Xiaolin Xiao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xiaolin Xiao has a total of 78 co-authors. Here are the top co-authors by number of shared publications:
- Minpeng Xu
Tianjin University
17 shared publications - Dong Ming
Tianjin University
16 shared publications Minpeng Xu
Tianjin International Joint Research Center for Neural Engineering, Academy of Medical Engineering and Translational Medicine, Tianjin University, Academy of Medical Engineering and Translational Medicine, Tianjin 300072, Tianjin, Tianjin, 300072, CHINA
12 shared publicationsDong Ming
Tianjin International Joint Research Center for Neural Engineering, Academy of Medical Engineering and Translational Medicine, Tianjin University, Academy of Medical Engineering and Translational Medicine, Tianjin 300072, Tianjin, Tianjin, 300072, CHINA
11 shared publications- Kun Wang
Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin, China
7 shared publications Tzyy-Ping Jung
Swartz Center for Computational Neuroscience Institute for Neural Computation, University of California San Diego, San Diego, CA, United States of America
7 shared publications
Latest Publications
- 15 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30 (7) , 5907-5920
An Online Adaptation Framework for Enhancing Calibration-Free SSVEP-Based BCI Performance
Accomplishing a plug-and-play steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) remains a critical challenge, due to the unsatisfying performance of calibration-free decoding algorithms. A current method called online adaptive canonical correlation analysis (OACCA) has proved efficient in enhancing calibration-free performance by self-adaptation merely with online data. However, OACCA only concerns the adaptation of spatial filters and excludes other useful adaptive procedures like individual template estimation, hindering fully exploitable model decoding and adaptation. This study proposes a new online adaptation framework termed online adaptive extended correlation analysis (OAECA) to augment the calibration-free online adaptation loop. OAECA first recalls and cleans the online trials for reliable data learning, then tunes individual templates and spatial filters for complete model updating, and finally adopts extended feature matching to improve target recognition. The simulation results on two public SSVEP datasets revealed that OAECA significantly outperformed OACCA for almost all 105 subjects, and both offline and online experiments further confirmed the effectiveness of OAECA. Particularly, OAECA achieved the highest average information transfer rate (ITR) of 202.17 bits/min in the online experiment, significantly exceeding the state-of-the-art OACCA of 177.02 bits/min. This study enhanced the calibration-free performance through comprehensive online adaptation, hopefully advancing SSVEP-based BCIs toward practical plug-and-play real-world applications.
- 15 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30 (7) , 5907-5920
An Online Adaptation Framework for Enhancing Calibration-Free SSVEP-Based BCI Performance
Accomplishing a plug-and-play steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) remains a critical challenge, due to the unsatisfying performance of calibration-free decoding algorithms. A current method called online adaptive canonical correlation analysis (OACCA) has proved efficient in enhancing calibration-free performance by self-adaptation merely with online data. However, OACCA only concerns the adaptation of spatial filters and excludes other useful adaptive procedures like individual template estimation, hindering fully exploitable model decoding and adaptation. This study proposes a new online adaptation framework termed online adaptive extended correlation analysis (OAECA) to augment the calibration-free online adaptation loop. OAECA first recalls and cleans the online trials for reliable data learning, then tunes individual templates and spatial filters for complete model updating, and finally adopts extended feature matching to improve target recognition. The simulation results on two public SSVEP datasets revealed that OAECA significantly outperformed OACCA for almost all 105 subjects, and both offline and online experiments further confirmed the effectiveness of OAECA. Particularly, OAECA achieved the highest average information transfer rate (ITR) of 202.17 bits/min in the online experiment, significantly exceeding the state-of-the-art OACCA of 177.02 bits/min. This study enhanced the calibration-free performance through comprehensive online adaptation, hopefully advancing SSVEP-based BCIs toward practical plug-and-play real-world applications.
