Exploration and research on paradigm, algorithm, as well as encoding and decoding concepts of brain-computer interface

doi:10.12267/j.issn.2096-5931.2024.05.009

Abstract

Abstract:

Brain-computer interface (BCI) is an interdisciplinary field combining brain science, information and communication technology, and artificial intelligence, enabling a direct information exchange between the brain and external devices. After decades of theoretical research and engineering validation, BCI is gradually moving from scientific research to industrial applications. With the increasing interest in the innovation chain and industrial chain, BCI has received widespread attention from various interdisciplinary fields. However, there are certain differences in the concepts of BCI technology in areas such as paradigm encoding and algorithm decoding compared with those in artificial intelligence and information and communication fields, which has caused some limitations on cooperation and exchange among multiple fields. To further promote the cross-field cooperation and exchange of BCI, and to drive the coordinated development of the technical chain and innovation chain in this field, this paper explores the paradigms, algorithms, as well as basic concepts and principles of encoding and decoding of BCI. Then, it designs a steady-state visual evoked potentials BCI based on left and right visual field stimulation.

Key words: BCI, paradigm, algorithm, encoding, decoding

CLC Number:

LIANG Liyan, KONG Shuyi, ZHANG Qian, CHENG Liwei, ZHOU Jie, SUN Yike. Exploration and research on paradigm, algorithm, as well as encoding and decoding concepts of brain-computer interface[J]. Information and Communications Technology and Policy, 2024, 50(5): 61-70.

Add to citation manager EndNote|Ris|BibTeX

URL:

http://ictp.caict.ac.cn/EN/10.12267/j.issn.2096-5931.2024.05.009

http://ictp.caict.ac.cn/EN/Y2024/V50/I5/61

Figures/Tables 5

References 31

[1]	GAO X R, WANG Y J, CHEN X G, et al. Interface, interaction, and intelligence in generalized brain-computer interfaces[J]. Trends in Cognitive Sciences, 2021, 25(8): 671-684. doi: 10.1016/j.tics.2021.04.003 pmid: 34116918
[2]	MCFARLAND D J, WOLPAW J R. EEG-based brain-computer interfaces[J]. Current Opinion in Biomedical Engineering, 2017, 4: 194-200. doi: 10.1016/j.cobme.2017.11.004 pmid: 29527584
[3]	XIAO X L, XU M P, HAN J, et al. Enhancement for P300-speller classification using multi-window discriminative canonical pattern matching[J]. Journal of Neural Engineering, 2021, 18(4): 046079.
[4]	ZHU D H, BIEGER J, GARCIA MOLINA G G, et al. A survey of stimulation methods used in SSVEP-based BCIs[J]. Computational Intelligence and Neuroscience, 2010, 2010: 702357.
[5]	BIN G Y, GAO X R, WANG Y J, et al. A high-speed BCI based on code modulation VEP[J]. Journal of Neural Engineering, 2011, 8(2): 025015.
[6]	WANG Z W, HEALY G, SMEATON A F, et al. A review of feature extraction and classification algorithms for image RSVP based BCI[J]. Signal Processing and Machine Learning for Brain-machine Interfaces, 2018: 243-270.
[7]	SHI N L, MIAO Y N, HUANG C X, et al. Estimating and approaching the maximum information rate of noninvasive visual brain-computer interface[J]. NeuroImage, 2024: 120548.
[8]	张翔, 郭士杰, 陈玲玲, 等. 基于触觉 P300 的脑控下肢康复机器人[J]. 科学技术与工程, 20232, 22(35): 15659-15666.
[9]	NINENKO I, KLEEVA D F, BUKREEV N, et al. An experimental paradigm for studying EEG correlates of olfactory discrimination[J]. Frontiers in Human Neuroscience, 2023, 17: 1117801.
[10]	PFURTSCHELLER G, ALLISON B Z, BRUNNER C, et al. The Hybrid BCI[J]. Frontiers in Neuroscience, 2010, 4(30): 30.
[11]	ERAT K, ŞAHIN E B, DOĞAN F, et al. Emotion recognition with EEG-based brain-computer interfaces: a systematic literature review[J]. Multimedia Tools and Applications, 2024: 1-48.
[12]	NIRMALA DEVI A N, RATHNA R. EEG data based human attention recognition using various machine learning techniques: a review[J]. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 2024, 11(7): 2299096.
[13]	ELDELE E, CHEN Z, LIU C, et al. An attention-based deep learning approach for sleep stage classification with single-channel EEG[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering: a Publication of the IEEE Engineering in Medicine and Biology Society, 2021, 29: 809-818.
[14]	MONTEIRO T G, SKOURUP C, ZHANG H. Using EEG for mental fatigue assessment: a comprehensive look into the current state of the art[J]. IEEE Transactions on Human-Machine Systems, 2019, 49(6): 599-610.
[15]	SCHMIERER T, LI T, LI Y. Harnessing machine learning for EEG signal analysis: innovations in depth of anaesthesia assessment[J]. Artificial Intelligence in Medicine, 2024, 151: 102869.
[16]	GUAN K, ZHANG Z, LIU T, et al. Cross-task mental workload recognition based on EEG tensor representation and transfer learning[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2023.
[17]	NAKANISHI M, WANG Y, CHEN X, et al. Enhancing detection of SSVEPs for a high-speed brain speller using task-related component analysis[J]. IEEE Transactions on Biomedical Engineering, 2018, 65(1): 104-112.
[18]	JIN J, XIAO R C, DALY I, et al. Internal feature selection method of CSP based on L1-norm and Dempster-Shafer theory[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(11): 4814-4825.
[19]	HOSSAIN K M, ISLAM M A, HOSSAIN S, et al. Status of deep learning for EEG-based brain-computer interface applications[J]. Frontiers in Computational Neuroscience, 2023, 16: 1-17.
[20]	LIANG L Y, ZHANG Q, ZHOU J, et al. Dataset evaluation method and application for performance testing of SSVEP-BCI decoding algorithm[J]. Sensors, 2023, 23(14): 6310.
[21]	JIANG W B, ZHAO L M, LU B L. Large brain model for learning generic representations with tremendous EEG data in BCI[C]// The 12th International Conference on Learning Representations. Vienna, 2024.
[22]	JOHN M S, PICTON T W. Human auditory steady-state responses to amplitude-modulated tones: phase and latency measurements[J]. Hearing Research, 2000, 141(1-2): 57-79. pmid: 10713496
[23]	BIN G Y, GAO X R, YAN Z, et al. An online multi-channel SSVEP-based brain-computer interface using a canonical correlation analysis method[J]. Journal of Neural Engineering, 2009, 6(4): 046002.
[24]	NAKANISHI M, WANG Y J, CHEN X G, et al. Enhancing detection of SSVEPs for a high-speed brain speller using task-related component analysis[J]. IEEE Transactions on Biomedical Engineering, 2018, 65(1): 104-112.
[25]	MCFARLAND D J, SARNACKI W A, WOLPAW J R. Brain-computer interface (BCI) operation: optimizing information transfer rates[J]. Biological Psychology, 2003, 63(3): 237-251. pmid: 12853169
[26]	WANG Y T, NAKANISHI M, WANG Y J, et al. An online brain-computer interface based on SSVEPs measured from non-hair-bearing areas[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2016, 25(1): 14-21.
[27]	KWAK N S, LEE S W. Error correction regression framework for enhancing the decoding accuracies of ear-EEG brain-computer interfaces[J]. IEEE Transactions on Cybernetics, 2020, 50(8): 3654-3667.
[28]	AHN J W, KU Y, KIM D Y, et al. Wearable in-the-ear EEG system for SSVEP-based brain-computer interface[J]. Electronics Letters, 2018, 54(7): 413-414. doi: 10.1049/el.2017.3970
[29]	FLORIANO A, RODRIGUEZ D D, DIEZ P F, et al. Assessment of high-frequency steady-state visual evoked potentials from below-the-hairline areas for a brain-computer interface based on depth-of-field[J]. Computer Methods and Programs in Biomedicine, 2020, 184: 105271.
[30]	LIANG L Y, BIN G Y, CHEN X G, et al. Optimizing a left and right visual field biphasic stimulation paradigm for SSVEP-based BCIs with hairless region behind the ear[J]. Journal of Neural Engineering, 2021, 18(6): 066040.
[31]	LIU B C, CHEN X G, SHI N L, et al. Improving the performance of individually calibrated SSVEP-BCI by task-discriminant component analysis[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2021, 29: 1998-2007.

