SSVEP Research for Generalized Task-Related Component Analysis #br#

doi:10.3778/j.issn.1002-8331.2208-0089

Abstract

Abstract: Steady-state visual evoked potential brain-computer interface（SSVEP-BCI） has been widely used because of its stability and efficiency. Task-related component analysis（TRCA） is a main method for frequency identification in SSVEP-BCI systems. To solve the problems of?low recognition accuracy in short time window, a generalized task-related component analysis（GTRCA） method is proposed to?maximize the correlation between a single training data, a single test data, and the predefined sines and cosines to improve the character recognition performance of SSVEP-BCI further. The proposed GTRCA method and its filter bank method are evaluated on the benchmark data set of 35 subjects. The results show that the proposed method has obvious advantages over other benchmark algorithms such as TRCA. The highest average classification accuracy is （90.7±4.71）%, and the highest information transfer rate is （188.46±18.69）?bit/min. The research shows that the GTRCA-based method has greater value to achieve the high-performance goal of SSVEP-BCI system.

Key words: brain-computer interface, steady-state visual evoked potential, generalized task-related component analysis

摘要： 稳态视觉诱发电位脑机接口（SSVEP-BCI）因其稳定、高效得到了广泛的应用。任务相关成分分析（TRCA）是一种在SSVEP-BCI系统中识别频率的主要方法。为了解决短时间窗口识别准确率较低等问题，提出了一种广义任务相关成分分析（GTRCA）方法，可最大化单个训练数据、单个测试数据和预定义的正余弦信号这三组数据之间的相关性以进一步提高SSVEP-BCI的字符识别性能。GTRCA方法及其滤波器方法在35名受试者的数据集上进行评估，结果表明该方法的分类性能与TRCA等基准算法相比具有明显优势，平均分类准确率最高达到（90.7±4.71）%，信息传输率最高达到（188.46±18.69）?bit/min。研究表明，基于GTRCA的方法对实现SSVEP-BCI系统的高性能目标具有较大价值。

关键词: 脑机接口, 稳态视觉诱发电位, 广义任务相关成分分析

HAN Dan, DONG Yanqing, GAO Chengxin, CAO Rui. SSVEP Research for Generalized Task-Related Component Analysis #br#[J]. Computer Engineering and Applications, 2023, 59(23): 334-340.

韩丹, 董艳清, 高程昕, 曹锐. 广义任务相关成分分析的SSVEP研究[J]. 计算机工程与应用, 2023, 59(23): 334-340.

References

[1] NORCIA A M，APPELBAUM L G，ALES J M，et al.The steady-state visual evoked potential in vision research：a review[J].Journal of Vision，2015，15（6）：4.
[2] GAO X R，WANG Y J，CHEN X G，et al.Interface，interaction，and intelligence in generalized brain-computer interfaces[J].Trends in Cognitive Science，2021，25（8）：671-684.
[3] MAHMOOD M，MZURIKWAO D，KIM Y S，et al.Fully portable and wireless universal brain-machine interfaces enabled by flexible scalp electronics and deep learning algorithm[J].Nat Mach Intell，2019，1（9）：412-422.
[4] BITTENCOURT-VILLALPANDO M，MAURITS N M.Stimuli and feature extraction algorithms for brain-computer Interfaces：a systematic comparison[J].IEEE Transactions on Neural Systems and Rehabilitation Engineering，2018，26（9）：1669-1679.
[5] NICOLAS-ALONSO L F，GOMEZ-GIL J.Brain computer interfaces，a review[J].Sensors-Basel，2012，12（2）：1211-1279.
[6] 乔敏，张德雨，刘思宇，等.新颖的稳态视觉诱发电位脑机接口系统[J].计算机工程与应用，2021，57（8）：153-159.
QIAO M，ZHANG D Y，LIU S Y，et al.Novel brain-computer interface system based on steady-state visual evoked potential[J].Computer Engineering and Applications，2021，57（8）：153-159.
[7] LI M，HE D，LI C，et al.Brain-computer interface speller based on steady-state visual evoked potential：a review focusing on the stimulus paradigm and performance[J].Brain Sciences，2021，11（4）：450.
[8] CHEN X G，WANG Y J，NAKANISHI M，et al.High-speed spelling with a noninvasive brain-computer interface[J].P Natl Acad Sci USA，2015，112（44）：6058-6067.
[9] CHEN X，WANG Y，GAO S，et al.Filter bank canonical correlation analysis for implementing a high-speed SSVEP-based brain-computer interface[J].J Neural Eng，2015，12（4）：046008.
[10] 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.
[11] TONG C，WANG H，YANG C，et al.Group ensemble learning enhances the accuracy and convenience of SSVEP-based BCIs via exploiting inter-subject information[J].Biomedical Signal Processing and Control，2021，68：102797.
[12] LEE H K，CHOI Y S，et al.Enhancing SSVEP-based brain-computer interface with two-step task-related component analysis[J].Sensors，2021，21（4）：1315.
[13] KIRAN KUMAR G R，RAMASUBBA REDDY M.Designing a sum of squared correlations framework for enhancing SSVEP-based BCIs[J].IEEE Trans Neural Syst Rehabil Eng，2019，27（10）：2044-2050.
[14] WANG Y，CHEN X，GAO X，et al.A benchmark dataset for SSVEP-based brain-computer interfaces[J].IEEE Transactions on Neural Systems and Rehabilitation Engineering，2017，25（10）：1746-1752.
[15] SRINIVASAN R，BIBI F A，NUNEZ P L.Steady-state visual evoked potentials：distributed local sources and wave-like dynamics are sensitive to flicker frequency[J].Brain Topogr，2006，18（3）：167-187.
[16] SUN Q，CHEN M，ZHANG L，et al.Similarity-constrained task-related component analysis for enhancing SSVEP detection[J].Journal of Neural Engineering，2021，18（4）：046080.
[17] ZHANG Y，XIE S Q，WANG H，et al.Data analytics in steady-state visual evoked potential-based brain-computer interface：a review[J].IEEE Sensors Journal，2021，21（2）：1124-1138.
[18] DING W，SHAN J，FANG B，et al.Filter bank convolutional neural network for short time-window steady-state visual evoked potential classification[J].IEEE Transactions on Neural Systems and Rehabilitation Engineering，2021，29：2615-2624.
[19] WOLPAW J R，MCFARLAND D J，VAUGHAN T M，et al.Brain-computer interfaces for communication and control[J].Neurological Rehabilitation，2002：451-459.