SZSiqi Zhang

Siqi Zhang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Siqi Zhang has a total of 23 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Three-Dimensional Electrode Model for EEG Forward Problem

    by Ting Zhang, Yan Liu, Liantao Cheng, Erfang Ma, Siqi Zhang, Xiaolin Li, Dezhong Yao, Yakang Dai

    Objective: This study aims to address inaccuracies in model description and boundary representation due to dimension-ality loss in the commonly-used point electrode model (PEM) and complete electrode model (CEM) for EEG forward problem (FP). Methods: To overcome these limitations, this paper proposes a three-dimensional electrode model (TEM). Firstly, we devise an extension-constraint framework to generate an electrode mesh based on the structural priors and seamlessly integrate it into the MRI-based head mesh through two modules: (1) an extension module designed to extend a cuboid mesh containing both head and electrode meshes to avoid the challenges in fusing two irregular stepped surface mesh, and (2) loosely coupled constraints formulated in the constraint module to describe the electrode structure and enhance the flexibility and extensibility. Secondly, an accurate boundary representation is achieved by setting a local equipotential on the metal surface of the electrodes. Results: Experimental results indicate that, compared with PEM and CEM, TEM exhibits significant differences in FP and inverse problem. Further explorations reveal that alterations in electrode height, structure, and contact area exert a more profound impact than conductivity, whereas the impact of air bubbles, hair, and gel bridges is structure-dependent. Conclusion: The proposed TEM has the potential to enhance the solution accuracy of FP and inverse problem. Significance: This paper introduces an ingenious method for incorporating the 3D structure of electrodes into FP solution to improve the accuracy and explore the effect of electrode structure.


  • Flexible-Center Hat Complete Electrode Model for EEG Forward Problem

    by Ting Zhang, Yan Liu, Erfang Ma, Bo Peng, Ardalan Aarabi, Siqi Zhang, Ying Hu, Jing Xiang, Yakang Dai

    Objective: This study aims to develop a more realistic electrode model by incorporating the non-uniform distribution of electrode contact conductance (ECC) and the shunting effects, to accurately solve EEG forward problem (FP). Methods: Firstly, a hat function is introduced to construct a more realistic hat-shaped distribution (HD) for ECC. Secondly, this hat function is modified by applying two parameters - offset ratio and offset direction - to account for the variability in ECC's center and to develop the flexible-center HD (FCHD). Finally, by integrating this FCHD into the complete electrode model (CEM) with the shunting effects, a novel flexible-center hat complete electrode model (FCH-CEM) is proposed and used to solve FP. Results: Simulation experiments using a realistic head model demonstrate the necessity of FCHCEM and its potential to improve the accuracy of the FP solution compared to current models, i.e., the point electrode model (PEM) and CEM. And compared to PEM, it has better performance under coarse mesh conditions (2 mm). Further experiments indicate the significance of considering shunting effects, as ignoring them results in larger errors than coarse mesh when the average contact conductance is large (). Conclusion: The proposed FCH-CEM has better accuracy and performance than PEM and complements CEM in finer meshes, making it necessary for coarse meshes. Significance: This study proposes a novel model that enhances electrode modeling and FP accuracy, and provides new ideas and methods for future research.


  • Open Access

    A Cross-Space CNN With Customized Characteristics for Motor Imagery EEG Classification

    by Ying Hu, Yan Liu, Siqi Zhang, Ting Zhang, Bin Dai, Bo Peng, Hongbo Yang, Yakang Dai

