Please wait a minute...
浙江大学学报(工学版)
Journal of ZheJiang University (Engineering Science)  2025, Vol. 59 Issue (12): 2472-2482    DOI: 10.3785/j.issn.1008-973X.2025.12.002
    
Steady-state visual evoked potential signal recognition based on cross-subject neighboring stimulus learning
Fan DU(),Yong WANG,Jun YAN,Hongxiang GUO*()
School of Mechanical Engineering and Electronic Information, China University of Geosciences, Wuhan 430074, China
Download: HTML     PDF(3291KB) HTML
Export: BibTeX | EndNote (RIS)      

Abstract  

A cross-subject neighboring stimulus learning method for steady-state visual evoked potential (SSVEP) signal recognition was proposed to address the performance limitations of SSVEP brain-computer interface (BCI) systems under conditions of insufficient calibration trials. Target-subject calibration trials were combined with sine-cosine reference signals, and the sine-cosine reference signal neighboring stimulus fundamental and harmonic information was effectively incorporated into the target-subject task-relevant information through the SAME data augmentation technique. On this basis, the fundamental and harmonic characteristics of the signal were extracted using canonical correlation analysis (CCA), and the task-related information of the signal was extracted in combination with task-related component analysis (TRCA). The spatial filter was optimized by analyzing the correlations within the target subject, between the target subject and the source subject, and between the target subject and the reference signal. Common frequency information from neighboring stimulus was extracted from both the target and source subjects, and target recognition was achieved through template matching. The experimental results showed that the proposed method achieved recognition accuracies of 80.17% and 70.83% on Benchmark and BETA datasets, respectively, using only one calibration trial, and the recognition time was only 0.6 seconds, which was an improvement of 16.75 percentage points and 15.85 percentage points, respectively, compared with the current state-of-the-art cross-subject learning method, eTransRCA. These results demonstrated the advantages of improving recognition accuracy and shortening calibration trial time, validating the effectiveness of the method.

Key words： brain-computer interface      steady-state visual evoked potential (SSVEP)      neighboring stimulus learning      transfer learning      cross-subject     
Received: 18 December 2024      Published: 25 November 2025
CLC:  TN 911.7  
Fund:  国家自然科学基金资助项目（61973283）.
Corresponding Authors: Hongxiang GUO     E-mail: 2498117298@qq.com;guohongxiang@cug.edu.cn
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Fan DU
Yong WANG
Jun YAN
Hongxiang GUO
Cite this article:

Fan DU,Yong WANG,Jun YAN,Hongxiang GUO. Steady-state visual evoked potential signal recognition based on cross-subject neighboring stimulus learning. Journal of ZheJiang University (Engineering Science), 2025, 59(12): 2472-2482.

URL:

https://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2025.12.002     OR     https://www.zjujournals.com/eng/Y2025/V59/I12/2472


基于跨受试者邻近刺激学习的稳态视觉诱发电位信号识别

为了解决稳态视觉诱发电位（SSVEP）脑-机接口（BCI）系统在校准试验不足时的性能限制，提出跨受试者邻近刺激学习的SSVEP信号识别方法. 该方法结合目标受试者校准试验与正余弦参考信号，通过SAME数据增强方法，将正余弦参考信号邻近刺激基波和谐波信息有效融入目标受试者任务相关信息中. 在此基础上，通过分析目标受试者内、目标受试者与源受试者之间以及目标受试者与参考信号之间的相关性，利用典型相关分析（CCA）提取信号的基波和谐波特性，并结合任务相关成分分析（TRCA）提取信号的任务相关信息，从而优化空间滤波器. 从目标受试者和源受试者中提取邻近刺激公共频率信息，最终通过模板匹配实现目标识别. 实验结果表明，在仅使用一次校准试验的情况下，所提出的方法在Benchmark和BETA数据集上的识别准确率分别达到了80.17%和70.83%，且识别时间仅为0.6 s，相较于当前最先进的跨受试者学习方法eTransRCA，分别提高了16.75、15.85个百分点. 结果证明了该方法在提高识别准确率和缩短校准试验时间方面的优势，验证了其有效性.