- 1 December 2025
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 22 (6) , 061004
Lightweight deep learning models for EEG decoding: a review
Brain–computer interface (BCI) technology enables direct communication between the human brain and external devices by decoding electroencephalography (EEG)signals into actionable commands. As a noninvasive and portable modality, EEG-based BCIs hold promise for applications ranging from neurorehabilitation to assistive technologies. However, their performance depends critically on the accurate extraction of relevant neural features and the reliable recognition of underlying patterns. Deep learning has transformed this process. By automatically learning complex, task-relevant representations from raw or minimally processed EEG data, deep neural networks have surpassed many traditional handcrafted feature approaches in both accuracy and adaptability. Yet, the substantial computational and memory demands of many deep learning architectures limit their deployment in portable or real-time BCI systems. This challenge has motivated a growing interest in lightweight models-architectures optimized to reduce complexity while preserving or even enhancing performance. This paper provides a systematic review of such lightweight deep learning models for EEG signal classification. To organize this landscape, existing approaches are categorized into three main strategies: (1) information integration strategies based on multi-scale feature fusion, (2) hidden layer optimization strategies, and (3) hybrid improvement strategies based on structural optimization. The review synthesizes recent advances, identifies emerging trends, and outlines potential directions for future research. These insights aim to inform the design of efficient and robust EEG classification architectures capable of meeting the practical demands of real-world BCI applications.
- 1 December 2025
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 22 (6) , 061004
Lightweight deep learning models for EEG decoding: a review
Brain–computer interface (BCI) technology enables direct communication between the human brain and external devices by decoding electroencephalography (EEG)signals into actionable commands. As a noninvasive and portable modality, EEG-based BCIs hold promise for applications ranging from neurorehabilitation to assistive technologies. However, their performance depends critically on the accurate extraction of relevant neural features and the reliable recognition of underlying patterns. Deep learning has transformed this process. By automatically learning complex, task-relevant representations from raw or minimally processed EEG data, deep neural networks have surpassed many traditional handcrafted feature approaches in both accuracy and adaptability. Yet, the substantial computational and memory demands of many deep learning architectures limit their deployment in portable or real-time BCI systems. This challenge has motivated a growing interest in lightweight models-architectures optimized to reduce complexity while preserving or even enhancing performance. This paper provides a systematic review of such lightweight deep learning models for EEG signal classification. To organize this landscape, existing approaches are categorized into three main strategies: (1) information integration strategies based on multi-scale feature fusion, (2) hidden layer optimization strategies, and (3) hybrid improvement strategies based on structural optimization. The review synthesizes recent advances, identifies emerging trends, and outlines potential directions for future research. These insights aim to inform the design of efficient and robust EEG classification architectures capable of meeting the practical demands of real-world BCI applications.
- Open Access
- 1 November 2025
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 3147 (1)
Repetition Suppression of aVEP Evoked by Weak Visual Stimulus in Brain-Computer Interface
Asymmetric visual evoked potentials (aVEPs) have shown potential in brain-computer interfaces (BCIs). However, its codec design is limited by the effect of repetition suppression, which is characterized by the attenuation of neural response after repeated stimulation. For now, there is still a lack of targeted explanation on the main mechanism of the repetition suppression effect in aVEP. To meet this end, a spatially multiple repeated visual stimulation paradigm under two different attentional states is proposed. Results revealed that repetition suppression effect in aVEPs is mainly driven by a bottom-up fatigue mechanism. Additionally, the response to a single repetition at the same location remains relatively stable, indicating potential usage in future coding paradigms for weak-stimulus brain-computer interface systems.
- 1 November 2025
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 3147 (1)
Open AccessRepetition Suppression of aVEP Evoked by Weak Visual Stimulus in Brain-Computer Interface
Asymmetric visual evoked potentials (aVEPs) have shown potential in brain-computer interfaces (BCIs). However, its codec design is limited by the effect of repetition suppression, which is characterized by the attenuation of neural response after repeated stimulation. For now, there is still a lack of targeted explanation on the main mechanism of the repetition suppression effect in aVEP. To meet this end, a spatially multiple repeated visual stimulation paradigm under two different attentional states is proposed. Results revealed that repetition suppression effect in aVEPs is mainly driven by a bottom-up fatigue mechanism. Additionally, the response to a single repetition at the same location remains relatively stable, indicating potential usage in future coding paradigms for weak-stimulus brain-computer interface systems.
