Haiqing Yu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Haiqing Yu has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Minpeng Xu
Tianjin University
5 shared publications - Dong Ming
Tianjin University
4 shared publications - Jiayuan Meng
Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin, China
3 shared publications - Tzyy-Ping Jung
University of California San Diego
3 shared publications - Yongzhi Huang
Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin, China
3 shared publications - Baolian Shan
Laboratory of Neural Engineering and Rehabilitation, Department of Intelligent Medical Engineering, College of Academy of Medical Engineering and Translational Medicine, Medical School of Tianjin University, Tianjin University, Tianjin, China
2 shared publications
Latest Publications
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 73 (7) , 2412-2424
Joint-Shrinkage Pattern Matching for Small-Sample and Imbalanced ERP Decoding in Brain–Computer Interfaces
Event-related potential (ERP)-based brain-computer interface (BCI) systems are approaching sub-microvolt-level resolution, enabling detailed decoding of sophisticated cognitive processes. This progress has increased the demand for robust classifiers. Current algorithms encounter two fundamental challenges when decoding ERPs: data scarcity and class imbalance. To address these challenges, we propose a joint-shrinkage pattern matching (JSPM) algorithm consisting of two modules. First, a novel joint-shrinkage spatial filter is constructed by integrating shrinkage-based regularization with the ℓℓ22,pp norm. This regularization approach effectively bridges the gap between complex structured regularization and implementation simplicity, which introduces automated regularization to enhance module robustness under data-scarce conditions. The ℓℓ22,pp-norm provides a flexible feature distance measurement, enabling adaptation to data quality variability. Second, a weighted template matching module mitigates decision boundary shift caused by class imbalance. Using error-related potentials (ErrPs) as representative signals, we validated the algorithm through comprehensive comparisons. JSPM significantly outperformed 14 state-of-the-art classifiers on one self-collected and two public ErrP datasets. With only 40 imbalanced training samples, it achieved up to 14.84% higher average balanced accuracy (bAcc) than competing methods, maintaining a 4.88% average bAcc advantage over its nearest competitor. Notably, JSPM significantly enhanced inter-class discriminability for ErrP features with approximately 1 μV amplitude, achieving a maximum bAcc enhancement of 8.80%compared to deep learning methods. Overall, JSPM effectively addresses small-sample and imbalanced ERP decoding in BCI systems, facilitating the transition from laboratory research to real-world applications.
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 73 (7) , 2412-2424
Joint-Shrinkage Pattern Matching for Small-Sample and Imbalanced ERP Decoding in Brain–Computer Interfaces
Event-related potential (ERP)-based brain-computer interface (BCI) systems are approaching sub-microvolt-level resolution, enabling detailed decoding of sophisticated cognitive processes. This progress has increased the demand for robust classifiers. Current algorithms encounter two fundamental challenges when decoding ERPs: data scarcity and class imbalance. To address these challenges, we propose a joint-shrinkage pattern matching (JSPM) algorithm consisting of two modules. First, a novel joint-shrinkage spatial filter is constructed by integrating shrinkage-based regularization with the ℓℓ22,pp norm. This regularization approach effectively bridges the gap between complex structured regularization and implementation simplicity, which introduces automated regularization to enhance module robustness under data-scarce conditions. The ℓℓ22,pp-norm provides a flexible feature distance measurement, enabling adaptation to data quality variability. Second, a weighted template matching module mitigates decision boundary shift caused by class imbalance. Using error-related potentials (ErrPs) as representative signals, we validated the algorithm through comprehensive comparisons. JSPM significantly outperformed 14 state-of-the-art classifiers on one self-collected and two public ErrP datasets. With only 40 imbalanced training samples, it achieved up to 14.84% higher average balanced accuracy (bAcc) than competing methods, maintaining a 4.88% average bAcc advantage over its nearest competitor. Notably, JSPM significantly enhanced inter-class discriminability for ErrP features with approximately 1 μV amplitude, achieving a maximum bAcc enhancement of 8.80%compared to deep learning methods. Overall, JSPM effectively addresses small-sample and imbalanced ERP decoding in BCI systems, facilitating the transition from laboratory research to real-world applications.
