用于运动准备诱发脑电响应识别的新型复合空间滤波算法研究*

doi:10.12267/j.issn.2096-5931.2024.05.001

信息通信技术与政策 ›› 2024, Vol. 50 ›› Issue (5): 2-11.doi: 10.12267/j.issn.2096-5931.2024.05.001

用于运动准备诱发脑电响应识别的新型复合空间滤波算法研究^*

Research on novel compound spatial filter algorithm for recognition of pre-movement EEG patterns

王坤, 黄依宁, 许敏鹏, 顾晓松, 明东

天津大学医学工程与转化医学研究院,天津 300072

收稿日期:2024-05-06 出版日期:2024-05-25 发布日期:2024-05-31
通讯作者: 明东,天津大学副校长,天津大学医学部执行主任,讲席教授,主要从事脑机接口、神经工程等方面的研究工作
作者简介:
王坤,天津大学医学工程与转化医学研究院副教授,主要从事脑机接口、运动意图脑电信号特征提取及其在神经康复中的应用等方面的研究工作
黄依宁,天津大学医学工程与转化医学研究院硕士研究生在读,主要从事脑机接口、运动意图脑电信号特征提取等方面的研究工作
许敏鹏,天津大学医学工程与转化医学研究院讲席教授,主要从事脑机接口,神经信号处理和神经调控等方面的研究工作
顾晓松,中国工程院院士,天津大学医学部主任,主要从事组织工程神经与神经再生等方面的研究工作
基金资助:
*国家自然科学基金项目(62206198);国家自然科学基金项目(62122059)

WANG Kun, HUANG Yining, XU Minpeng, GU Xiaosong, MING Dong

Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin 300072, China

Received:2024-05-06 Online:2024-05-25 Published:2024-05-31

摘要/Abstract

摘要：

脑机接口(Brain-Computer Interface,BCI)是人类大脑与外界环境之间的直接信息交流通路,在人体运动功能康复、替代、增强等多方面日益凸显其重要科学意义与应用价值。基于运动意图的脑机接口范式作为最自然的脑机交互方式,受到研究者的广泛关注。对运动预备阶段的脑电特征进行解码能够使BCI响应速度更快、灵活度更高。然而,该阶段的脑电特征信号微弱,难以高效识别。针对上述挑战,围绕运动预备阶段脑电低频时域空间侧向性特征强化开展研究,设计了左右手自主按键运动任务,针对低频运动相关皮质电位特征,结合判别空间模式与任务相关成分分析两种算法,提出了一种新型复合空间模式滤波算法。实验结果显示,该算法平均识别正确率可达78.56%,优于已有文献报道,可为基于运动意图的高效脑机交互提供理论依据与技术支持。

关键词: 运动预备, 脑电, 脑机接口, 空间滤波

Abstract:

Brain-computer interface (BCI) establishes a direct information communication channel between the brain and the external environment, which has increasingly highlighted its important scientific significance and application value in many aspects of human motor function rehabilitation, replacement and enhancement. As the most natural brain-computer interaction mode, BCI paradigm based on movement intention has been widely concerned by researchers. The decoding of pre-movement EEG patterns can make BCI more responsive and flexible. However, the EEG features at this stage are weak and difficult to recognize efficiently. Based on the above challenges, research is focused on the enhancement of temporal and spatial lateral characteristics of pre-movement EEG in low frequency. Aleft and right hand self-paced keystroke task is designed, and a new composite spatial filtering algorithm is proposed by combining discriminative canonical pattern matching (DCPM) and task-related component analysis (TRCA). The results show that the average accuracy of EEG signal recognition under this algorithm can reach 78.56%, which is better than previous literature reports, and can provide theoretical basis and technical support for efficient brain-computer interaction based on motion intention.

Key words: movement preparation, electroencephalography, brain-computer interface, spatial filter

中图分类号:

R318

王坤, 黄依宁, 许敏鹏, 顾晓松, 明东. 用于运动准备诱发脑电响应识别的新型复合空间滤波算法研究^*[J]. 信息通信技术与政策, 2024, 50(5): 2-11.

WANG Kun, HUANG Yining, XU Minpeng, GU Xiaosong, MING Dong. Research on novel compound spatial filter algorithm for recognition of pre-movement EEG patterns[J]. Information and Communications Technology and Policy, 2024, 50(5): 2-11.

