基于FBCCA和ITCCA的SSVEP融合识别算法

The SSVEP fusion recognition algorithm based on FBCCA and ITCCA

摘要

稳态视觉诱发电位(steady-state visual evoked potential,SSVEP)经过视觉刺激后由大脑的枕叶区域产生,具有特征明显、信号稳定和较高信噪比等特点。对SSVEP目标的识别以及如何提高SSVEP的分类准确率,是近年来基于SSVEP的脑-机接口的热点问题。经典的典型相关分析(canonical correlation analysis,CCA)算法虽然能够识别出SSVEP,但是存在许多的缺点,识别的效果有限。对于CCA的改进算法,如滤波器组典型相关分析(filter band canonical correlation analysis,FBCCA)和基于个体模版的典型相关分析(individual template-based canonical correlation analysis,ITCCA),能够有效地提升SSVEP目标的分类性能。通过比较和分析这两种算法的改进思路,本文提出一种新的SSVEP识别算法,并将该算法与FBCCA和ITCCA算法进行对比,实验的结果表明该算法在不同的条件下(谐波数、时间窗口长度、滤波器组设计方案)均具有优秀的识别效果。研究结果为SSVEP的识别提供了新的解决思路,对基于SSVEP的脑-机接口的研究具有十分重要的作用。

Abstract

Steady-state visual evoked potential (SSVEP) is generated by the occipital region of the brain after visual stimulation, which has the characteristics of obvious characteristics, stable signal and high signal-to-noise ratio. The classification and recognition of SSVEP and how to improve the recognition accuracy of SSVEP are the core issues of SSVEP-based brain-computer interface. Although the traditional canonical correlation analysis (CCA) algorithm can identify SSVEP, there are many shortcomings and the recognition effect is limited. For the improved algorithms of CCA, such as filter band canonical correlation analysis (FBCCA) and individual template-based canonical correlation analysis (ITCCA), could effectively improve the classification accuracy of SSVEP. By comparing and analyzing the improved ideas of the two algorithms, this paper proposes a new SSVEP recognition algorithm, and compares the algorithm with FBCCA and ITCCA algorithm. The experimental results show that the algorithm has excellent recognition effect under different conditions (harmonic number, time window length, filter bank design). This study provides a new solution for the recognition of SSVEP, which is of great significance for the research and development of SSVEP-based brain-computer interface.

关键词

脑-机接口 / 稳态视觉诱发电位 / 典型相关分析 / SSVEP识别算法

Key words

brain-computer interface / steady-state visual evoked potential / canonical correlation analysis / SSVEP recognition algorithm

[1] Moore M M. Real-world applications for brain-computer interface technology[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2003,11(2):162-165.
[2] Dhiman R.Machine learning techniques for electroencephalogram based brain-computer interface: a systematic literature review[J]. Measurement: Sensors, 2023: 100823.
[3] King B J, Read G J M, Salmon P M. Identifying risk controls for future advanced brain-computer interfaces: a prospective risk assessment approach using work domain analysis[J]. Applied Ergonomics, 2023, 111: 104028.
[4] Williams S C, Horsfall H L, Funnell J P, et al. Neurosurgical team acceptability of brain-computer interfaces: a two-stage international cross-sectional survey[J]. World Neurosurgery, 2022, 164: e884-e898.
[5] Velasco-álvarez F, Fernández-rodríguez Á, Ron-angevin R. Brain-computer interface (BCI)-generated speech to control domotic devices[J]. Neurocomputing, 2022, 509: 121-136.
[6] Yuan X, Zhang L, Sun Q, et al. A novel command generation method for SSVEP-based BCI by introducing SSVEP blocking response[J]. Computers in Biology and Medicine, 2022, 146: 105521.
[7] Tabanfar Z, Ghassemi F, Moradi M H. A subject-independent SSVEP-based BCI target detection system based on fuzzy ordering of EEG task-related Components[J].Biomedical Signal Processing and Control, 2023, 79: 104171.
[8] Tang Z, Wang X, Wu J, et al. A BCI painting system using a hybrid control approach based on SSVEP and P300[J]. Computers in Biology and Medicine, 2022, 150: 106118.
[9] Jia C, Gao X, Hong B, et al. Frequency and phase mixed coding in SSVEP-based brain-computer interface[J]. IEEE Transactions on Biomedical Engineering, 2010, 58(1): 200-206.
[10] Na R, Hu C, Sun Y, et al. An embedded lightweight SSVEP-BCI electric wheelchair with hybrid stimulator[J]. Digital Signal Processing, 2021, 116: 103101.
[11] Ma P, Dong C, Lin R, et al. Effect of local network characteristics on the performance of the SSVEP brain-computer interface[J]. IRBM, 2023, 44(4):100781.
[12] Wang K, Qiu S, Wei W, et al. A multimodal approach to estimating vigilance in SSVEP-based BCI[J]. Expert Systems with Applications, 2023, 225: 120177.
[13] Chen J, Zhang Y, Pan Y, et al. A Transformer-based deep neural network model for SSVEP classification[J]. Neural Networks, 2023, 164: 521-534.
[14] Wang Y, Wang R, Gao X, et al. A practical VEP-based brain-computer interface[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2006, 14(2): 234-240.
[15] Bin G, Gao X, 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.
[16] Chen X, Wang Y, Gao S, et al. Filter bank canonical correlation analysis for implementing a high-speed SSVEP-based brain-computer interface[J]. Journal of Neural Engineering, 2015, 12(4): 046008.
[17] Saidi P, Vosoughi A, Atia G. Detection of brain stimuli using Ramanujan periodicity transforms[J]. Journal of Neural Engineering, 2019, 16(3): 036021.
[18] Wang H, Sun Y, Wang F, et al. Cross-subject assistance: inter- and intra-subject maximal correlation for enhancing the performance of SSVEP-based BCIs[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2021, 29: 517-526.
[19] Zhao S, Wang R, Bao R, et al. Spatially-coded SSVEP BCI without pre-training based on FBCCA[J]. Biomedical Signal Processing and Control, 2023, 84: 104717.
[20] Kwon J, Im C H. Novel Signal-to-Signal translation method based on StarGAN to generate artificial EEG for SSVEP-based brain-computer interfaces[J]. Expert Systems with Applications, 2022, 203: 117574.
[21] Wang Y, Nakanishi M, Wang Y T, et al. Enhancing detection of steady-state visual evoked potentials using individual training data[C]//2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Chicago, IL, USA: IEEE, 2014: 3037-3040.
[22] 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, 2016, 25(10): 1746-1752.

基金资助

国防基础科研计划(JCKY2022410C002)