Personalization of Brain–Computer Interfaces Based on the SSVEP Paradigm Considering Individual User Response Characteristics
Abstract
Steady-State Visually Evoked Potential (SSVEP)-based Brain-Computer Interfaces (BCIs) provide users with an alternative means of controlling external devices without physical interaction. However, their practical application outside research laboratories remains limited due to the high inter-individual variability in user responses to visual stimuli, which reduces the accuracy and efficiency of BCIs. This issue represents one of the key challenges in the field. In this work, we investigate how accounting for individual sensitivity to photic stimulation frequency affects the performance of modern machine learning models commonly employed in BCI design. To address this problem, we collected a custom electroencephalography (EEG) dataset recorded from a group of eight participants. For each participant, stimulation frequencies were selected individually using a frequency compatibility coefficient proposed in our previous studies. Six most compatible and six least compatible stimulation frequencies were determined for each subject. The results of testing three state-of-the-art machine learning models (ATCNet, EEG-TCNet, and EEGNet) demonstrate a substantial improvement in classification performance. On average across participants, the transition to classifying compatible frequency sets increased classification accuracy from 61-69% to 95-98% for all models, while Cohen’s kappa improved from 0.52-0.63 to 0.94-0.98. These findings highlight the potential of incorporating individual response characteristics to enhance the efficiency of SSVEP-based Brain–Computer Interfaces.
Full Text:
PDF (Russian)References
Levitskaya O. S., Lebedev M. A. Interfeys mozg – komp'yuter: budushchee v nastoyashchem [Brain-computer interface: the future in the present]. Vestnik RGMU, 2016, no. 2. Available at: https://cyberleninka.ru/article/n/interfeys-mozg-kompyuter-buduschee-v-nastoyaschem (accessed: 13.11.2024).
Mokienko O.A., Chernikova L.A., Frolov A.A. Interfeis mozg-komp'yuter kak novaya tekhnologiya neiroreabilitatsii [Brain-computer interface as a novel tool of neurorehabilitation]. Annaly klinicheskoi i ehksperimental'noi nevrologii = Annals of Clinical and Experimental Neurology, 2011, vol. 5, no. 3, pp. 46–52
Hochberg L.R., Serruya M.D., Friehs G.M. et al. Neuronal ensemble control of prosthetic devices by a human with tetraplegia. Nature, 2006, vol. 442(7099), pp. 164–171.
Kennedy P.R., Bakay R.A.E. Restoration of neural output from a paralyzed patient by a direct brain connection. NeuroReport, 1998, vol. 9(8), pp. 1707–1711.
Vidal J.J. Toward direct brain-computer communication. Annu Rev Biophys Bioeng, 1973, vol. 2, pp. 157–180. DOI: 10.1146/annurev.bb.02.060173.001105. PMID: 4583653.
Altuwaijri G.A., Muhammad G., Altaheri H., Alsulaiman M. A Multi-Branch Convolutional Neural Network with Squeeze-and-Excitation Attention Blocks for EEG-Based Motor Imagery Signals Classification. Diagnostics, 2022, vol. 12:995. DOI: https://doi.org/10.3390/diagnostics12040995
Altaheri H., Muhammad G., Alsulaiman M. Physics-Informed Attention Temporal Convolu-tional Network for EEG-Based Motor Imagery Classification. IEEE Transactions on Industrial Informatics, 2023, vol. 19, pp. 2249–2258. DOI: 10.1109/TII.2022.3197419.
Li, Zhe. Mamba with split-based pyramidal convolution and Kolmogorov-Arnold network-channel-spatial attention for electroencephalogram classification. Frontiers in Sensors, 2025, vol. 6: 1548729.
Deng, Yang, et al. OS-SSVEP: one-shot SSVEP classification. Neural Networks, 2024, vol. 180:106734.
Wei, Qingguo, et al. Enhancing the performance of SSVEP-based BCIs by combining task-related component analysis and deep neural network. Scientific Reports, 2025, vol. 15.1:365.
Amiri S., Rabbi A., Azinfar L., Fazel-Rezai R. A Review of P300, SSVEP, and Hybrid P300/SSVEP Brain- Computer Interface Systems. InTech, 2013. DOI: 10.5772/56135
Ng K.B., Bradley A.P., Cunnington R. Stimulus specificity of a steady-state visual-evoked potential-based brain–computerinterface. J. Neural Eng, 2012, vol. 9(3):036008. – DOI: 10.1088/1741-2560/9/3/036008.
