Lipeng Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Lipeng Zhang has a total of 54 co-authors. Here are the top co-authors by number of shared publications:
- Rui Zhang
Henan Key Laboratory of Brain Science and Brain-Computer Interface Technology, School of Electrical and Information Engineering, ZhengZhou University, Zhengzhou, China
10 shared publications Yuxia Hu
Henan Key Laboratory of Brain Science and Brain-Computer Interface Technology, School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, People's Republic of China
5 shared publicationsMingming Chen
School of Electrical and Information Engineering, Zhengzhou University, Henan Key Laboratory of Brain Science and Brain-Computer Interface Technology, Institute of Neuroscience, Zhengzhou University, 100 Kexue Avenue, Zhengzhou 450001, P. R. China
4 shared publications- Mingming Chen
School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou, China
4 shared publications - Renping Yu
School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou, China
4 shared publications - Shaoting Yan
School of Electrical and Information Engineering, Zhengzhou University, Henan Key Laboratory of Brain Science and Brain-Computer Interface Technology, Institute of Neuroscience, Zhengzhou University, 100 Kexue Avenue, Zhengzhou 450001, P. R. China
4 shared publications
Latest Publications
- 30 October 2026
- Published by World Scientific Pub Co Pte Ltd in International Journal of Pattern Recognition and Artificial Intelligence
Wavelet-Guided Frequency-Domain Adaptive Learning: Balancing Adversarial Defense and High-Fidelity Image Reconstruction
Deep learning has achieved remarkable success across diverse domains, including image recognition, segmentation, and restoration. However, adversarial attacks — where imperceptible perturbations are introduced to normal images to mislead models — pose significant security risks to deep neural networks, underscoring the critical need for robust adversarial defense strategies. Image reconstruction-based defense is widely adopted for its downstream model independence and flexibility, yet existing methods often prioritize defense effectiveness at the expense of image quality, limiting their applicability in high-stakes scenarios such as medical diagnosis and remote sensing. To address this imbalance, we propose WS-Net, a wavelet-guided frequency-domain adaptive denoising network. Leveraging the nonuniform distribution of adversarial noise, WS-Net decomposes images into low-frequency and high-frequency components via Discrete Wavelet Transform (DWT), applying denoising exclusively to high-frequency components to preserve critical structural information. At its core is the Swin Network Denoiser (SND), constructed with Swin Transformer-based blocks that utilize shifted window self-attention to accurately distinguish noise from image details. A multi-level loss function — combining pixel-level [Formula: see text] loss, feature-level perceptual loss, style loss, and adversarial loss — constrains the model from multiple dimensions. Experimental results on the ImageNet dataset demonstrate that WS-Net outperforms state-of-the-art models, achieving a top-1 accuracy of 71.4% on clean images, 70.2% under Gaussian noise, and superior defense performance across nine adversarial attacks (e.g. 68.5% accuracy against CW attacks, 67.9% against DeepFool). Notably, WS-Net achieves a Peak Signal-to-Noise Ratio (PSNR) of 30.2[Formula: see text]dB and a Structural Similarity Index (SSIM) of 0.87, balancing defense robustness and image fidelity effectively. The code for WS-Net is available at https://github.com/faaatwang/WS_Net.git .
- 30 October 2026
- Published by World Scientific Pub Co Pte Ltd in International Journal of Pattern Recognition and Artificial Intelligence
Wavelet-Guided Frequency-Domain Adaptive Learning: Balancing Adversarial Defense and High-Fidelity Image Reconstruction
Deep learning has achieved remarkable success across diverse domains, including image recognition, segmentation, and restoration. However, adversarial attacks — where imperceptible perturbations are introduced to normal images to mislead models — pose significant security risks to deep neural networks, underscoring the critical need for robust adversarial defense strategies. Image reconstruction-based defense is widely adopted for its downstream model independence and flexibility, yet existing methods often prioritize defense effectiveness at the expense of image quality, limiting their applicability in high-stakes scenarios such as medical diagnosis and remote sensing. To address this imbalance, we propose WS-Net, a wavelet-guided frequency-domain adaptive denoising network. Leveraging the nonuniform distribution of adversarial noise, WS-Net decomposes images into low-frequency and high-frequency components via Discrete Wavelet Transform (DWT), applying denoising exclusively to high-frequency components to preserve critical structural information. At its core is the Swin Network Denoiser (SND), constructed with Swin Transformer-based blocks that utilize shifted window self-attention to accurately distinguish noise from image details. A multi-level loss function — combining pixel-level [Formula: see text] loss, feature-level perceptual loss, style loss, and adversarial loss — constrains the model from multiple dimensions. Experimental results on the ImageNet dataset demonstrate that WS-Net outperforms state-of-the-art models, achieving a top-1 accuracy of 71.4% on clean images, 70.2% under Gaussian noise, and superior defense performance across nine adversarial attacks (e.g. 68.5% accuracy against CW attacks, 67.9% against DeepFool). Notably, WS-Net achieves a Peak Signal-to-Noise Ratio (PSNR) of 30.2[Formula: see text]dB and a Structural Similarity Index (SSIM) of 0.87, balancing defense robustness and image fidelity effectively. The code for WS-Net is available at https://github.com/faaatwang/WS_Net.git .