- 1 October 2025
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 22 (5) , 056031
BGTransform: a neurophysiologically informed EEG data augmentation framework
Objective. Deep learning has emerged as a powerful approach for decoding electroencephalography (EEG)-based brain–computer interface (BCI) signals. However, its effectiveness is often limited by the scarcity and variability of available training data. Existing data augmentation methods often introduce signal distortions or lack physiological validity. This study proposes a novel augmentation strategy designed to improve generalization while preserving the underlying neurophysiological structure of EEG signals. Approach. We propose Background EEG Transform (BGTransform), a principled data augmentation framework that leverages the neurophysiological dissociation between task-related activity and ongoing background EEG. In contrast to existing methods, BGTransform generates new trials by selectively perturbing the background EEG component while preserving the task-related signal, thus enabling controlled variability without compromising class-discriminative features. We applied BGTransform to three publicly available EEG-BCI datasets spanning steady-state visual evoked potential and P300 paradigms. The effectiveness of BGTransform is evaluated using several widely adopted neural decoding models under three training regimes: (1) without augmentation (baseline model), (2) with conventional augmentation methods, and (3) with BGTransform. Main results. Across all datasets and model architectures, BGTransform consistently outperformed both baseline models and conventional augmentation techniques. Compared to models trained without BGTransform, it achieved average classification accuracy improvements of 2.45%–15.52%, 4.36%–17.15% and 7.55%–10.47% across the three datasets, respectively. In addition, BGTransform demonstrated greater robustness across subjects and tasks, maintaining stable performance under varying recording conditions. Significance. BGTransform provides a principled and effective approach to augmenting EEG data, informed by neurophysiological insight. By preserving task-related components and introducing controlled variability, the method addresses the challenge of data sparsity in EEG-BCI training. These findings support the utility of BGTransform for improving the accuracy, robustness, and generalizability of deep learning models in neural engineering applications.
- 1 October 2025
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 22 (5) , 056031
BGTransform: a neurophysiologically informed EEG data augmentation framework
Objective. Deep learning has emerged as a powerful approach for decoding electroencephalography (EEG)-based brain–computer interface (BCI) signals. However, its effectiveness is often limited by the scarcity and variability of available training data. Existing data augmentation methods often introduce signal distortions or lack physiological validity. This study proposes a novel augmentation strategy designed to improve generalization while preserving the underlying neurophysiological structure of EEG signals. Approach. We propose Background EEG Transform (BGTransform), a principled data augmentation framework that leverages the neurophysiological dissociation between task-related activity and ongoing background EEG. In contrast to existing methods, BGTransform generates new trials by selectively perturbing the background EEG component while preserving the task-related signal, thus enabling controlled variability without compromising class-discriminative features. We applied BGTransform to three publicly available EEG-BCI datasets spanning steady-state visual evoked potential and P300 paradigms. The effectiveness of BGTransform is evaluated using several widely adopted neural decoding models under three training regimes: (1) without augmentation (baseline model), (2) with conventional augmentation methods, and (3) with BGTransform. Main results. Across all datasets and model architectures, BGTransform consistently outperformed both baseline models and conventional augmentation techniques. Compared to models trained without BGTransform, it achieved average classification accuracy improvements of 2.45%–15.52%, 4.36%–17.15% and 7.55%–10.47% across the three datasets, respectively. In addition, BGTransform demonstrated greater robustness across subjects and tasks, maintaining stable performance under varying recording conditions. Significance. BGTransform provides a principled and effective approach to augmenting EEG data, informed by neurophysiological insight. By preserving task-related components and introducing controlled variability, the method addresses the challenge of data sparsity in EEG-BCI training. These findings support the utility of BGTransform for improving the accuracy, robustness, and generalizability of deep learning models in neural engineering applications.