关键词： 脑-机接口,  稳态视觉诱发电位（SSVEP）,  邻近刺激学习,  迁移学习,  跨受试者 
Fig.1 Flowchart for obtaining spatial filter
Fig.2 Comparison of classification accuracy and ITR against different data lengths and numbers of calibration trials
Fig.3 Feature values obtained by eTransRCA and proposed method from an example subject
Fig.4 Comparison between multi-stimulus learning and neighboring stimulus learning
Fig.5 Classification accuracy against different numbers of calibration trials and source subjects
Fig.6 Comparison of classification accuracy against different numbers of calibration trials
Fig.7 Distribution of classification accuracy across subjects under different algorithms
Fig.8 Definition of neighboring stimulus to target stimulus
Fig.9 Classification accuracy against different numbers of neighboring stimulus
Fig.10 Comparison of classification accuracy against different data lengths
情况相关系数选择P/%
$ {{r}}_{1} $$ {{r}}_{2} $$ \dfrac{1}{3}({{r}}_{3}+{{r}}_{4}+{{r}}_{5}) $BenchmarkBETA
(a)√√√80.1770.83
(b)√√?77.6267.74
(c)√?√70.2161.78
(d)?√√79.1368.43
Tab.1 Ablation studies on different combinations of correaltion coefficients
选择方法P/%
Nt = 1Nt = 2Nt = 3Nt = 4Nt = 5
随机选择70.3476.4079.5480.1381.34
有经验选择71.4378.1580.6381.5482.82
p值************
Tab.2 Comparison of classification accuracy between two source subject selection methods
[1]   RAVI A, LU J, PEARCE S, et al Enhanced system robustness of asynchronous BCI in augmented reality using steady-state motion visual evoked potential[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2022, 30: 85- 95
doi: 10.1109/TNSRE.2022.3140772
[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
[3]   YADAV D, YADAV S, VEER K A comprehensive assessment of brain computer interfaces: recent trends and challenges[J]. Journal of Neuroscience Methods, 2020, 346: 108918
doi: 10.1016/j.jneumeth.2020.108918
[4]   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
doi: 10.1088/1741-2560/6/4/046002
[5]   YIN E, ZHOU Z, JIANG J, et al A speedy hybrid BCI spelling approach combining P300 and SSVEP[J]. IEEE Transactions on Bio-Medical Engineering, 2014, 61 (2): 473- 483
doi: 10.1109/TBME.2013.2281976
[6]   CHEN X, WANG Y, NAKANISHI M, et al High-speed spelling with a noninvasive brain-computer interface[J]. Proceedings of the National Academy of Sciences of the United States of America, 2015, 112 (44): 6058- 6067
[7]   PEI W, WU X, ZHANG X, et al A pre-gelled EEG electrode and its application in SSVEP-based BCI[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2022, 30: 843- 850
doi: 10.1109/TNSRE.2022.3161989
[8]   CHENG M, GAO X, GAO S, et al Design and implementation of a brain-computer interface with high transfer rates[J]. IEEE Transactions on Bio-Medical Engineering, 2002, 49 (10): 1181- 1186
doi: 10.1109/TBME.2002.803536
[9]   陈熙来, 丛佩超, 万东宝, 等 基于SSVEP信号的下肢外骨骼机器人控制系统研究[J]. 机电信息, 2024, (7): 42- 45
CHEN Xilai, CONG Peichao, WAN Dongbao, et al Research on lower limb exoskeleton robot control system based on SSVEP signals[J]. Mechanical and Electrical Information, 2024, (7): 42- 45
[10]   CHAI X, ZHANG Z, GUAN K, et al A hybrid BCI-controlled smart home system combining SSVEP and EMG for individuals with paralysis[J]. Biomedical Signal Processing and Control, 2020, 56: 101687
doi: 10.1016/j.bspc.2019.101687
[11]   REZEIKA A, BENDA M, STAWICKI P, et al Brain-computer interface spellers: a review[J]. Brain Sciences, 2018, 8 (4): 57
doi: 10.3390/brainsci8040057
[12]   MÜLLER-PUTZ G R, PFURTSCHELLER G Control of an electrical prosthesis with an SSVEP-based BCI[J]. IEEE Transactions on Bio-Medical Engineering, 2008, 55 (1): 361- 364
doi: 10.1109/TBME.2007.897815
[13]   FRIMAN O, VOLOSYAK I, GRÄSER A Multiple channel detection of steady-state visual evoked potentials for brain-computer interfaces[J]. IEEE Transactions on Bio-Medical Engineering, 2007, 54 (4): 742- 750
doi: 10.1109/TBME.2006.889160