- 29 April 2026
- Published by World Scientific Pub Co Pte Ltd in International Journal of Neural Systems
- Vol. 36  (10) , 2650035
Recurrent Processing Dynamics in Occluded Object Recognition Revealed by Electroencephalography and Deep Neural Networks
The human visual system excels at recognizing occluded objects, yet the temporal dynamics of recurrent processing in this task remain unclear. Using high-temporal-resolution Electroencephalography (EEG), backward masking, and deep neural networks (DNNs), we employed a two-stage paradigm to investigate recurrent processing in occluded object recognition. In Experiment 1, we manipulated occlusion levels and applied multivariate pattern analysis (MVPA) and temporal generalization analysis (TGA) to investigate the neural differences in object recognition across varying degrees of occlusion. In Experiment 2, backward masking was used to dissociate feedforward and recurrent contributions, assessed via representational similarity analysis (RSA). Results revealed a distinct shift in processing mechanisms: While low occlusion primarily relied on a rapid feedforward sweep, higher occlusion necessitated the recruitment of additional processing. Further characterization of this processing based on TGA and RSA under mask conditions revealed a two-stage recurrent process: An early stage (200–300[ ]ms) associated with low-level features, and a late stage (300–500[ ]ms) involved mid- and high-level representations, reflecting cross-hierarchical recurrent interactions. The early mask condition disrupted this coordination, highlighting the essential role of recurrent processing. These findings clarify the temporal dynamics of recurrent processing in occluded object recognition and emphasize the critical role of recurrence in achieving robust biological vision.
- 29 April 2026
- Published by World Scientific Pub Co Pte Ltd in International Journal of Neural Systems
- Vol. 36  (10) , 2650035
Recurrent Processing Dynamics in Occluded Object Recognition Revealed by Electroencephalography and Deep Neural Networks
The human visual system excels at recognizing occluded objects, yet the temporal dynamics of recurrent processing in this task remain unclear. Using high-temporal-resolution Electroencephalography (EEG), backward masking, and deep neural networks (DNNs), we employed a two-stage paradigm to investigate recurrent processing in occluded object recognition. In Experiment 1, we manipulated occlusion levels and applied multivariate pattern analysis (MVPA) and temporal generalization analysis (TGA) to investigate the neural differences in object recognition across varying degrees of occlusion. In Experiment 2, backward masking was used to dissociate feedforward and recurrent contributions, assessed via representational similarity analysis (RSA). Results revealed a distinct shift in processing mechanisms: While low occlusion primarily relied on a rapid feedforward sweep, higher occlusion necessitated the recruitment of additional processing. Further characterization of this processing based on TGA and RSA under mask conditions revealed a two-stage recurrent process: An early stage (200–300[ ]ms) associated with low-level features, and a late stage (300–500[ ]ms) involved mid- and high-level representations, reflecting cross-hierarchical recurrent interactions. The early mask condition disrupted this coordination, highlighting the essential role of recurrent processing. These findings clarify the temporal dynamics of recurrent processing in occluded object recognition and emphasize the critical role of recurrence in achieving robust biological vision.
- Open Access
- 8 February 2026
- Published by Springer Nature in Journal of NeuroEngineering and Rehabilitation
- Vol. 23  (1)
Prognosis prediction of patients with disorders of consciousness based on digital twin brain models
The accurate prediction of prognosis in patients with disorders of consciousness (DOC) is a significant challenge in clinical practice. Some studies based
- 8 February 2026
- Published by Springer Nature in Journal of NeuroEngineering and Rehabilitation
- Vol. 23  (1)
Open AccessPrognosis prediction of patients with disorders of consciousness based on digital twin brain models
The accurate prediction of prognosis in patients with disorders of consciousness (DOC) is a significant challenge in clinical practice. Some studies based
- 1 February 2025
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 22  (1) , 016034
Improving pre-movement patterns detection with multi-dimensional EEG features for readiness potential decrease
Objective. The readiness potential (RP) is an important neural characteristic in motor preparation-based brain–computer interface. In our previous research, we observed a significant decrease of the RP amplitude in some cases, which severely affects the pre-movement patterns detection. In this paper, we aimed to improve the accuracy (Acc) of pre-movement patterns detection in the condition of RP decrease. Approach. We analyzed multi-dimensional EEG features in terms of time–frequency, brain networks, and cross-frequency coupling (CFC). And, a multi-dimensional Electroencephalogram feature combination (MEFC) algorithm was proposed. The features used include: (1) waveforms of the RP; (2) energy in alpha and beta bands; (3) brain network in alpha and beta bands; and (4) CFC value between 2 and 10 Hz. Main results. By employing support vector machines, the MEFC method achieved an average recognition rate of 88.9% and 85.5% under normal and RP decrease conditions, respectively. Compared to classical algorithm, the average Acc for both tasks improved by 7.8% and 8.8% respectively. Significance. This method can effectively improve the Acc of pre-movement patterns decoding in the condition of RP decrease.