- 29 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 22 (15455955) , 20234-20248
A High-DOF BCI Control Strategy Mapping Discrete Commands to Continuous Motion for a Drone
Objective: Because of the non-stationary nature of electroencephalogram (EEG) signals, traditional non-invasive brain-computer interfaces (BCIs) usually only produce discrete commands, limiting their ability to control external devices continuously. This study proposes a novel BCI control strategy mapping multiple discrete commands to continuous motion, enabling real-time manipulation of a drone in four degrees of freedom (DOF). Methods: Our strategy used the fast steady state visual evoked potential (SSVEP) encoding and decoding method to convert user intentions into the drone’s flight status in near real-time. Simultaneously, the drone’s live video was embedded into the SSVEP stimuli, providing users with a first-person perspective control experience. Results: In drone control experiments, participants successfully maneuvered the drone through complex path-following tasks in simulated and physical scenarios. The mean flight trajectory bias ratio was measured as 0.81, with a mean flight smoothness of -3.31 (measured by spectral arc length) and mean Fitts’s throughput of 9.18 bits/min. Notably, the brain-to-hand ratio (BHR) for all metrics approached 1, indicating that our non-invasive control system achieved comparable performance to manual control systems. Conclusion: These results suggest the effectiveness of our proposed BCI control strategy that maps discrete commands to continuous motion and extends the capabilities of non-invasive BCIs in continuous control scenarios. Significance: This study significantly advances the applications of BCI and propels human-machine interaction towards a more direct realm.
- 29 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 22 (15455955) , 20234-20248
A High-DOF BCI Control Strategy Mapping Discrete Commands to Continuous Motion for a Drone
Objective: Because of the non-stationary nature of electroencephalogram (EEG) signals, traditional non-invasive brain-computer interfaces (BCIs) usually only produce discrete commands, limiting their ability to control external devices continuously. This study proposes a novel BCI control strategy mapping multiple discrete commands to continuous motion, enabling real-time manipulation of a drone in four degrees of freedom (DOF). Methods: Our strategy used the fast steady state visual evoked potential (SSVEP) encoding and decoding method to convert user intentions into the drone’s flight status in near real-time. Simultaneously, the drone’s live video was embedded into the SSVEP stimuli, providing users with a first-person perspective control experience. Results: In drone control experiments, participants successfully maneuvered the drone through complex path-following tasks in simulated and physical scenarios. The mean flight trajectory bias ratio was measured as 0.81, with a mean flight smoothness of -3.31 (measured by spectral arc length) and mean Fitts’s throughput of 9.18 bits/min. Notably, the brain-to-hand ratio (BHR) for all metrics approached 1, indicating that our non-invasive control system achieved comparable performance to manual control systems. Conclusion: These results suggest the effectiveness of our proposed BCI control strategy that maps discrete commands to continuous motion and extends the capabilities of non-invasive BCIs in continuous control scenarios. Significance: This study significantly advances the applications of BCI and propels human-machine interaction towards a more direct realm.
