MTI: a Motor Imagery Strategy Assisted by Tactile Imagery with Strong Correlation

Abstract

In order to improve the performance of the braincomputer interface system of motor imagery (MI), the optimization of the MI strategy is an effective means.Therefore, this paper proposes a motor-tactile imagery (MTI) strategy to improve the classification accuracy of the MI-based brain-computer interface (BCI) system by adding a corresponding strong correlation of tactile imagery to each imaginary action of the MI.Electroencephalogram (EEG) signals generated by different strategies were collected, and the corresponding classification accuracy was obtained.The experimental results showed that the performance of the MTI-training group (84.08% ± 7.36%) was significantly better than that of the MI group and the MTI-withouttraining group.The MTI strategy proposed in this study can significantly improve the performance of BCI.

Keywords

motor-tactile imagery (MTI) / tactile training / brain-computer interface (BCI)

References

[1] YU T Y, XIAO J, WANG F Y, et al. Enhanced motor imagery training using a hybrid BCI with feedback[J]. IEEE Transactions on Bio-Medical Engineering, 2015, 62(7): 1706-1717.

[2] ZHONG Y C, YAO L, WANG J, et al. Tactile sensation assisted motor imagery training for enhanced BCI performance: a randomized controlled study[J]. IEEE Transactions on Bio-Medical Engineering, 2023, 70(2): 694-702.

[3] ZHANG X Z, GUO Y Q, GAO B Y, et al. Alpha frequency intervention by electrical stimulation to improve performance in mu-based BCI[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2020, 28 (6): 1262-1270.

[4] YAO L, JIANG N, MRACHACZ-KERSTING N, et al. Performance variation of a somatosensory BCI based on imagined sensation: a large population study[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2022, 30: 2486-2493.

[5] KILTENI K, ANDERSSON B J, HOUBORG C, et al. Motor imagery involves predicting the sensory consequences of the imagined movement[J]. Nature Communications, 2018, 9 (1): 1617.

[6] MOROZOVA M, NASIBULLINA A, YAKOVLEV L, et al. Tactile versus motor imagery: differences in corticospinal excitability assessed with single-pulse TMS[J]. Scientific Reports, 2024, 14(1): 14862.

[7] SENGUPTA P, LAKSHMINARAYANAN K. Cortical activation and BCI performance during brief tactile imagery: A comparative study with motor imagery[J]. Behavioural Brain Research, 2024, 459: 114760.

[8] YAKOVLEV L, SYROV N, MIROSHNIKOV A, et al. Event-related desynchronization induced by tactile imagery: An EEG study[J]. eNeuro, 2023, 10(6): ENEURO.0455-22.2023.

[9] BASHFORD L, ROSENTHAL I, KELLIS S, et al. The neurophysiological representation of imagined somatosensory percepts in human cortex[J]. The Journal of Neuroscience, 2021, 41 (10): 2177-2185.

[10] SCHMIDT T T, OSTWALD D, BLANKENBURG F. Imaging tactile imagery: changes in brain connectivity support perceptual grounding of mental images in primary sensory cortices[J]. Neuroimage, 2014, 98: 216-224.

[11] BREITWIESER C, KAISER V, NEUPER C, et al. Stability and distribution of steady-state somatosensory evoked potentials elicited by vibrotactile stimulation[J]. Medical & Biological Engineering & Computing, 2012, 50 (4): 347-357.

[12] GUO Y, LI B Z, YANG L D. Novel fractional wavelet transform: Principles, MRA and application[J]. Digital Signal Processing, 2021, 110: 102937.

[13] DAUBECHIES I, LU J F, WU H T. Synchrosqueezed wavelet transforms: an empirical mode decomposition-like tool[J]. Applied and Computational Harmonic Analysis, 2011, 30(2): 243-261.