导出引用管理器 EndNote|Ris|BibTeX

链接本文:

http://ictp.caict.ac.cn/CN/10.12267/j.issn.2096-5931.2024.05.001

http://ictp.caict.ac.cn/CN/Y2024/V50/I5/2

图/表 8

参考文献 12

[1]	WOLPAW J, WOLPAW E W. Brain-computer interfaces: principles and practice[M]. New York: Oxford University Press, 2012.
[2]	WOLPAW J R, BIRBAUMER N, MCFARLAND D J, et al. Brain-computer interfaces for communication and control[J]. Clinical Neurophysiology, 2002, 113(6):767-791. doi: 10.1016/s1388-2457(02)00057-3 pmid: 12048038
[3]	BLANKERTZ B, CURIO G, MÜLLER K R. Classifying single trial EEG: towards brain computer interfacing[M]//. Advances in Neural Information Processing Systems. Burlington: Morgan Kaufmann Publishers, 2002:157-164.
[4]	XIAO R, DING L. EEG resolutions in detecting and decoding finger movements from spectral analysis[J]. Frontiers in Neuroscience, 2015, 9:308. doi: 10.3389/fnins.2015.00308 pmid: 26388720
[5]	WANG Y, ZHANG Z, LI Y, et al. BCI competition 2003-data set IV: an algorithm based on CSSD and FDA for classifying single-trial EEG[J]. IEEE Transactions on Biomedical Engineering, 2004, 51(6):1081-1086.
[6]	RAMOSER H, MULLER-GERKING J, PFURTSCHELLER G. Optimal spatial filtering of single trial EEG during imagined hand movement[J]. IEEE Transactions on Rehabilitation Engineering, 2000, 8(4):441-446. doi: 10.1109/86.895946 pmid: 11204034
[7]	许敏鹏, 王有良, 梅杰, 等. 非侵入式异步脑机接口技术研究综述[J]. 信号处理, 2023, 39(8):1386-1398.
[8]	ABOU ZEID E, SERESHKEH A R, CHAU T. A pipeline of spatio-temporal filtering for predicting the laterality of self-initiated fine movements from single trial readiness potentials[J]. Journal of Neural Engineering, 2016, 13(6):066012.
[9]	XIAO X, XU M, JIN J, et al. Discriminative canonical pattern matching for single-trial classification of ERP components[J]. IEEE Transactions on Biomedical Engineering, 2020, 67(8):2266-2275.
[10]	WANG K, XU M, WANG Y, et al. Enhance decoding of pre-movement EEG patterns for brain-computer interfaces[J]. Journal of Neural Engineering, 2020, 17(1):016033.
[11]	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.
[12]	XU M, XIAO X, WANG Y, et al. A brain-computer interface based on miniature-event-related potentials induced by very small lateral visual stimuli[J]. IEEE Transactions on Biomedical Engineering, 2018, 65(5):1166-1175.

被试	delta	theta	alpha	beta	all
S1	79.50%	65.00%	56.75%	55.00%	81.00%
S2	82.00%	60.00%	53.25%	55.00%	75.50%
S3	77.75%	63.25%	58.25%	54.00%	79.25%
S4	63.50%	50.75%	54.75%	51.00%	64.50%
S5	79.25%	66.25%	51.50%	54.75%	80.00%
S6	53.75%	52.50%	50.00%	53.25%	55.50%
S7	76.25%	77.25%	56.25%	56.75%	76.75%
S8	79.50%	66.00%	56.75%	55.00%	76.75%
S9	74.50%	69.25%	51.50%	49.75%	74.50%
S10	75.50%	73.50%	59.50%	58.75%	79.25%
S11	77.25%	59.00%	59.50%	53.00%	71.75%
S12	77.75%	71.50%	63.00%	59.25%	79.00%
Mean	74.71%	64.52%	55.92%	54.63%	74.48%
Std.	8.05%	8.01%	3.88%	2.78%	7.49%

被试	delta	theta	alpha	beta	all
S1	79.50%	65.00%	56.75%	55.00%	81.00%
S2	82.00%	60.00%	53.25%	55.00%	75.50%
S3	77.75%	63.25%	58.25%	54.00%	79.25%
S4	63.50%	50.75%	54.75%	51.00%	64.50%
S5	79.25%	66.25%	51.50%	54.75%	80.00%
S6	53.75%	52.50%	50.00%	53.25%	55.50%
S7	76.25%	77.25%	56.25%	56.75%	76.75%
S8	79.50%	66.00%	56.75%	55.00%	76.75%
S9	74.50%	69.25%	51.50%	49.75%	74.50%
S10	75.50%	73.50%	59.50%	58.75%	79.25%
S11	77.25%	59.00%	59.50%	53.00%	71.75%
S12	77.75%	71.50%	63.00%	59.25%	79.00%
Mean	74.71%	64.52%	55.92%	54.63%	74.48%
Std.	8.05%	8.01%	3.88%	2.78%	7.49%