- 24 July 2025
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 22 (4) , 046028
Research on coding and decoding algorithm of binocular brain-controlled unmanned vehicle
Objective. With the rapid development of brain–computer interface (BCI) technology, steady-state visual evoked potential (SSVEP) has emerged as an effective method for high-efficiency information transmission. However, traditional single-frequency stimulation methods face limitations in command set scalability and visual comfort. Approach. To address these issues, we propose a novel binocular SSVEP stimulation paradigm for brain-controlled unmanned vehicles. (UV) This system uses a checkerboard and phase encoding for stimulus presentation, encoding a single target with two frequencies to expand the command set. The frequencies are set between 30–35 Hz to enhance visual comfort. By leveraging polarized light technology, each eye receives distinct frequencies, suppressing intermodulation components and reducing the stimulated area for each eye. We also introduce an improved filter bank dual-frequency task-discriminant component analysis (FBD-TDCA) algorithm. Main results. Experimental results show that, in a 15-command simulation, only six frequencies successfully encoded all commands, achieving comparable performance to traditional single-frequency paradigms. Furthermore, the FBD-TDCA algorithm outperformed existing methods such as filter bank task-related component analysis and filter bank canonical correlation analysis, achieving a classification accuracy of 89.27% ± 3.67 and an information translate rate of 163.87 ± 14.32 bits min−1, with statistical significance confirmed through paired t-tests. The system’s practical application was further demonstrated in an online 12-command UV control task. Participants achieved an average classification accuracy of 90.34% ± 8.75%, with most maintaining low path deviation rates during navigation tasks. Significance. The proposed binocular SSVEP stimulation paradigm and FBD-TDCA algorithm address the limitations of traditional methods, offering enhanced command set scalability, improved visual comfort, and superior performance, paving the way for more efficient and user-friendly BCI applications in real-world scenarios.
- 24 July 2025
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 22 (4) , 046028
Research on coding and decoding algorithm of binocular brain-controlled unmanned vehicle
Objective. With the rapid development of brain–computer interface (BCI) technology, steady-state visual evoked potential (SSVEP) has emerged as an effective method for high-efficiency information transmission. However, traditional single-frequency stimulation methods face limitations in command set scalability and visual comfort. Approach. To address these issues, we propose a novel binocular SSVEP stimulation paradigm for brain-controlled unmanned vehicles. (UV) This system uses a checkerboard and phase encoding for stimulus presentation, encoding a single target with two frequencies to expand the command set. The frequencies are set between 30–35 Hz to enhance visual comfort. By leveraging polarized light technology, each eye receives distinct frequencies, suppressing intermodulation components and reducing the stimulated area for each eye. We also introduce an improved filter bank dual-frequency task-discriminant component analysis (FBD-TDCA) algorithm. Main results. Experimental results show that, in a 15-command simulation, only six frequencies successfully encoded all commands, achieving comparable performance to traditional single-frequency paradigms. Furthermore, the FBD-TDCA algorithm outperformed existing methods such as filter bank task-related component analysis and filter bank canonical correlation analysis, achieving a classification accuracy of 89.27% ± 3.67 and an information translate rate of 163.87 ± 14.32 bits min−1, with statistical significance confirmed through paired t-tests. The system’s practical application was further demonstrated in an online 12-command UV control task. Participants achieved an average classification accuracy of 90.34% ± 8.75%, with most maintaining low path deviation rates during navigation tasks. Significance. The proposed binocular SSVEP stimulation paradigm and FBD-TDCA algorithm address the limitations of traditional methods, offering enhanced command set scalability, improved visual comfort, and superior performance, paving the way for more efficient and user-friendly BCI applications in real-world scenarios.
- 25 June 2025
- Vol. 42 (3) , 620-627
[Research on the relationship between resting-state spontaneous electroencephalography and task-evoked electroencephalography].
In recent years, it has become a new direction in the field of neuroscience to explore the mode characteristics, functional significance and interaction mechanism of resting spontaneous electroencephalography (EEG) and task-evoked EEG. This paper introduced the basic characteristics of spontaneous EEG and task-evoked EEG, and summarized the core role of spontaneous EEG in shaping the adaptability of the nervous system. It focused on how the spontaneous EEG interacted with the task-evoked EEG in the process of task processing, and emphasized that the spontaneous EEG could significantly affect the performance of tasks such as perception, cognition and movement by regulating neural activities and predicting external stimuli. These studies provide an important theoretical basis for in-depth understanding of the principle and mechanism of brain information processing in resting and task states, and point out the direction for further exploring the complex relationship between them in the future.
- 25 June 2025
- Vol. 42 (3) , 620-627
[Research on the relationship between resting-state spontaneous electroencephalography and task-evoked electroencephalography].