- 20 January 2026
- Published by Elsevier in Learning and Instruction
- Vol. 103
Tracking college student's learning gains using EEG hyperscanning: An interpersonal neuroscience approach development and validation
- 20 January 2026
- Published by Elsevier in Learning and Instruction
- Vol. 103
Tracking college student's learning gains using EEG hyperscanning: An interpersonal neuroscience approach development and validation
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Systems and Rehabilitation Engineering
- Vol. 34, 997-1009
Predicting Attention Decline: An Integrated Beta-Band and SSVEP Approach for Visual Brain–Computer Interfaces
Real-time monitoring of sustained attention fluctuations during continuous complex tasks is vital for enhancing task performance and preventing accidents. Attention modulates neurons in the visual cortex in various ways to improve the visual sensitivity at an attended location. EEG-based brain-computer interfaces (BCIs) offer one of the most effective approaches for monitoring the state of human individuals. Whether transient responses evoked by brief stimuli, steady-state responses elicited by prolonged stimuli, or spontaneous neural oscillations, researchers can extract recognized electrophysiological features that reflect attention levels. However, unimodal features face inherent limitations, such as the low signal-to-noise ratio of transient responses and susceptibility of spontaneous rhythms to electrophysiological interference. Nevertheless, few studies have explored multimodal feature fusion for attention state monitoring. Here, we developed an innovative continuous go/no-go task to concurrently evoke both event-related potential (ERP) and steady-state visual evoked potential (SSVEP), while modulating spontaneous oscillatory activities through attentional engagement. To maximize the attentional modulation effect, we integrated the contrast-response functions of the modulation effect of attention on SSVEP and implemented 12 stimulus contrast levels to identify optimal visual stimulation intensity. Results from 25 subjects demonstrated that the decline in sustained attention during a continuous task was predictable before behavioral mistakes. Classification performance peaked at 31.60% stimulus contrast condition using the fused features combining spontaneous beta-band oscillations and SSVEP responses (average: 74.48%; best: 90.83%). These findings advance the development of more robust real-time attention monitoring systems based on BCI technology.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Systems and Rehabilitation Engineering
- Vol. 34, 997-1009
Open AccessPredicting Attention Decline: An Integrated Beta-Band and SSVEP Approach for Visual Brain–Computer Interfaces
Real-time monitoring of sustained attention fluctuations during continuous complex tasks is vital for enhancing task performance and preventing accidents. Attention modulates neurons in the visual cortex in various ways to improve the visual sensitivity at an attended location. EEG-based brain-computer interfaces (BCIs) offer one of the most effective approaches for monitoring the state of human individuals. Whether transient responses evoked by brief stimuli, steady-state responses elicited by prolonged stimuli, or spontaneous neural oscillations, researchers can extract recognized electrophysiological features that reflect attention levels. However, unimodal features face inherent limitations, such as the low signal-to-noise ratio of transient responses and susceptibility of spontaneous rhythms to electrophysiological interference. Nevertheless, few studies have explored multimodal feature fusion for attention state monitoring. Here, we developed an innovative continuous go/no-go task to concurrently evoke both event-related potential (ERP) and steady-state visual evoked potential (SSVEP), while modulating spontaneous oscillatory activities through attentional engagement. To maximize the attentional modulation effect, we integrated the contrast-response functions of the modulation effect of attention on SSVEP and implemented 12 stimulus contrast levels to identify optimal visual stimulation intensity. Results from 25 subjects demonstrated that the decline in sustained attention during a continuous task was predictable before behavioral mistakes. Classification performance peaked at 31.60% stimulus contrast condition using the fused features combining spontaneous beta-band oscillations and SSVEP responses (average: 74.48%; best: 90.83%). These findings advance the development of more robust real-time attention monitoring systems based on BCI technology.
