Session-independent subject-adaptive mental imagery BCI using selective filter-bank adaptive Riemannian features.
Uloženo v:
| Název: | Session-independent subject-adaptive mental imagery BCI using selective filter-bank adaptive Riemannian features. |
|---|---|
| Autoři: | Meenakshinathan J; Department of Electrical Engineering, IIT Kanpur, Kanpur, India. msandhya@iitk.ac.in., Gupta V; Department of Electrical Engineering, IIT Kanpur, Kanpur, India., Reddy TK; Department of Electronics Engineering, IIT Roorkee, Roorkee, India., Behera L; Department of Electrical Engineering, IIT Kanpur, Kanpur, India.; IIT Mandi, Mandi, India., Sandhan T; Department of Electrical Engineering, IIT Kanpur, Kanpur, India. |
| Zdroj: | Medical & biological engineering & computing [Med Biol Eng Comput] 2024 Nov; Vol. 62 (11), pp. 3293-3310. Date of Electronic Publication: 2024 Jun 03. |
| Způsob vydávání: | Journal Article |
| Jazyk: | English |
| Informace o časopise: | Publisher: Springer Country of Publication: United States NLM ID: 7704869 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1741-0444 (Electronic) Linking ISSN: 01400118 NLM ISO Abbreviation: Med Biol Eng Comput Subsets: MEDLINE |
| Imprint Name(s): | Publication: New York, NY : Springer Original Publication: Stevenage, Eng., Peregrinus. |
| Výrazy ze slovníku MeSH: | Brain-Computer Interfaces* , Electroencephalography*/methods , Imagination*/physiology , Signal Processing, Computer-Assisted*, Humans ; Algorithms |
| Abstrakt: | The brain-computer interfaces (BCIs) facilitate the users to exploit information encoded in neural signals, specifically electroencephalogram (EEG), to control devices and for neural rehabilitation. Mental imagery (MI)-driven BCI predicts the user's pre-meditated mental objectives, which could be deployed as command signals. This paper presents a novel learning-based framework for classifying MI tasks using EEG-based BCI. In particular, our work focuses on the variation in inter-session data and the extraction of multi-spectral user-tailored features for robust performance. Thus, the goal is to create a calibration-free subject-adaptive learning framework for various mental imagery tasks not restricted to motor imagery alone. In this regard, critical spectral bands and the best temporal window are first selected from the EEG training trials of the subject based on the Riemannian user learning distance metric (Dscore) that checks for distinct and stable patterns. The filtered covariance matrices of the EEG trials in each spectral band are then transformed towards a reference covariance matrix using the Riemannian transfer learning, enabling the different sessions to be comparable. The evaluation of our proposed Selective Time-window and Multi-scale Filter-Bank with Adaptive Riemannian (STFB-AR) features on four public datasets, including disabled subjects, showed around 15% and 8% improvement in mean accuracy over baseline and fixed filter-bank models, respectively. (© 2024. International Federation for Medical and Biological Engineering.) |