In recent years, it has become a new direction in the field of neuroscience to explore the mode characteristics, functional significance and interaction mechanism of resting spontaneous electroencephalography (EEG) and task-evoked EEG. This paper introduced the basic characteristics of spontaneous EEG and task-evoked EEG, and summarized the core role of spontaneous EEG in shaping the adaptability of the nervous system. It focused on how the spontaneous EEG interacted with the task-evoked EEG in the process of task processing, and emphasized that the spontaneous EEG could significantly affect the performance of tasks such as perception, cognition and movement by regulating neural activities and predicting external stimuli. These studies provide an important theoretical basis for in-depth understanding of the principle and mechanism of brain information processing in resting and task states, and point out the direction for further exploring the complex relationship between them in the future.
- Open Access
- 12 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Systems and Rehabilitation Engineering
- Vol. 33 (15344320) , 1202-1211
Enhanced Spatial Division Multiple Access BCI Performance via Incorporating MEG With EEG
Spatial division multiple access (SDMA) is a way of encoding BCI systems based on spatial distribution of brain signal characteristics. However, SDMA-BCI based on EEG had poor system performance limited by spatial resolution. MEG-EEG fusion modality analysis can help solve this problem. According retina-cortical relationship, this study used stimulus out of the central visual field and tiny fixation points to construct a 16-command SDMA coded MEG-EEG fusion modality BCI system. We achieved this by synchronously acquiring MEG and EEG signals from 10 subjects. We compared the spatiotemporal features between MEG and EEG by analyzing signals in the occipital region. We fused MEG and EEG modalities without any signal processing and used the multi-class discriminative canonical pattern matching (Multi-DCPM) algorithm to evaluate and compare the system performance of EEG, MEG, and MEG-EEG fusion modalities. The result showed that MEG and EEG had obvious differences in spatial distribution characteristics. MEG improves offline classification accuracy of the 16 fixation points by 27.81% over EEG at 4s data length. Specially, the MEG-EEG fusion modality achieves an impressive average offline accuracy of 91.71%, which was a significant improvement over MEG (p<0.01, ANOVA). The MEG-EEG fusion modality achieved average information transfer rate (ITR) of 60.74 bits/min with a data length of 1 s, which was a 14% improvement over MEG. The MEG-EEG fusion modality significantly enhanced the spatial features and performance of SDMA-encoded BCIs. These results highlight the potential and feasibility of MEG-EEG fusion modality BCI, and provide theoretical insights and practical value for promoting the further development and application of SDMA in BCI.
- 12 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Systems and Rehabilitation Engineering
- Vol. 33 (15344320) , 1202-1211
Open AccessEnhanced Spatial Division Multiple Access BCI Performance via Incorporating MEG With EEG
Spatial division multiple access (SDMA) is a way of encoding BCI systems based on spatial distribution of brain signal characteristics. However, SDMA-BCI based on EEG had poor system performance limited by spatial resolution. MEG-EEG fusion modality analysis can help solve this problem. According retina-cortical relationship, this study used stimulus out of the central visual field and tiny fixation points to construct a 16-command SDMA coded MEG-EEG fusion modality BCI system. We achieved this by synchronously acquiring MEG and EEG signals from 10 subjects. We compared the spatiotemporal features between MEG and EEG by analyzing signals in the occipital region. We fused MEG and EEG modalities without any signal processing and used the multi-class discriminative canonical pattern matching (Multi-DCPM) algorithm to evaluate and compare the system performance of EEG, MEG, and MEG-EEG fusion modalities. The result showed that MEG and EEG had obvious differences in spatial distribution characteristics. MEG improves offline classification accuracy of the 16 fixation points by 27.81% over EEG at 4s data length. Specially, the MEG-EEG fusion modality achieves an impressive average offline accuracy of 91.71%, which was a significant improvement over MEG (p<0.01, ANOVA). The MEG-EEG fusion modality achieved average information transfer rate (ITR) of 60.74 bits/min with a data length of 1 s, which was a 14% improvement over MEG. The MEG-EEG fusion modality significantly enhanced the spatial features and performance of SDMA-encoded BCIs. These results highlight the potential and feasibility of MEG-EEG fusion modality BCI, and provide theoretical insights and practical value for promoting the further development and application of SDMA in BCI.