- Open Access
- 27 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 245-250
Neural Correlates of Proprioceptive Ankle Joint Position Anticipation
- 27 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 245-250
Open AccessNeural Correlates of Proprioceptive Ankle Joint Position Anticipation
- 15 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (1) , 235-247
Interpretable Multi-Branch Architecture for Spatiotemporal Neural Networks and Its Application in Seizure Prediction
Currently, spatiotemporal convolutional neural networks (CNNs) for electroencephalogram (EEG) signals have emerged as promising tools for seizure prediction (SP), which explore the spatiotemporal biomarkers in an epileptic brain. Generally, these CNNs capture spatiotemporal features at single spectral resolution. However, epileptiform EEG signals contain irregular neural oscillations of different frequencies in different brain regions. Therefore, it may be underperforming and uninterpretable for the CNNs without capturing complex spectral properties sufficiently. This study proposed a novel interpretable multi-branch architecture for spatiotemporal CNNs, namely MultiSincNet. On the one hand, the MultiSincNet could directly show the frequency boundaries using the interpretable sinc-convolution layers. On the other hand, it could extract and integrate multiple spatiotemporal features across varying spectral resolutions using parallel branches. Moreover, we also constructed a post-hoc explanation technique for multi-branch CNNs, using the first-order Taylor expansion and chain rule based on the multivariate composite function, which demonstrates the crucial spatiotemporal features learned by the proposed multi-branch spatiotemporal CNN. When combined with the optimal MultiSincNet, ShallowConvNet, DeepConvNet, and EEGWaveNet had significantly improved the subject-specific performance on most metrics. Specifically, the optimal MultiSincNet significantly increased the average accuracy, sensitivity, specificity, binary F1-score, weighted F1-score, and AUC of EEGWaveNet by about 7%, 8%, 7%, 8%, 7%, and 7%, respectively. Besides, the visualization results showed that the optimal model mainly extracts the spectral energy difference from the high gamma band focalized to specific spatial areas as the dominant spatiotemporal EEG feature.
- 15 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (1) , 235-247
Interpretable Multi-Branch Architecture for Spatiotemporal Neural Networks and Its Application in Seizure Prediction
Currently, spatiotemporal convolutional neural networks (CNNs) for electroencephalogram (EEG) signals have emerged as promising tools for seizure prediction (SP), which explore the spatiotemporal biomarkers in an epileptic brain. Generally, these CNNs capture spatiotemporal features at single spectral resolution. However, epileptiform EEG signals contain irregular neural oscillations of different frequencies in different brain regions. Therefore, it may be underperforming and uninterpretable for the CNNs without capturing complex spectral properties sufficiently. This study proposed a novel interpretable multi-branch architecture for spatiotemporal CNNs, namely MultiSincNet. On the one hand, the MultiSincNet could directly show the frequency boundaries using the interpretable sinc-convolution layers. On the other hand, it could extract and integrate multiple spatiotemporal features across varying spectral resolutions using parallel branches. Moreover, we also constructed a post-hoc explanation technique for multi-branch CNNs, using the first-order Taylor expansion and chain rule based on the multivariate composite function, which demonstrates the crucial spatiotemporal features learned by the proposed multi-branch spatiotemporal CNN. When combined with the optimal MultiSincNet, ShallowConvNet, DeepConvNet, and EEGWaveNet had significantly improved the subject-specific performance on most metrics. Specifically, the optimal MultiSincNet significantly increased the average accuracy, sensitivity, specificity, binary F1-score, weighted F1-score, and AUC of EEGWaveNet by about 7%, 8%, 7%, 8%, 7%, and 7%, respectively. Besides, the visualization results showed that the optimal model mainly extracts the spectral energy difference from the high gamma band focalized to specific spatial areas as the dominant spatiotemporal EEG feature.