[14]   ZHANG Y, XU P, CHENG K, et al Multivariate synchronization index for frequency recognition of SSVEP-based brain-computer interface[J]. Journal of Neuroscience Methods, 2014, 221: 32- 40
doi: 10.1016/j.jneumeth.2013.07.018
[15]   LIN Z, ZHANG C, WU W, et al Frequency recognition based on canonical correlation analysis for SSVEP-based BCIs[J]. IEEE Transactions on Biomedical Engineering, 2006, 53 (12): 2610- 2614
doi: 10.1109/TBME.2006.886577
[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
doi: 10.1088/1741-2560/12/4/046008
[17]   ZHANG Y, ZHOU G, JIN J, et al Frequency recognition in SSVEP-based BCI using multiset canonical correlation analysis[J]. International Journal of Neural Systems, 2014, 24 (4): 1450013
doi: 10.1142/S0129065714500130
[18]   CHEN X, WANG Y, NAKANISHI M, et al High-speed spelling with a noninvasive brain-computer interface[J]. Proceedings of the National Academy of Sciences of the United States of America, 2015, 112 (44): 6058- 6067
[19]   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 Bio-Medical Engineering, 2018, 65 (1): 104- 112
doi: 10.1109/TBME.2017.2694818
[20]   LIU B, CHEN X, SHI N, 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
doi: 10.1109/TNSRE.2021.3114340
[21]   KE Y, LIU S, MING D Enhancing SSVEP identification with less individual calibration data using periodically repeated component analysis[J]. IEEE Transactions on Bio-Medical Engineering, 2024, 71 (4): 1319- 1331
doi: 10.1109/TBME.2023.3333435
[22]   HUANG J, YANG P, XIONG B, et al Incorporating neighboring stimuli data for enhanced SSVEP-based BCIs[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 2521109
[23]   WONG C M, WAN F, WANG B, et al Learning across multi-stimulus enhances target recognition methods in SSVEP-based BCIs[J]. Journal of Neural Engineering, 2020, 17 (1): 016026
doi: 10.1088/1741-2552/ab2373
[24]   YUAN P, CHEN X, WANG Y, et al Enhancing performances of SSVEP-based brain–computer interfaces via exploiting inter-subject information[J]. Journal of Neural Engineering, 2015, 12 (4): 046006
doi: 10.1088/1741-2560/12/4/046006
[25]   WAYTOWICH N R, FALLER J, GARCIA J O, et al. Unsupervised adaptive transfer learning for Steady-State Visual Evoked Potential brain-computer interfaces [C]// IEEE International Conference on Systems, Man, and Cybernetics. Budapest: IEEE, 2016: 4135–4140.
[26]   YAN W, WU Y, DU C, et al Cross-subject spatial filter transfer method for SSVEP-EEG feature recognition[J]. Journal of Neural Engineering, 2022, 19 (3): 036008
doi: 10.1088/1741-2552/ac6b57
[27]   YAN W, WU Y, DU C, et al An improved cross-subject spatial filter transfer method for SSVEP-based BCI[J]. Journal of Neural Engineering, 2022, 19 (4): 046028
doi: 10.1088/1741-2552/ac81ee
[28]   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
doi: 10.1109/TNSRE.2021.3057938
[29]   LAN W, WANG R, HE Y, et al Cross domain correlation maximization for enhancing the target recognition of SSVEP-based brain-computer interfaces[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2023, 31: 3545- 3555
doi: 10.1109/TNSRE.2023.3309543
[30]   WEI Q, ZHANG Y, WANG Y, et al A canonical correlation analysis-based transfer learning framework for enhancing the performance of SSVEP-based BCIs[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2023, 31: 2809- 2821
doi: 10.1109/TNSRE.2023.3288397
[31]   CHIANG K J, WEI C S, NAKANISHI M, et al. Cross-subject transfer learning improves the practicality of real-world applications of brain-computer interfaces [C]// 9th International IEEE/EMBS Conference on Neural Engineering. San Francisco: IEEE, 2019: 424–427.
[32]   BIAN R, WU H, LIU B, et al Small data least-squares transformation (sd-LST) for fast calibration of SSVEP-based BCIs[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2022, 31: 446- 455
[33]   LUO R, XU M, ZHOU X, et al Data augmentation of SSVEPs using source aliasing matrix estimation for brain-computer interfaces[J]. IEEE Transactions on Bio-Medical Engineering, 2023, 70 (6): 1775- 1785