- 1 February 2025
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 22 (1) , 016043
Enhancing detection of SSVEPs using discriminant compacted network
Objective. Steady-state visual evoked potential-based brain–computer interfaces (SSVEP-BCIs) have gained significant attention due to their simplicity, high signal to noise ratio and high information transfer rates (ITRs). Currently, accurate detection is a critical issue for enhancing the performance of SSVEP-BCI systems. Approach. This study proposed a novel decoding method called Discriminant Compacted Network (Dis-ComNet), which exploited the advantages of both spatial filtering and deep learning (DL). Specifically, this study enhanced SSVEP features using global template alignment and discriminant spatial pattern, and then designed a compacted temporal-spatio module (CTSM) to extract finer features. The proposed method was evaluated on a self-collected high-frequency dataset, a public Benchmark dataset and a public wearable dataset. Main Results. The results showed that Dis-ComNet significantly outperformed state-of-the-art spatial filtering methods, DL methods, and other fusion methods. Remarkably, Dis-ComNet improved the classification accuracy by 3.9%, 3.5%, 3.2%, 13.3%, 17.4%, 37.5%, and 2.5% when comparing with eTRCA, eTRCA-R, TDCA, DNN, EEGnet, Ensemble-DNN, and TRCA-Net respectively in the high-frequency dataset. The achieved results were 4.7%, 4.6%, 23.6%, 52.5%, 31.7%, and 7.0% higher than those of eTRCA, eTRCA-R, DNN, EEGnet, Ensemble-DNN, and TRCA-Net, respectively, and were comparable to those of TDCA in Benchmark dataset. The accuracy of Dis-ComNet in the wearable dataset was 9.5%, 7.1%, 36.1%, 26.3%, 15.7% and 4.7% higher than eTRCA, eTRCA-R, DNN, EEGnet, Ensemble-DNN, and TRCA-Net respectively, and comparable to TDCA. Besides, our model achieved the ITRs up to 126.0 bits/min, 236.4 bits/min and 103.6 bits/min in the high-frequency, Benchmark and the wearable datasets respectively. Significance. This study develops an effective model for the detection of SSVEPs, facilitating the development of high accuracy SSVEP-BCI systems.
- 1 February 2025
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 22 (1) , 016043
Enhancing detection of SSVEPs using discriminant compacted network
Objective. Steady-state visual evoked potential-based brain–computer interfaces (SSVEP-BCIs) have gained significant attention due to their simplicity, high signal to noise ratio and high information transfer rates (ITRs). Currently, accurate detection is a critical issue for enhancing the performance of SSVEP-BCI systems. Approach. This study proposed a novel decoding method called Discriminant Compacted Network (Dis-ComNet), which exploited the advantages of both spatial filtering and deep learning (DL). Specifically, this study enhanced SSVEP features using global template alignment and discriminant spatial pattern, and then designed a compacted temporal-spatio module (CTSM) to extract finer features. The proposed method was evaluated on a self-collected high-frequency dataset, a public Benchmark dataset and a public wearable dataset. Main Results. The results showed that Dis-ComNet significantly outperformed state-of-the-art spatial filtering methods, DL methods, and other fusion methods. Remarkably, Dis-ComNet improved the classification accuracy by 3.9%, 3.5%, 3.2%, 13.3%, 17.4%, 37.5%, and 2.5% when comparing with eTRCA, eTRCA-R, TDCA, DNN, EEGnet, Ensemble-DNN, and TRCA-Net respectively in the high-frequency dataset. The achieved results were 4.7%, 4.6%, 23.6%, 52.5%, 31.7%, and 7.0% higher than those of eTRCA, eTRCA-R, DNN, EEGnet, Ensemble-DNN, and TRCA-Net, respectively, and were comparable to those of TDCA in Benchmark dataset. The accuracy of Dis-ComNet in the wearable dataset was 9.5%, 7.1%, 36.1%, 26.3%, 15.7% and 4.7% higher than eTRCA, eTRCA-R, DNN, EEGnet, Ensemble-DNN, and TRCA-Net respectively, and comparable to TDCA. Besides, our model achieved the ITRs up to 126.0 bits/min, 236.4 bits/min and 103.6 bits/min in the high-frequency, Benchmark and the wearable datasets respectively. Significance. This study develops an effective model for the detection of SSVEPs, facilitating the development of high accuracy SSVEP-BCI systems.
