Cross-subject fusion based on time-weighting canonical correlation analysis in SSVEP-BCIs

Sun, Yonghe; Ding, Wenzheng; Liu, Xiaolin; Zheng, Dezhi; Chen, Xinlei; Hui, Qianxin; Na, Rui; Wang, Shuai

doi:10.1016/j.measurement.2022.111524

Cited by 15 publications

(5 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To demonstrate the performance of PMF-CNN, this subsection compared the state-of-the-art UL-based methods (ms-eCCA [14], CORRCA [30], and TSCORRCA [30]) or SL-based methods (DNN [24], FBCNN [7], Conv-CA [16], and MTL [17]) with our proposed model. During the experimental procedure, the data length for SSVEP-EEG was established within the range of 0.2 to 1.0 seconds.…”

Section: Quantified Analysis Of Results On Benchmarkmentioning

confidence: 99%

“…Our method achieved an accuracy of 99.37% at 1.0, evidently demonstrating superior performance compared to other approaches. ms-eCCA [14] was an extended CCA-based algorithm which was widely applied to identify SSVEP-EEG signals. The algorithm learned calibration data across multiple stimuli on top of the original CCA to generate more data, effectively solving the challenge of smaller data sizes.…”

Section: Quantified Analysis Of Results On Benchmarkmentioning

confidence: 99%

“…Another large publicly available SSVEP dataset, BETA, was employed for evaluation to further validate PMF-CNN robustness and adaptability. The baseline methods opted for FBCCA [25], ms-eCCA [14], ITCCA [32], and TRCA [31] and SL-based methods: DNN [24] and Conv-CA [16]. Unlike Benchmark dataset, BETA has more data.…”

Section: Quantified Analysis Of Results On Betamentioning

confidence: 99%

“…Shao et al [13] incorporated local time information constraints and delay embedding constraints into the design of multivariate synchronization index-based algorithms to further improve the algorithmic classification performance of SSVEP signals. To solve the problem of lower accuracies of SSVEP recognition in short time, Sun et al [14] proposed a temporal domain enhancement method based on time-weighted CCA (TWCCA). This method integrated all features and no longer targeted specific number of targets, thus not requiring excessive calibration data.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

PMF-CNN: parallel multi-band fusion convolutional neural network for SSVEP-EEG decoding

Yang,

Zhao,

et al. 2024

Biomed. Phys. Eng. Express

View full text Add to dashboard Cite

Steady-state visual evoked potential (SSVEP) is a key technique of electroencephalography (EEG)-based brain-computer interfaces (BCI), which has been widely applied to neurological function assessment and postoperative rehabilitation. However, accurate decoding of the user's intended based on the SSVEP-EEG signals is challenging due to the low signal-to-noise ratio and large individual variability of the signals. To address these issues, we proposed a parallel multi-band fusion convolutional neural network (PMF-CNN). Multi frequency band signals were served as the input of PMF-CNN to fully utilize the time-frequency information of EEG. Three parallel modules, spatial self-attention (SAM), temporal self-attention (TAM), and squeeze-excitation (SEM), were proposed to automatically extract multi-dimensional features from spatial, temporal, and frequency domains, respectively. A novel spatial-temporal-frequency representation were designed to capture the correlation of electrode channels, time intervals, and different sub-harmonics by using SAM, TAM, and SEM, respectively. The three parallel modules operate independently and simultaneously. A four layers CNN classification module was designed to fuse parallel multi-dimensional features and achieve the accurate classification of SSVEP-EEG signals. The PMF-CNN was further interpreted by using brain functional connectivity analysis. The proposed method was validated using two large publicly available datasets. After trained using our proposed dual-stage training pattern, the classification accuracies were 99.37% and 93.96%, respectively, which are superior to the current state-of-the-art SSVEP-EEG classification algorithms. The algorithm exhibits high classification accuracy and good robustness, which has the potential to be applied to postoperative rehabilitation.

show abstract

Section: Quantified Analysis Of Results On Benchmarkmentioning

confidence: 99%

Section: Quantified Analysis Of Results On Benchmarkmentioning

confidence: 99%

Section: Quantified Analysis Of Results On Betamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

PMF-CNN: parallel multi-band fusion convolutional neural network for SSVEP-EEG decoding

Yang,

Zhao,

et al. 2024

Biomed. Phys. Eng. Express

View full text Add to dashboard Cite

show abstract

“…Another way is to utilize the EEG data from existing subjects to facilitate the algorithm implementation for a new subject. For example, a cross-subject fusion method was proposed in [17] to efficiently shorten the calibration time of the target user using the data from other subjects. A cross-subject assistance framework was introduced in [18] to enhance the robustness of SSVEP recognition by maximizing inter-and intrasubject correlation.…”

Section: Introductionmentioning

confidence: 99%

An efficient CNN-LSTM network with spectral normalization and label smoothing technologies for SSVEP frequency recognition

2022

View full text Add to dashboard Cite

Objective. Steady-state visual evoked potentials(SSVEPs) based braincomputer interface(BCI) has received great interests owing to the high information transfer rate(ITR) and available large number of targets. However, the performance of frequency recognition methods heavily depends on the amount of the calibration data for intra-subject classiﬁcation. Some research adopted the deep learning(DL) algorithm to conduct the inter-subject classiﬁcation, which could reduce the calculation procedure, but the performance still has large room to improve compared with the intra-subject classiﬁcation. Approach. To address these issues, we proposed an eﬃcient SSVEP DL NETwork (termed SSVEPNET) based on 1D convolution and long short-term memory (LSTM) module. To enhance the performance of SSVEPNT, we adopted the spectral normalization and label smoothing technologies during implementing the network architecture. We evaluated the SSVEPNET and compared it with other methods for the intra- and inter-subject classiﬁcation under diﬀerent conditions, i.e., two datasets, two time-window lengths (1 s and 0.5 s), three sizes of training data. Main results. Under all the experimental settings, the proposed SSVEPNET achieved the highest average accuracy for the intra- and inter-subject classiﬁcation on the two SSVEP datasets, when compared with other traditional and DL baseline methods. Signif icance. The extensive experimental results demonstrate that the proposed DL model holds promise to enhance frequency recognition performance in SSVEP-based BCIs. Besides, the mixed network structures with CNN and LSTM, and the spectral normalization and label smoothing could be useful optimization strategies to design eﬃcient models for EEG data.

show abstract

Improving CCA Algorithms on SSVEP Classification with Reinforcement Learning Based Temporal Filtering

Ou,

Do,

Tran

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Cross-subject fusion based on time-weighting canonical correlation analysis in SSVEP-BCIs

Cited by 15 publications

References 29 publications

PMF-CNN: parallel multi-band fusion convolutional neural network for SSVEP-EEG decoding

PMF-CNN: parallel multi-band fusion convolutional neural network for SSVEP-EEG decoding

An efficient CNN-LSTM network with spectral normalization and label smoothing technologies for SSVEP frequency recognition

Improving CCA Algorithms on SSVEP Classification with Reinforcement Learning Based Temporal Filtering

Contact Info

Product

Resources

About