Chevallier S. et al. The largest EEG-based BCI reproducibility study for open science: the MOABB benchmark. arXiv preprint arXiv:2404.15319. – 2024.
Xiang L., Jingjing C., Nanlin S., Chen Y., Puze G., Xiaogang C., Yijun W., Shangkai G., Xiaorong G. A hybrid steady-state visual evoked response-based brain-computer interface with MEG and EEG. Expert Systems with Applications, 2023, vol. 223, pp. 119736. – DOI: 10.1016/j.eswa.2023.119736.
Becker S., Dhindsa K., Mousapour L., Al Dabagh Y. BCI Illiteracy: It’s Us, Not Them. Op-timizing BCIs for Individual Brains. 10th International Winter Conference on Brain-Computer Interface (BCI), Gangwon-do, Korea, 2022, pp. 1–3. DOI: 10.1109/BCI53720.2022.9735007.
Chailloux Peguero J.D., Hernández-Rojas L.G., Mendoza-Montoya O., Caraza R., Antelis J.M. SSVEP detection assessment by combining visual stimuli paradigms and no-training detection methods. Front. Neurosci, 2023, vol. 17:1142892. – DOI: 10.3389/fnins.2023.1142892
Kuś R., Duszyk A., Milanowski P., Łabecki M., Bierzyńska M., Radzikowska Z., Michalska M., Żygierewicz J., Suffczyński P., Durka P.J. On the Quantification of SSVEP Frequency Responses in Human EEG in Realistic BCI Conditions. PLoS ONE, 2013, vol. 8, pp. 1–9. – DOI: 10.1371/journal.pone.0077536
Kozin A., Gerasimov A., Bakaev M., Pashkov A., Razumnikova O. Automating Stimulation Frequency Selection for SSVEP-Based Brain-Computer Interfaces // Algorithms. – 2023. – Vol. 16(11). – P. 502. – DOI: 10.3390/a16110502
Kozin A.V., Gerasimov A.K., Bakaev M.A. Individual'nyi podkhod k vyboru chastoty fotostimulyatsii v sistemakh IMK na osnove SSVEP-paradigmy i modelei mashinnogo obucheniya [An individualized approach to selecting photostimulation frequency in BCI systems based on the SSVEP paradigm and machine learning models]. Sistemy analiza i obrabotki dannykh = Analysis and Data Processing Systems, 2025, no. 3 (99), pp. 45–68. DOI: 10.17212/2782-2001-2025-3-45-68.
Mitsar-EEG-SmartBCI: Wireless neurointerfaces for BCI research and development [Online]. Available: https://www.mitsar-eeg.ru/page.php?id=smartbci/. Accessed: May 13, 2025.
SmartCAPx24 Light Rev2 [Online]. Available: https://mitsar-eeg.com/product/smartcapx24-light-rev2-by-mcscap/. Accessed: Nov. 9, 2025.)
Lab Streaming Layer. Why LSL? [Online]. Available: https://labstreaminglayer.org/#/ . Accessed: May 13, 2025.
A. V. Kozin, Certificate of State Registration of a Computer Program, No. 2025663518, May 28, 2025 inRussian.
Nakanishi M., Wang Y., Wang Y.T., Jung T.P. A Comparison Study of Canonical Correlation Analysis Based Methods for Detecting Steady-State Visual Evoked Potentials. PLOS ONE, 2015, vol. 10(10), pp. 1–18. – DOI: 10.1371/journal.pone.0140703
Wang Y., Chen X., Gao X., Gao S. A Benchmark Dataset for SSVEP-Based Brain-Computer Interfaces. IEEE Trans Neural Syst Rehabil Eng, 2017, vol. 25(10), pp. 1746–1752. – DOI: 10.1109/TNSRE.2016.2627556..
Ingolfsson T. M., Hersche M., Wang X., Kobayashi N., Cavigelli L., Benini L. EEG-TCNet: An Accurate Temporal Convolutional Network for Embedded Motor-Imagery Brain–Machine Interfaces. IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2020, pp. 2958–2965. – DOI: 10.1109/SMC42975.2020.9283028
Lawhern V., Solon A., Waytowich N., Gordon S., Hung C., Lance B. EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces. Journal of Neural Engineering, 2016, vol. 15. DOI: 10.1088/1741-2552/aace8c.
Refbacks
- There are currently no refbacks.
Abava Кибербезопасность ИТ конгресс СНЭ
ISSN: 2307-8162