| References: | Lotte F, Bougrain L, Cichocki A, Clerc M, Congedo M, Rakotomamonjy A, Yger F (2018) A review of classification algorithms for EEG-based brain-computer interfaces: a 10 year update. J Neural Eng 15(3):031005. (PMID: 10.1088/1741-2552/aab2f229488902) Blankertz B, Kawanabe M, Tomioka R, Hohlefeld FU, Nikulin VV, Müller K-R (2007) Invariant common spatial patterns: alleviating nonstationarities in brain-computer interfacing. In: NIPS, pp 113–120. Citeseer. Chaudhary AK, Gupta V, Gaurav K, Reddy TK, Behera L (2023) EEG control of a robotic wheelchair. Dos Santos EM, San-Martin R, Fraga FJ (2023) Comparison of subject-independent and subject-specific EEG-based BCI using LDA and SVM classifiers. Med Biol Eng Comput 61(3):835–845. (PMID: 10.1007/s11517-023-02769-336626112) Reddy TK, Arora V, Behera L, Wang Y-K, Lin C-T (2019) Multiclass fuzzy time-delay common spatio-spectral patterns with fuzzy information theoretic optimization for EEG-based regression problems in brain-computer interface (BCI). IEEE Trans Fuzzy Syst 27(10):1943–1951. (PMID: 10.1109/TFUZZ.2019.2892921) Gaurav K, Reddy SD, Reddy TK (2023) Entropy based EEG irregularity quantification in single-channel SSVEP-based BCIS. In: 2023 IEEE Silchar subsection conference (SILCON), pp 1–6. IEEE. Kim C, Sun J, Liu D, Wang Q, Paek S (2018) An effective feature extraction method by power spectral density of EEG signal for 2-class motor imagery-based BCI. Med Biol Eng Comput 56:1645–1658. (PMID: 10.1007/s11517-017-1761-429497931) Kumar S, Reddy T, Behera L (2018) EEG based motor imagery classification using instantaneous phase difference sequence. In: 2018 IEEE international conference on systems, man, and cybernetics (SMC), pp 499–504. IEEE. Zanini P, Congedo M, Jutten C, Said S, Berthoumieu Y (2017) Transfer learning: a Riemannian geometry framework with applications to brain-computer interfaces. IEEE BME 65(5):1107–1116. (PMID: 10.1109/TBME.2017.2742541) Chai R, Ling SH, Hunter GP, Tran Y, Nguyen HT (2013) Brain-computer interface classifier for wheelchair commands using neural network with fuzzy particle swarm optimization. IEEE JBHI 18(5):1614–1624. Reddy TK, Arora V, Behera L, Wang Y-k, Lin C-T (2020) Fuzzy divergence based analysis for EEG drowsiness detection brain computer interfaces. In: 2020 IEEE international conference on fuzzy systems (FUZZ-IEEE), pp 1–7. Reddy TK, Behera L (2022) Driver drowsiness detection: an approach based on intelligent brain-computer interfaces. IEEE Syst Man Cybern Mag 8(1):16–28. (PMID: 10.1109/MSMC.2021.3069145) Gaur P, McCreadie K, Pachori RB, Wang H, Prasad G (2019) Tangent space features-based transfer learning classification model for two-class motor imagery brain-computer interface. Int J Neural Syst 29(10):1950025. (PMID: 10.1142/S012906571950025431711330) Lotte F, Guan C (2010) Regularizing common spatial patterns to improve BCI designs: unified theory and new algorithms. IEEE BME 58(2):355–362. (PMID: 10.1109/TBME.2010.2082539) Gu J, Jiang J, Ge S, Wang H (2023) Capped L21-norm-based common spatial patterns for EEG signals classification applicable to BCI systems. Med Biol Eng Comput 61(5):1083–1092. (PMID: 10.1007/s11517-023-02782-636658415) Appriou A, Cichocki A, Lotte F (2020) Modern machine-learning algorithms: for classifying cognitive and affective states from electroencephalography signals. IEEE Syst Man Cybern Mag 6(3):29–38. (PMID: 10.1109/MSMC.2020.2968638) Reddy TK, Arora V, Gupta V, Biswas R, Behera L (2021) EEG-based drowsiness detection with fuzzy independent phase-locking value representations using Lagrangian-based deep neural networks. IEEE Trans Syst Man Cybern: Syst 52(1):101–111. (PMID: 10.1109/TSMC.2021.3113823) Gupta V, Meenakshinathan J, Reddy TK, Behera L (2022) Performance study of neural structured learning using