- Open Access
- 8 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Systems and Rehabilitation Engineering
- Vol. 33 (15344320) , 420-430
SSVEP Enhancement in Mixed Reality Environment for Brain–Computer Interfaces
Expanding the application possibilities of brain-computer interfaces (BCIs) is possible through their implementation in mixed reality (MR) environments. However, visual stimuli are displayed against a realistic scene in the MR environment, which degrades BCI performance. The purpose of this study was to optimize stimulus colors in order to improve the MR-BCI system’s performance. In the MR environment, a 10-command SSVEP-BCI was deployed. Various stimulus colors and background colors for the BCI system were tested and optimized in offline and online experiments. Color contrast ratios (CCRs) between stimulus and background colors were introduced to assess the performance difference among all conditions. Additionally, we proposed a cross-correlation task-related component analysis based on simulated annealing (SA-xTRCA), which can increase the signal-to-noise ratio (SNR) and detection accuracy by aligning SSVEP trials. The results of an offline experiment showed that the background and stimulus colors had a significant interaction effect that can impact system performance. A possible nonlinear relationship between CCR value and SSVEP detection accuracy exists. Online experiment results demonstrated that the system performed best with polychromatic stimulus on the colored background. The proposed SA-xTRCA significantly outperformed the other four traditional algorithms. The online average information transfer rate (ITR) achieved 57.58 ± 5.31 bits/min. This study proved that system performance can be effectively enhanced by optimizing stimulus color based on background color. In MR environments, CCR can be used as a quantitative criterion for choosing stimulus colors in BCI system design.
- 8 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Systems and Rehabilitation Engineering
- Vol. 33 (15344320) , 420-430
Open AccessSSVEP Enhancement in Mixed Reality Environment for Brain–Computer Interfaces
Expanding the application possibilities of brain-computer interfaces (BCIs) is possible through their implementation in mixed reality (MR) environments. However, visual stimuli are displayed against a realistic scene in the MR environment, which degrades BCI performance. The purpose of this study was to optimize stimulus colors in order to improve the MR-BCI system’s performance. In the MR environment, a 10-command SSVEP-BCI was deployed. Various stimulus colors and background colors for the BCI system were tested and optimized in offline and online experiments. Color contrast ratios (CCRs) between stimulus and background colors were introduced to assess the performance difference among all conditions. Additionally, we proposed a cross-correlation task-related component analysis based on simulated annealing (SA-xTRCA), which can increase the signal-to-noise ratio (SNR) and detection accuracy by aligning SSVEP trials. The results of an offline experiment showed that the background and stimulus colors had a significant interaction effect that can impact system performance. A possible nonlinear relationship between CCR value and SSVEP detection accuracy exists. Online experiment results demonstrated that the system performed best with polychromatic stimulus on the colored background. The proposed SA-xTRCA significantly outperformed the other four traditional algorithms. The online average information transfer rate (ITR) achieved 57.58 ± 5.31 bits/min. This study proved that system performance can be effectively enhanced by optimizing stimulus color based on background color. In MR environments, CCR can be used as a quantitative criterion for choosing stimulus colors in BCI system design.