被试	delta	theta	alpha	beta	all
S1	75.25%	67.75%	59.50%	54.50%	76.00%
S2	70.75%	58.75%	54.25%	56.75%	72.00%
S3	78.00%	59.25%	58.25%	56.75%	77.00%
S4	65.50%	50.75%	54.00%	53.00%	65.00%
S5	78.75%	65.25%	56.00%	56.50%	79.50%
S6	53.25%	57.75%	53.75%	51.50%	50.25%
S7	72.25%	74.25%	56.50%	54.00%	75.75%
S8	79.00%	67.25%	57.50%	54.25%	75.25%
S9	66.25%	62.50%	47.75%	52.00%	67.75%
S10	75.00%	64.25%	56.00%	52.00%	77.75%
S11	75.25%	59.50%	54.00%	55.50%	71.75%
S12	74.75%	66.00%	60.00%	58.25%	75.25%
Mean	72.00%	62.77%	55.63%	54.58%	71.94%
Std.	7.37%	6.06%	3.28%	2.20%	8.01%

被试	delta	theta	alpha	beta	all
S1	75.25%	67.75%	59.50%	54.50%	76.00%
S2	70.75%	58.75%	54.25%	56.75%	72.00%
S3	78.00%	59.25%	58.25%	56.75%	77.00%
S4	65.50%	50.75%	54.00%	53.00%	65.00%
S5	78.75%	65.25%	56.00%	56.50%	79.50%
S6	53.25%	57.75%	53.75%	51.50%	50.25%
S7	72.25%	74.25%	56.50%	54.00%	75.75%
S8	79.00%	67.25%	57.50%	54.25%	75.25%
S9	66.25%	62.50%	47.75%	52.00%	67.75%
S10	75.00%	64.25%	56.00%	52.00%	77.75%
S11	75.25%	59.50%	54.00%	55.50%	71.75%
S12	74.75%	66.00%	60.00%	58.25%	75.25%
Mean	72.00%	62.77%	55.63%	54.58%	71.94%
Std.	7.37%	6.06%	3.28%	2.20%	8.01%

被试	DCPM	TRCA	新型复合空间模式滤波算法
S1	80.75%	78.25%	82.50%
S2	77.50%	71.25%	79.75%
S3	77.50%	76.75%	79.25%
S4	64.25%	65.00%	68.00%
S5	82.75%	78.75%	84.50%
S6	56.25%	55.50%	61.25%
S7	77.75%	77.00%	83.25%
S8	79.00%	75.75%	82.00%
S9	76.75%	68.75%	79.00%
S10	81.00%	75.50%	82.00%
S11	76.25%	72.50%	78.00%
S12	80.75%	76.75%	83.25%
Mean	75.88%	72.65%	78.56%
Std.	7.75%	6.80%	6.95%

用于运动准备诱发脑电响应识别的新型复合空间滤波算法研究^*

Research on novel compound spatial filter algorithm for recognition of pre-movement EEG patterns

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 12

相关文章 11

编辑推荐

Metrics

本文评价

[1]	成苈委, 张倩, 梁栗炎, 周洁, 于青民, 黄俊杰. 面向脑机接口的高速通信需求及相关应用场景[J]. 信息通信技术与政策, 2024, 50(5): 12-17.
[2]	白睿钰, 王炫棋, 张梓墨, 吉博文. 皮层微创脑机接口传感器发展现状与趋势^*[J]. 信息通信技术与政策, 2024, 50(5): 18-25.
[3]	王战阳, 张洪欣, 杨晨. 基于子空间方法的任务依赖脑电实时压缩算法研究^*[J]. 信息通信技术与政策, 2024, 50(5): 26-33.
[4]	胡碧荣, 王晓东, 王浩冲, 史改革. 面向脑机接口测试的高精度脑电信号模拟发生系统设计与实现^*[J]. 信息通信技术与政策, 2024, 50(5): 34-40.
[5]	董越, 刘可, 王涛. 基于混合模态的脑机接口技术应用:神经康复新方向[J]. 信息通信技术与政策, 2024, 50(5): 41-46.
[6]	查玮, 杨雨潇, 胡胜蓉. 浙江省脑机接口产业发展趋势研究^*[J]. 信息通信技术与政策, 2024, 50(5): 47-53.
[7]	徐明. 脑机接口技术的伦理挑战及其理性规制研究[J]. 信息通信技术与政策, 2024, 50(5): 54-59.
[8]	梁栗炎, 孔姝懿, 张倩, 成苈委, 周洁, 孙艺珂. 脑机接口的范式、算法与编解码概念探讨与研究[J]. 信息通信技术与政策, 2024, 50(5): 61-70.
[9]	周洁, 王淳佳, 张倩. 专利视角下植入式脑机接口电极技术发展趋势分析[J]. 信息通信技术与政策, 2023, 49(3): 61-67.
[10]	李静雯, 王秀梅. 脑机接口技术在医疗领域的应用[J]. 信息通信技术与政策, 2021, 47(2): 87-91.
[11]	高越. 美国脑机接口技术研究及应用进展*[J]. 信息通信技术与政策, 2020, 46(12): 75-80.