizing event-related spectral perturbation (ERSP) features. Cross-validation techniques and leave-one-out analyses were employed to assess model generalizability. Feature extraction focused on four frequency bands:
• Delta: 1-4 Hz
• Theta: 4-8 Hz
• Alpha: 8-13 Hz
• Beta: 13-30 Hz
Additional derived measures included relative power calculations and band ratios (Subasi,2007).
Results:
The Random Forest classifier demonstrated superior performance, achieving an overall accuracy of 88% (±2%) in distinguishing between four distinct key press actions, significantly outperforming both Gradient Boosting (68% ±2%) and SVM (84% ±2%) approaches (Lotte
et al., 2018).
Beta band activity showed consistent and distinctive modulation patterns in motor cortex regions (C3, Cz, C4), with normalized power differences of 0.75 ±0.12 across channels. The analysis revealed particularly strong discrimination for certain actions, with precision and recall values exceeding 0.90 for specific motor commands.
Leave-one-out cross-validation demonstrated reasonable generalizability across subjects, achieving an accuracy of 0.757 (±0.429). Processing times remained consistently manageable (approximately 1.16 seconds per sample), suggesting potential feasibility for near-real-time applications
(McFarland et al., 2015).
Conclusions:
This research establishes a viable framework for EEG-based action decoding in gaming environments, demonstrating the potential for practical applications in adaptive gaming interfaces and rehabilitation systems (Craik et al., 2019). The success of beta band features and ERSP-based classification provides a foundation for developing more sophisticated braincomputer interaction systems.
While the achieved classification accuracy represents a significant advancement, several areas for improvement were identified, including enhanced cross-subject generalization and reduced processing latency. Future work should focus on integrating deep learning approaches and implementing multimodal data integration. The applications extend beyond gaming to include therapeutic interventions, highlighting the impact of this research in advancing brain computer interface technology.
Modeling and Analysis Methods:
EEG/MEG Modeling and Analysis 1
Novel Imaging Acquisition Methods:
EEG 2
Keywords:
Cognition
Computational Neuroscience
Data analysis
Electroencephaolography (EEG)
Experimental Design
Informatics
Machine Learning
Motor
1|2Indicates the priority used for review
By submitting your proposal, you grant permission for the Organization for Human Brain Mapping (OHBM) to distribute your work in any format, including video, audio print and electronic text through OHBM OnDemand, social media channels, the OHBM website, or other electronic publications and media.
I accept
The Open Science Special Interest Group (OSSIG) is introducing a reproducibility challenge for OHBM 2025. This new initiative aims to enhance the reproducibility of scientific results and foster collaborations between labs. Teams will consist of a “source” party and a “reproducing” party, and will be evaluated on the success of their replication, the openness of the source work, and additional deliverables. Click here for more information.
Propose your OHBM abstract(s) as source work for future OHBM meetings by selecting one of the following options:
I do not want to participate in the reproducibility challenge.
Please indicate below if your study was a "resting state" or "task-activation” study.
Other
Healthy subjects only or patients (note that patient studies may also involve healthy subjects):
Healthy subjects
Was this research conducted in the United States?
No
Were any human subjects research approved by the relevant Institutional Review Board or ethics panel?
NOTE: Any human subjects studies without IRB approval will be automatically rejected.
Yes
Were any animal research approved by the relevant IACUC or other animal research panel?
NOTE: Any animal studies without IACUC approval will be automatically rejected.
Not applicable
Please indicate which methods were used in your research:
EEG/ERP
Provide references using APA citation style.
1. Craik, A., He, Y., & Contreras-Vidal, J. L. (2019). Deep learning for electroencephalogram (EEG) classification tasks: A review. Journal of Neural Engineering, 16(3), 031001.
2. Delorme, A., & Makeig, S. (2004). EEGLAB: An open source toolbox for analysis of single-trial EEG dynamics. Journal of Neuroscience Methods, 134(1), 9-21.
3. He, H., &Wu, D. (2019). Transfer learning for brain–computer interfaces: A Euclidean space data alignment approach. IEEE Transactions on Biomedical Engineering, 67(2), 399-410. 2
4. Lotte, F., Congedo, M., Lecuyer, A., Lamarche, F., & Arnaldi, B. (2018). A review of classification algorithms for EEG-based brain computer interfaces: A 10-year update. Journal of Neural Engineering, 15(3), 031005.
5. Makeig, S., Debener, S., Onton, J., & Delorme, A. (2004). Mining event-related brain dynamics. Trends in Cognitive Sciences, 8(5), 204-210.
6. McFarland, D. J., Sarnacki, W. A., & Wolpaw, J. R. (2015). Electroencephalographic (EEG) control of three-dimensional movement. Journal of Neural Engineering, 12(3), 036007.
7. Nicolas-Alonso, L. F., & Gomez-Gil, J. (2012). Brain computer interfaces: A review. Sensors, 12(2), 1211-1279.
8. Subasi, A. (2007). EEG signal classification using wavelet feature extraction and a mixture of expert model. Expert Systems with Applications, 32(4), 1084-1093.
No