Riemannian features for BCI classification. In: 2022 National conference on communications (NCC), pp 297–301. IEEE. Tabar YR, Halici U (2016) A novel deep learning approach for classification of EEG motor imagery signals. J Neural Eng 14(1):016003. (PMID: 10.1088/1741-2560/14/1/01600327900952) Han D-K, Jeong J-H (2021) Domain generalization for session-independent brain-computer interface. In: 2021 9th International winter conference on BCI, pp 1–5. Echtioui A, Zouch W, Ghorbel M, Mhiri C, Hamam H (2021) In: 2021 International wireless communications and mobile computing (IWCMC), title=a novel ensemble learning approach for classification of EEG motor imagery signals, pp 1648–1653. https://doi.org/10.1109/IWCMC51323.2021.9498833. Xie Y, Wang K, Meng J, Yue J, Meng L, Yi W, Jung T-P, Xu M, Ming D (2023) Cross-dataset transfer learning for motor imagery signal classification via multi-task learning and pre-training. J Neural Eng 20(5):056037. (PMID: 10.1088/1741-2552/acfe9c) Zhao H, Zheng Q, Ma K, Li H, Zheng Y (2021) Deep representation-based domain adaptation for nonstationary EEG classification. IIEEE TNNLS 32(2):535–545. https://doi.org/10.1109/TNNLS.2020.3010780. (PMID: 10.1109/TNNLS.2020.3010780) Lawhern VJ, Solon AJ, Waytowich NR, Gordon SM, Hung CP, Lance BJ (2018) EEGNet: a compact convolutional neural network for EEG-based brain-computer interfaces. J Neural Eng 15(5):056013. (PMID: 10.1088/1741-2552/aace8c29932424) Mane R, Chew E, Chua K, Ang KK, Robinson N, Vinod AP, Lee S-W, Guan C (2021) FBCNet: a multi-view convolutional neural network for brain-computer interface. Preprint arXiv:2104.01233. Li Y, Guo L, Liu Y, Liu J, Meng F (2021) A temporal-spectral-based squeeze-and-excitation feature fusion network for motor imagery EEG decoding. IEEE Trans Neural Syst Rehabil Eng 29:1534–1545. (PMID: 10.1109/TNSRE.2021.309990834310314) Schirrmeister RT, Springenberg JT, Fiederer LDJ, Glasstetter M, Eggensperger K, Tangermann M, Hutter F, Burgard W, Ball T (2017) Deep learning with convolutional neural networks for EEG decoding and visualization. Hum Brain Mapp 38:5391–5420. (PMID: 10.1002/hbm.23730287828655655781) Ju C, Gao D, Mane R, Tan B, Liu Y, Guan C (2020) Federated transfer learning for EEG signal classification. In: 2020 42nd Annual international conference of the IEEE engineering in medicine & biology society (EMBC), pp 3040–3045. IEEE. Pan L, Wang K, Xu L, Sun X, Yi W, Xu M, Ming D (2023) Riemannian geometric and ensemble learning for decoding cross-session motor imagery electroencephalography signals. J Neural Eng 20(6):066011. (PMID: 10.1088/1741-2552/ad0a01) Benaroch C, Jeunet C, Lotte F (2021) MI-BCI performances correlate with subject-specific frequency band characteristics. In: BCI 2021-8th international meeting of the brain-computer interface society. Ince NF, Goksu F, Tewfik AH, Arica S (2009) Adapting subject specific motor imagery EEG patterns in space-time-frequency for a brain computer interface. Biomed Signal Process Control 4(3):236–246. (PMID: 10.1016/j.bspc.2009.03.005) Zhang Y, Chen J (2022) Filter bank Riemannian-based kernel support vector machine for motor imagery decoding. In: ITM web of conferences, vol 47, p 02013. EDP Sciences. Wu F, Gong A, Li H, Zhao L, Zhang W, Fu Y (2021) A new subject-specific discriminative and multi-scale filter bank tangent space mapping method for recognition of multiclass motor imagery. Front Hum Neurosci 15:595723. (PMID: 