被试	在线训练阶段(5 s窗)		在线测试阶段(3 s窗)
被试	准确率	ITR/bits/min	准确率	ITR/bits/min
被试1	97.22%	36.06	100.00%	61.46
被试2	80.00%	23.69	91.67%	49.42
被试3	88.33%	29.03	91.67%	49.42
被试4	61.67%	14.17	83.33%	40.43
被试5	83.33%	25.73	91.67%	49.42
被试6	58.33%	12.69	83.33%	40.43
被试7	86.67%	27.90	83.33%	40.43
被试8	100.00%	39.11	100.00%	61.46
平均±标准差	81.94%±14.13%	26.05±8.72	90.63%±6.51%	49.06±8.15

被试	在线训练阶段(5 s窗)		在线测试阶段(3 s窗)
被试	准确率	ITR/bits/min	准确率	ITR/bits/min
被试1	97.22%	36.06	100.00%	61.46
被试2	80.00%	23.69	91.67%	49.42
被试3	88.33%	29.03	91.67%	49.42
被试4	61.67%	14.17	83.33%	40.43
被试5	83.33%	25.73	91.67%	49.42
被试6	58.33%	12.69	83.33%	40.43
被试7	86.67%	27.90	83.33%	40.43
被试8	100.00%	39.11	100.00%	61.46
平均±标准差	81.94%±14.13%	26.05±8.72	90.63%±6.51%	49.06±8.15

研究工作	被试数	目标数	识别准确率	ITR/bits/min	验证方式
Wang^[26]等	5	12	84.08%	30.21	在线
Kwak^[27]等	11	3	78.79%	18.07	在线
Ahn^[28]等	6	6	79.90%	11.03	离线
Floriano^[29]等	4	2	91.60%	5.30	在线
Liang^[30]等	16	12	84.20%	17.80	在线
本文工作	8	12	90.63%	49.06	在线

研究工作	被试数	目标数	识别准确率	ITR/bits/min	验证方式
Wang^[26]等	5	12	84.08%	30.21	在线
Kwak^[27]等	11	3	78.79%	18.07	在线
Ahn^[28]等	6	6	79.90%	11.03	离线
Floriano^[29]等	4	2	91.60%	5.30	在线
Liang^[30]等	16	12	84.20%	17.80	在线
本文工作	8	12	90.63%	49.06	在线