Channel Selection Strategies for High-Accuracy EEG-Based Biometric Authentication

doi:10.23940/ijpe.26.01.p3.1928

Abstract

Abstract: Security is a primary concern in modern applications where large volumes of data are exchanged, making authentication and protection from external attacks essential. Biometric systems offer enhanced robustness, with EEG signals providing unique, hard-to-replicate cognitive patterns. This work aims to design an EEG-based personalized authentication system with improved accuracy and reduced processing complexity through optimized channel selection. A novel spectral correlation-based channel selection method interfaced with selection logic for reduced processing is proposed to optimally cluster EEG channels. Signal fusion with minimum deviation constraints mitigates information loss from discarded channels in PCA/Wilcoxon approaches. The proposed method achieves a decision accuracy of 99.2% with lower computational overhead, outperforming PCA/Wilcoxon-based systems. The integration of optimized channel selection and signal fusion enables high-accuracy, real-time EEG-based authentication suitable for resource-constrained biomedical security applications.

Key words: authentication, biometric security system, channel selection, channel clustering and fusion, EEG signal, energy correlation method

Shashank D. Biradar, Sanjay L. Nalbalwar, Shankar B. Deosarkar, and Brijesh R. Iyer. Channel Selection Strategies for High-Accuracy EEG-Based Biometric Authentication [J]. Int J Performability Eng, 2026, 22(1): 19-28.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

References

[1] Moolla Y., De Kock A., Mabuza-Hocquet G., Ntshangase C.S., Nelufule N., andKhanyile P., 2021. Biometric recognition of infants using fingerprint, iris, and ear biometrics.IEEE Access, 9, pp. 38269-38286.
[2] Alrawili R., AlQahtani A.A.S., andKhan M.K., 2024. Comprehensive survey: biometric user authentication application, evaluation, and discussion.Computers and Electrical Engineering, 119, 109485.
[3] Mandalapu H., PN A.R., Ramachandra R., Rao K.S., Mitra P., Prasanna S.M., andBusch C., 2021. Audio-visual biometric recognition and presentation attack detection: A comprehensive survey.IEEE Access, 9, pp. 37431-37455.
[4] Shaheed K., Szczuko P., Kumar M., Qureshi I., Abbas Q., andUllah I., 2024. Deep learning techniques for biometric security: A systematic review of presentation attack detection systems.Engineering Applications of Artificial Intelligence, 129, 107569.
[5] Fidas C.A., andLyras D., 2023. A review of EEG-based user authentication: trends and future research directions.IEEE Access, 11, pp. 22917-22934.
[6] Seyfizadeh A., Peach R.L., Tovote P., Isaias I.U., Volkmann J., andMuthuraman M., 2024. Enhancing security in brain-computer interface applications with deep learning: electroencephalogram-based user identification.Expert Systems with Applications, 253, 124218.
[7] Zhang S., Sun L., Mao X., Hu C., andLiu P., 2021. Review on EEG‐based authentication technology.Computational Intelligence and Neuroscience, 2021(1), 5229576.
[8] Sui Y., Yu H., Zhang C., Chen Y., Jiang C., andLi L., 2022. Deep brain-machine interfaces: sensing and modulating the human deep brain. National Science Review, 9(10), nwac212.
[9] Pongthanisorn G., Shirai A., Sugiyama S., andCapi G., 2023. Combination of reinforcement and deep learning for EEG channel optimization on brain-machine interface systems. In2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), pp. 97-102.
[10] Chen X., Ye Z., Xie X., Liu Y., Gao X., Su W., Zhu S., Sun Y., Zhang M., andMa S., 2022. Web search via an efficient and effective brain-machine interface. InProceedings of the Fifteenth ACM International Conference on Web Search and Data Mining, pp. 1569-1572.
[11] Wang M., Wang S., andHu J., 2022. Cancellable template design for privacy-preserving EEG biometric authentication systems.IEEE Transactions on Information Forensics and Security, 17, pp. 3350-3364.
[12] Xia K., Duch W., Sun Y., Xu K., Fang W., Luo H., Zhang Y., Sang D., Xu X., Wang F.Y., andWu D., 2022. Privacy-preserving brain-computer interfaces: A systematic review. IEEE Transactions on Computational Social Systems,10(5), pp. 2312-2324.
[13] Salama G.M., El-Gazar S., Omar B., andHassan A.A., 2024. Multimodal cancelable biometric authentication system based on EEG signal for IoT applications. Journal of Optics,53(3), pp. 1839-1853.
[14] Meng L., Jiang X., Chen X., Liu W., Luo H., andWu D., 2024. Adversarial filtering based evasion and backdoor attacks to EEG-based brain-computer interfaces.Information Fusion, 107, 102316.
[15] Lee Y.E., Kwak N.S., andLee S.W., 2020. A real-time movement artifact removal method for ambulatory brain-computer interfaces. IEEE Transactions on Neural Systems and Rehabilitation Engineering,28(12), pp. 2660-2670.
[16] Ketola E.C., Barankovich M., Schuckers S., Ray-Dowling A., Hou D., andImtiaz M.H., 2022. Channel reduction for an EEG-based authentication system while performing motor movements.Sensors, 22(23), 9156.
[17] Al Hammadi A.Y., Lee D., Yeun C.Y., Damiani E., Kim S.K., Yoo P.D., andChoi H.J., 2020. Novel EEG sensor-based risk framework for the detection of insider threats in safety critical industrial infrastructure.IEEE Access, 8, pp. 206222-206234.
[18] La Rocca D., Campisi P., Vegso B., Cserti P., Kozmann G., Babiloni F., andFallani F.D.V., 2014. Human brain distinctiveness based on EEG spectral coherence connectivity. IEEE Transactions on Biomedical Engineering,61(9), pp. 2406-2412.
[19] Rodrigues D., Silva G.F., Papa J.P., Marana A.N., andYang X.S., 2016. EEG-based person identification through binary flower pollination algorithm.Expert Systems with Applications, 62, pp. 81-90.
[20] Koike-Akino T., Mahajan R., Marks T.K., Wang Y., Watanabe S., Tuzel O., andOrlik P., 2016. High-accuracy user identification using EEG biometrics. In2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 854-858.
[21] Ortega-Rodríguez J., Gómez-González J.F., andPereda E., 2023. Selection of the minimum number of EEG sensors to guarantee biometric identification of individuals.Sensors, 23(9), 4239.
[22] Alzahab N.A., Di Iorio A., Apollonio L., Alshalak M., Gravina A., Antognoli L., Baldi M., Scalise L., andAlchalabi B., 2021. Auditory evoked potential EEG-biometric dataset.