doi: 10.1109/TBME.2022.3227036
[34]   MÜLLER M M, HILLYARD S Concurrent recording of steady-state and transient event-related potentials as indices of visual-spatial selective attention[J]. Clinical Neurophysiology, 2000, 111 (9): 1544- 1552
doi: 10.1016/S1388-2457(00)00371-0
[35]   MUN S, PARK M C, PARK S, et al SSVEP and ERP measurement of cognitive fatigue caused by stereoscopic 3D[J]. Neuroscience Letters, 2012, 525 (2): 89- 94
doi: 10.1016/j.neulet.2012.07.049
[36]   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
doi: 10.1109/TNSRE.2016.2627556
[37]   LIU B, HUANG X, WANG Y, et al BETA: a large benchmark database toward SSVEP-BCI application[J]. Frontiers in Neuroscience, 2020, 14: 627
doi: 10.3389/fnins.2020.00627
[1] Guangming WANG,Zhengyao BAI,Shuai SONG,Yue’e XU. Lightweight multimodal data fusion network for auxiliary diagnosis of Alzheimer’s disease[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(1): 39-48.
[2] Ke CHEN,Wenhao ZHANG. Zero-shot object rumor detection based on contrastive learning[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(9): 1790-1800.
[3] Shuhan WU,Dan WANG,Yuanfang CHEN,Ziyu JIA,Yueqi ZHANG,Meng XU. Attention-fused filter bank dual-view graph convolution motor imagery EEG classification[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(7): 1326-1335.
[4] Zihan ZHOU,Xumeng WANG,Wei CHEN. Interactive visualization generation method for time series data based on transfer learning[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(2): 239-246.
[5] Yunlong ZHAO,Minzhe ZHAO,Wenqiang ZHU,Xingyu CHA. Cloud-edge collaborative natural language processing method based on lightweight transfer learning[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(12): 2531-2539.
[6] Yifan ZHOU,Lingwei ZHANG,Zhengdong ZHOU,Zhi CAI,Mengyao YUAN,Xiaoxi YUAN,Zeyi YANG. Classification of group speech imagined EEG signals based on attention mechanism and deep learning[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(12): 2540-2546.
[7] Ling-wei ZHANG,Zheng-dong ZHOU,Yun-fei XU,Jia-wen WANG,Wen-tao JI,Ze-feng SONG. Classification of imagined speech EEG signals based on feature fusion[J]. Journal of ZheJiang University (Engineering Science), 2023, 57(4): 726-734.
[8] Xia HUA,Xin-qing WANG,Ting RUI,Fa-ming SHAO,Dong WANG. Vision-driven end-to-end maneuvering object tracking of UAV[J]. Journal of ZheJiang University (Engineering Science), 2022, 56(7): 1464-1472.
[9] Yi-cong GAO,Yan-kun WANG,Shao-mei FEI,Qiong LIN. Intelligent proofreading method of engineering drawing based on transfer learning[J]. Journal of ZheJiang University (Engineering Science), 2022, 56(5): 856-863, 889.
[10] Xiao-feng FU,Li NIU. Micro-expression classification based on deep convolution and auto-encoder enhancement[J]. Journal of ZheJiang University (Engineering Science), 2022, 56(10): 1948-1957.
[11] Zhi-chao CHEN,Hai-ning JIAO,Jie YANG,Hua-fu ZENG. Garbage image classification algorithm based on improved MobileNet v2[J]. Journal of ZheJiang University (Engineering Science), 2021, 55(8): 1490-1499.
[12] Jin-zhen LIU,Fang-fang YE,Hui XIONG. Recognition of multi-class motor imagery EEG signals based on convolutional neural network[J]. Journal of ZheJiang University (Engineering Science), 2021, 55(11): 2054-2066.
[13] Zhuang KANG,Jie YANG,Hao-qi GUO. Automatic garbage classification system based on machine vision[J]. Journal of ZheJiang University (Engineering Science), 2020, 54(7): 1272-1280.
[14] Zong-li SHEN,Jian-bo YU. Wafer map defect recognition based on transfer learning and deep forest[J]. Journal of ZheJiang University (Engineering Science), 2020, 54(6): 1228-1239.
[15] Xiao-feng FU,Li NIU,Zhuo-qun HU,Jian-jun LI,Qing WU. Deep micro-expression spotting network training based on concept of transition frame[J]. Journal of ZheJiang University (Engineering Science), 2020, 54(11): 2128-2137.