10.3389/fnhum.2021.595723337629117982728) Gaur P, Pachori RB, Wang H, Prasad G (2018) A multi-class EEG-based BCI classification using multivariate empirical mode decomposition based filtering and Riemannian geometry. Expert Syst Appl 95:201–211. (PMID: 10.1016/j.eswa.2017.11.007) Xie X, Zou X, Yu T, Tang R, Hou Y, Qi F (2022) Multiple graph fusion based on Riemannian geometry for motor imagery classification. Appl Intell 52(8):9067–9079. (PMID: 10.1007/s10489-021-02975-2) Moufassih M, Tarahi O, Hamou S, Agounad S, Idrissi Azami H (2023) Boosting motor imagery brain-computer interface classification using multiband and hybrid feature extraction. Multimed Tools Appl 1–32. Ramoser H, Muller-Gerking J, Pfurtscheller G (2000) Optimal spatial filtering of single trial EEG during imagined hand movement. IEEE Trans Rehabil Eng 8(4):441–446. (PMID: 10.1109/86.89594611204034) Barachant A, Bonnet S, Congedo M, Jutten C (2010) Riemannian geometry applied to BCI classification. In: Intl conference on latent variable analysis and signal separation, pp 629–636. Springer. Barachant A, Bonnet S, Congedo M, Jutten C (2011) Multiclass brain-computer interface classification by Riemannian geometry. IEEE BME 59(4):920–928. (PMID: 10.1109/TBME.2011.2172210) Lotte F, Jeunet C (2017) Online classification accuracy is a poor metric to study mental imagery BCI user learning: an experimental demonstration and new metrics. In: 7th International BCI conference. Kumar S, Yger F, Lotte F (2019) Towards adaptive classification using Riemannian geometry approaches in brain-computer interfaces. In: 2019 7th International winter conference on BCI, pp 1–6. Reuderink B, Poel M (2008) Robustness of the common spatial patterns algorithm in the BCI-pipeline. University of Twente, Tech. Rep. Tangermann M, Müller K-R, Aertsen A, Birbaumer N, Braun C, Brunner C, Leeb R, Mehring C, Miller KJ et al (2012) Review of the BCI competition IV. Front Neurosci 55. Scherer R, Faller J, Friedrich EV, Opisso E, Costa U, Kübler A, Müller-Putz GR (2015) Individually adapted imagery improves brain-computer interface performance in end-users with disability. PloS One 10(5):0123727. (PMID: 10.1371/journal.pone.0123727) Zhou B, Wu X, Lv Z, Zhang L, Guo X (2016) A fully automated trial selection method for optimization of motor imagery based brain-computer interface. PloS One 11(9):0162657. (PMID: 10.1371/journal.pone.0162657) Faller J, Vidaurre C, Solis-Escalante T, Neuper C, Scherer R (2012) Autocalibration and recurrent adaptation: towards a plug and play online ERD-BCI. IEEE TSNE 20(3):313–319. Rodrigues PLC, Congedo M, Jutten C (2018) Multivariate time-series analysis via manifold learning. In: 2018 IEEE statistical signal processing workshop (SSP), pp 573–577. Maaten L, Hinton G (2008) Visualizing data using t-SNE. J Mach Learn Res 9(11). |
| Grant Information: | FIG-100953 Indian Institute of Technology Roorkee; SER-1968-ECD Department of Science and Technology, Ministry of Science and Technology, India |
| Contributed Indexing: | Keywords: Brain-computer interface; Machine learning; Riemannian geometry; Subject-adaptive; Transfer learning |
| Entry Date(s): | Date Created: 20240602 Date Completed: 20241016 Latest Revision: 20241016 |
| Update Code: | 20250114 |
| DOI: | 10.1007/s11517-024-03137-5 |
| PMID: | 38825665 |
| Databáze: | MEDLINE |
Full Text Finder 
Nájsť tento článok vo Web of Science Buďte první, kdo okomentuje tento záznam!