Dalu Zheng

Dalu Zheng

Auto-generated profile, based on publicly available information

Dalu Zheng

School of Electronic and Information Engineering, Northwestern Polytechnical University, Xian, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 June 2024 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
HTHao Tang
Hao Tang
SXSongyun Xie
Songyun Xie
XXXinzhou Xie
Xinzhou Xie
CYCui Yujie
Cui Yujie
BLBohan Li
Bohan Li
ZTZhongyu Tian
Zhongyu Tian
Graph neural networks (GNNs) have demonstrated efficient processing of graph-structured data, making them a promising method for electroencephalogram (EEG) emotion recognition. However, due to dynamic functional connectivity and nonlinear relationships between brain regions, representing EEG as graph data remains a great challenge. To solve this problem, we proposed a multi-domain based graph representation learning (MD $^{2}$ GRL) framework to model EEG signals as graph data. Specifically, MD $^{2}$ GRL leverages gated recurrent units (GRU) and power spectral density (PSD) to construct node features of two subgraphs. Subsequently, the self-attention mechanism is adopted to learn the similarity matrix between nodes and fuse it with the intrinsic spatial matrix of EEG to compute the corresponding adjacency matrix. In addition, we introduced a learnable soft thresholding operator to sparsify the adjacency matrix to reduce noise in the graph structure. In the downstream task, we designed a dual-branch GNN and incorporated spatial asymmetry for graph coarsening. We conducted experiments using the publicly available datasets SEED and DEAP, separately for subject-dependent and subject-independent, to evaluate the performance of our model in emotion classification. Experimental results demonstrated that our method achieved state-of-the-art (SOTA) classification performance in both subject-dependent and subject-independent experiments. Furthermore, the visualization analysis of the learned graph structure reveals EEG channel connections that are significantly related to emotion and suppress irrelevant noise. These findings are consistent with established neuroscience research and demonstrate the potential of our approach in comprehending the neural underpinnings of emotion.

1 June 2023 in Journal of Neural Engineering
Verified
Journal Article
Open access
PDF file
CYCui Yujie
Cui Yujie
SXSongyun Xie
Songyun Xie
XXXinzhou Xie
Xinzhou Xie
DZDalu Zheng
Dalu Zheng
HTHao Tang
Hao Tang
YJYiye Jiang
Yiye Jiang
Objective. Rapid serial visual presentation (RSVP) based on electroencephalography (EEG) has been widely used in the target detection field, which distinguishes target and non-target by detecting event-related potential (ERP) components. However, the classification performance of the RSVP task is limited by the variability of ERP components, which is a great challenge in developing RSVP for real-life applications. Approach. To tackle this issue, a classification framework based on the ERP feature enhancement to offset the negative impact of the variability of ERP components for RSVP task classification named latency detection and EEG reconstruction was proposed in this paper. First, a spatial-temporal similarity measurement approach was proposed for latency detection. Subsequently, we constructed a single-trial EEG signal model containing ERP latency information. Then, according to the latency information detected in the first step, the model can be solved to obtain the corrected ERP signal and realize the enhancement of ERP features. Finally, the EEG signal after ERP enhancement can be processed by most of the existing feature extraction and classification methods of the RSVP task in this framework. Main results. Nine subjects were recruited to participate in the RSVP experiment on vehicle detection. Four popular algorithms (spatially weighted Fisher linear discrimination-principal component analysis (PCA), hierarchical discriminant PCA, hierarchical discriminant component analysis, and spatial-temporal hybrid common spatial pattern-PCA) in RSVP-based brain–computer interface for feature extraction were selected to verify the performance of our proposed framework. Experimental results showed that our proposed framework significantly outperforms the conventional classification framework in terms of area under curve, balanced accuracy, true positive rate, and false positive rate in four feature extraction methods. Additionally, statistical results showed that our proposed framework enables better performance with fewer training samples, channel numbers, and shorter temporal window sizes. Significance. As a result, the classification performance of the RSVP task was significantly improved by using our proposed framework. Our proposed classification framework will significantly promote the practical application of the RSVP task.