    The classification of motor imagery-electroencephalogram(MI-EEG)based brain-computer interface(BCI)can be used to decode neurological activities, which has been widely applied in the control of external devices. However, two factors still hinder the improvement of classification accuracy and robustness, especially in multi-class tasks. First, existing algorithms are based on a single space (measuring or source space). They suffer from the holistic low spatial resolution of the measuring space or the locally high spatial resolution information accessed from the source space, failing to provide holistic and high-resolution representations. Second, the subject specificity is not sufficiently characterized, resulting in the loss of personalized intrinsic information. Therefore, we propose a cross-space convolutional neural network (CS-CNN) with customized characteristics for four-class MI-EEG classification. This algorithm uses the modified customized band common spatial patterns (CBCSP) and duplex mean-shift clustering (DMSClustering) to express the specific rhythms and source distribution information in cross-space. At the same time, multi-view features from the time, frequency and space domains are extracted, connecting with CNN to fuse the characteristics from two spaces and classify them. MI-EEG was collected from 20 subjects. Lastly, the classification accuracy of the proposed is 96.05% with real MRI information and 94.79% without MRI in the private dataset. And the results in the BCI competition IV-2a show that CS-CNN outperforms the state-of-the-art algorithms, achieving an accuracy improvement of 1.98%, and a standard deviation reduction of 5.15%.


  • Whole-Brain Dynamic Resting-State Functional Network Analysis in Benign Epilepsy With Centrotemporal Spikes

    by Siqi Zhang, Jihong Tang, Jing Huang, Guihai Suo, Zhiyong Zhou, Bo You, Yakang Dai, Yan Liu

    Benign epilepsy with centrotemporal spikes (BECTS), the most common type of epilepsy among children, is considered a network disorder. Both fMRI and EEG source imaging (ESI) studies have indicated that BECTS is associated with static resting-state functional network (SFN) alterations (e.g., decreased global efficiency) in source space. However, we find that the abovementioned alterations are not significant when the SFN calculations are performed in the scalp space using only clinical routine low-density (e.g., 19 channels) EEG recordings (shown in our results). In the context of EEG microstates, it is clear that networks in the scalp space with resting-state EEG recordings dynamically reconfigure in a well-organized way based on different functional states. We are therefore inspired to propose a whole-brain dynamic resting-state functional network (DFN) computation method based on resting-state low-density EEG recordings with four classical microstates in scalp space. Notably, on the one hand, this approach is suitable for clinical conditions, and, on the other hand, the dynamic alternations calculated with a DFN may promote our understanding of how the networks change in BECTS. We analysed the changes in a DFN in six frequency bands (δ, θ, α low , α high , β, and γ) in patients with BECTS compared to those for healthy controls. Superior to traditional SFNs, the proposed DFN can reveal significant differences between individuals with BECTS and healthy controls (e.g., lower global efficiency), thus matching traditional fMRI and ESI methods in the source space. Our method directly performs DFN computations from low-density EEG recordings and avoids complex ESI computations, making it promising for clinical applications, especially in the outpatient diagnosis stage.


  • Efficient Rejection of Artifacts for Short-Term Few-Channel EEG Based on Fast Adaptive Multidimensional Sub-Bands Blind Source Separation

    by Siqi Zhang, Bo You, Xun Lang, Yuanfeng Zhou, Fulai An, Yakang Dai, Yan Liu

    Artifacts rejection is crucial to electroencephalogram (EEG) application. Short-term few-channel EEG (e.g., in real-time detection of stress level and motor imagery) brings new challenges for removing artifacts due to less data. The existing artifact removal methods cannot guarantee both effectiveness and efficiency for removing artifacts from short-term few-channel EEG recordings. Consequently, we propose a fast adaptive sub-bands’ blind source separation method to remove artifacts from short-term few-channel EEG recordings effectively and efficiently. First, noise-assisted fast multivariate empirical mode decomposition (NA-FMEMD), as a fast adaptive multidimensional sub-bands’ decomposition method, is used to decompose short-term few-channel EEG recordings into multidimensional sub-bands. Then canonical correlation analysis (CCA), as a blind source separation method, is used to estimate artifact-related and EEG-related sources. Finally, EEG-related sources are intelligently selected and reconstructed as clean EEG recordings. The results demonstrate that our method takes at least five times less computing time for 2-s few-channel EEG recordings than state-of-the-art methods with similar effectiveness, using the same computer and software. Therefore, our method enhances the efficiency of removing artifacts from short-term few-channel EEG recordings while ensuring effectiveness, and it is more suitable for real-time processing.