- 1 January 2024
- Published by Science Exploration Press in Computational Biomedicine
A bi-directional LSTM architecture enhanced with channel attention for seizure prediction
Aims: Neural networks capable of capturing temporal dependencies in electroencephalogram (EEG) signals hold considerable potential for seizure prediction by modeling the progressive evolution of preictal EEG changes. However, redundant or less informative temporal features may obscure critical preictal patterns, limiting seizure prediction performance. To address this, we developed a neural architecture that effectively leverages informative temporal features to enhance seizure prediction capability. Methods: We designed a bidirectional long short-term memory (BiLSTM) network enhanced with a channel attention mechanism, termed Attention-BiLSTM, which adaptively emphasizes informative temporal features while reducing information redundancy. We further analyze the model’s attention weights and feature distributions to provide interpretable insights into its decision-making process. Results: Evaluation on the CHB-MIT scalp EEG dataset demonstrates that Attention-BiLSTM achieves significant performance improvements over the baseline BiLSTM, with an average accuracy of 94.77%, sensitivity of 94.58%, specificity of 94.97%, and an area under the curve of 98.38%. Furthermore, visualization results indicate that the proposed model progressively enhances feature discriminability and directs attention to the most relevant temporal features for seizure prediction. Conclusion: The proposed Attention-BiLSTM achieves improved performance and interpretability, offering valuable insights to support future development of scalable and generalizable seizure prediction systems.
- 1 January 2024
- Published by Science Exploration Press in Computational Biomedicine
A bi-directional LSTM architecture enhanced with channel attention for seizure prediction
Aims: Neural networks capable of capturing temporal dependencies in electroencephalogram (EEG) signals hold considerable potential for seizure prediction by modeling the progressive evolution of preictal EEG changes. However, redundant or less informative temporal features may obscure critical preictal patterns, limiting seizure prediction performance. To address this, we developed a neural architecture that effectively leverages informative temporal features to enhance seizure prediction capability. Methods: We designed a bidirectional long short-term memory (BiLSTM) network enhanced with a channel attention mechanism, termed Attention-BiLSTM, which adaptively emphasizes informative temporal features while reducing information redundancy. We further analyze the model’s attention weights and feature distributions to provide interpretable insights into its decision-making process. Results: Evaluation on the CHB-MIT scalp EEG dataset demonstrates that Attention-BiLSTM achieves significant performance improvements over the baseline BiLSTM, with an average accuracy of 94.77%, sensitivity of 94.58%, specificity of 94.97%, and an area under the curve of 98.38%. Furthermore, visualization results indicate that the proposed model progressively enhances feature discriminability and directs attention to the most relevant temporal features for seizure prediction. Conclusion: The proposed Attention-BiLSTM achieves improved performance and interpretability, offering valuable insights to support future development of scalable and generalizable seizure prediction systems.
- Top Cited PapersOpen Access
- 9 June 2023
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 9 (23) , eadh0478
Decoding and synthesizing tonal language speech from brain activity
Recent studies have shown that the feasibility of speech brain-computer interfaces (BCIs) as a clinically valid treatment in helping nontonal language patients with communication disorders restore their speech ability. However, tonal language speech BCI is challenging because additional precise control of laryngeal movements to produce lexical tones is required. Thus, the model should emphasize the features from the tonal-related cortex. Here, we designed a modularized multistream neural network that directly synthesizes tonal language speech from intracranial recordings. The network decoded lexical tones and base syllables independently via parallel streams of neural network modules inspired by neuroscience findings. The speech was synthesized by combining tonal syllable labels with nondiscriminant speech neural activity. Compared to commonly used baseline models, our proposed models achieved higher performance with modest training data and computational costs. These findings raise a potential strategy for approaching tonal language speech restoration.
- 9 June 2023
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 9 (23) , eadh0478
Top Cited PapersOpen AccessDecoding and synthesizing tonal language speech from brain activity
Recent studies have shown that the feasibility of speech brain-computer interfaces (BCIs) as a clinically valid treatment in helping nontonal language patients with communication disorders restore their speech ability. However, tonal language speech BCI is challenging because additional precise control of laryngeal movements to produce lexical tones is required. Thus, the model should emphasize the features from the tonal-related cortex. Here, we designed a modularized multistream neural network that directly synthesizes tonal language speech from intracranial recordings. The network decoded lexical tones and base syllables independently via parallel streams of neural network modules inspired by neuroscience findings. The speech was synthesized by combining tonal syllable labels with nondiscriminant speech neural activity. Compared to commonly used baseline models, our proposed models achieved higher performance with modest training data and computational costs. These findings raise a potential strategy for approaching tonal language speech restoration.