13 January 2025 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Verified
Journal Article
Open access
DZDalu Zheng
Dalu Zheng
SXSongyun Xie
Songyun Xie
XXXinzhou Xie
Xinzhou Xie
MSMichael Scholz
Michael Scholz
HTHao Tang
Hao Tang
Binocular disparate stimulation based on steady-state visual evoked potentials (SSVEP) generates more recognizable features but also introduces complexity hardening the interpretability of SSVEP responses. The individual contribution of each visual pathway when stimulating parts of the visual field remains unclear and is further obfuscated by the large spatial integration of EEG systems. We propose "independent visual field stimulation" (IVFS), utilizing a head-mounted display (HMD) as a novel experimental paradigm to improve the interpretability of SSVEP responses. By stimulating only half of the visual field and "coding" the stimulus further with different phases individual contributions of pathways and eyes can be easily separated and thus the mode of action becomes clearer. In a first proof-of-principles study on 15 subjects we demonstrate that IVFS with a 180° phase difference causes left and right scalp SSVEPs to exhibit a similar phase difference, and the propagation mechanism of SSVEPs conforms to the standing wave mode. Stimulating ipsilateral or contralateral pathways individually does influence temporal information processing but not SSVEP amplitudes. Utilizing the phase of the stimulus in addition to its frequency creates a new dimension and thus helps significantly to overcome frequency limitations in SSVEP research which otherwise dramatically hinder the read-out due to the prominent lowpass nature of the human head.

1 January 2025 in Electronics Letters
Verified
Journal Article
Open access
DZDalu Zheng
Dalu Zheng
SXSongyun Xie
Songyun Xie
XXXinzhou Xie
Xinzhou Xie
QLQing Liu
Qing Liu
Augmented reality (AR) technology can provide immersive and natural interactive interfaces for brain‐computer interface (BCI) systems. The control architecture of existing AR‐BCIs is at joint‐level (JL) or action‐level (AL), which brings a huge user burden and poor interactive experiences. A task‐level (TL) BCI control method was proposed in this study to enhance interactive experiences. The TL AR‐BCI system based on steady‐state visual evoked potentials was implemented controlling a robotic arm to grab and drop blocks. The online experiment of ten subjects shows TL AR‐BCI can effectively reduce the number of control steps and stimulation time while maintaining the same performance as JL and AL AR‐BCIs. The performance of three AR‐BCIs (JL, AL, TL) was calculated (mean accuracy: 90.66%, 92.52% and 92.2%. Mean information transfer rates: 77.56, 80.06, and 82.71 bits/min. Mean numbers of control steps: 35.48, 17.32, and 13.05. Mean stimulation time: 0.97, 0.97 and 0.89 s). The results show that TL AR‐BCI can effectively reduce the number of control steps and stimulation time while maintaining the same performance as JL and AL AR‐BCIs.

9 November 2026
Verified
Conference Paper
Open access
HTHao Tang
Hao Tang
SXSongyun Xie
Songyun Xie
XXXinzhou Xie
Xinzhou Xie
CLCan Liao
Can Liao
BLBohan Li
Bohan Li
DZDalu Zheng
Dalu Zheng

27 May 2026 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Verified
Journal Article
Open access
DZDalu Zheng
Dalu Zheng
WLWeiren Lin
Weiren Lin
SXSongyun Xie
Songyun Xie
XXXinzhou Xie
Xinzhou Xie
HTHao Tang
Hao Tang
BLBohan Li
Bohan Li
Dual-frequency modulation strategies in SSVEP-BCIs not only elicit fundamental responses but also induce robust intermodulation components (IMCs) through nonlinear neural integration, significantly expanding the available coding space. While IMCs can arise from various levels of the visual hierarchy depending on the stimulus complexity, the fundamental physiological origins of IMCs induced by pure luminance flicker—specifically whether they arise from retinal nonlinearity or cortical integration—remain debated. To resolve this, we employed a head-mounted display to physically isolate visual fields, comparing dichoptic hemifields (cortical) and monocular hemifield (retinal) conditions across varying spatial densities. Our results provide evidence that IMCs in scalp EEG during luminance modulation originate predominantly from retinal nonlinearities. Furthermore, while the geometric shape of the stimulus exerts a significant influence, the total length of the spatial boundaries separating the two frequencies acts as the dominant determinant of nonlinear output intensity. To elucidate why high-frequency IMCs often appear attenuated despite this robust boundary-driven generation, we constructed a spectral synthesis model (A = β·ITC·Freq−α). This analysis demonstrated that the scalp-recorded amplitude is directly proportional to Inter-Trial Coherence (ITC) but is severely dampened by the brain’s intrinsic 1/f capacitive filtering, confirming that the apparent weakness of high-frequency components is an artifact of physical transmission.