- 1 February 2025
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 22  (1) , 016034
Improving pre-movement patterns detection with multi-dimensional EEG features for readiness potential decrease
Objective. The readiness potential (RP) is an important neural characteristic in motor preparation-based brain–computer interface. In our previous research, we observed a significant decrease of the RP amplitude in some cases, which severely affects the pre-movement patterns detection. In this paper, we aimed to improve the accuracy (Acc) of pre-movement patterns detection in the condition of RP decrease. Approach. We analyzed multi-dimensional EEG features in terms of time–frequency, brain networks, and cross-frequency coupling (CFC). And, a multi-dimensional Electroencephalogram feature combination (MEFC) algorithm was proposed. The features used include: (1) waveforms of the RP; (2) energy in alpha and beta bands; (3) brain network in alpha and beta bands; and (4) CFC value between 2 and 10 Hz. Main results. By employing support vector machines, the MEFC method achieved an average recognition rate of 88.9% and 85.5% under normal and RP decrease conditions, respectively. Compared to classical algorithm, the average Acc for both tasks improved by 7.8% and 8.8% respectively. Significance. This method can effectively improve the Acc of pre-movement patterns decoding in the condition of RP decrease.
- 2 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29  (3) , 2222-2232
Real-Time Epileptic Seizure Prediction Method With Spatio-Temporal Information Transfer Learning
The accurate prediction of epileptic seizures is a significant challenge in the field of epilepsy. Despite numerous studies devoted to improving the prediction accuracy, there are still some difficulties in the application of current methods in clinical practice, such as high computational cost, poor real-time performance, and over-reliance on labeled data. To address these issues, a real-time seizure prediction method with spatio-temporal information transfer learning (RTSPM-STITL) has been proposed in this study. In the RTSPM-STITL method, the human brain is regarded as a time-varying high-dimensional neurodynamic system, in which epileptic seizures are viewed as state transitions caused by time-varying system parameters. Specifically, the spatio-temporal information transfer (STIT) model is firstly constructed by the recurrent neural network (RNN) and trained by the Force Learning (a realtime learning mechanism). Then the trained STIT model is utilized to transform the high-dimensional neurodynamic system data into low-dimensional time series to capture the dynamic features of epileptic seizures. Also, the critical slowing down effect (CSD) of the dynamic features of epileptic seizures is utilized to detect seizure warning signals. The experimental results demonstrate that the proposed method can achieve higher accuracy and sensitivity without labeled data on both the CHB-MIT and Siena scalp EEG databases. Especially, the parameters of the STIT model can be updated in real-time based on patient data, without iterative training. More importantly, the STIT model can maintain high sensitivity and accuracy with only 48400 parameters, which is reduced by more than 91% compared with contrast models in this experiment. Therefore, the proposed method can significantly reduce the computational cost and accurately predict epileptic seizures, as well as with high real-time, practicality, applicability, and interpretability.
- 2 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29  (3) , 2222-2232
Real-Time Epileptic Seizure Prediction Method With Spatio-Temporal Information Transfer Learning
The accurate prediction of epileptic seizures is a significant challenge in the field of epilepsy. Despite numerous studies devoted to improving the prediction accuracy, there are still some difficulties in the application of current methods in clinical practice, such as high computational cost, poor real-time performance, and over-reliance on labeled data. To address these issues, a real-time seizure prediction method with spatio-temporal information transfer learning (RTSPM-STITL) has been proposed in this study. In the RTSPM-STITL method, the human brain is regarded as a time-varying high-dimensional neurodynamic system, in which epileptic seizures are viewed as state transitions caused by time-varying system parameters. Specifically, the spatio-temporal information transfer (STIT) model is firstly constructed by the recurrent neural network (RNN) and trained by the Force Learning (a realtime learning mechanism). Then the trained STIT model is utilized to transform the high-dimensional neurodynamic system data into low-dimensional time series to capture the dynamic features of epileptic seizures. Also, the critical slowing down effect (CSD) of the dynamic features of epileptic seizures is utilized to detect seizure warning signals. The experimental results demonstrate that the proposed method can achieve higher accuracy and sensitivity without labeled data on both the CHB-MIT and Siena scalp EEG databases. Especially, the parameters of the STIT model can be updated in real-time based on patient data, without iterative training. More importantly, the STIT model can maintain high sensitivity and accuracy with only 48400 parameters, which is reduced by more than 91% compared with contrast models in this experiment. Therefore, the proposed method can significantly reduce the computational cost and accurately predict epileptic seizures, as well as with high real-time, practicality, applicability, and interpretability.
- 8 November 2024
- Published by Elsevier in Computer Methods and Programs in Biomedicine
- Vol. 258, 108483
Localizing the seizure onset zone and predicting the surgery outcomes in patients with drug-resistant epilepsy: A new approach based on the causal network
- 8 November 2024
- Published by Elsevier in Computer Methods and Programs in Biomedicine
- Vol. 258, 108483
Localizing the seizure onset zone and predicting the surgery outcomes in patients with drug-resistant epilepsy: A new approach based on the causal network
- 19 April 2024
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 95
Vagus nerve stimulation modulating the directed brain network of patients with drug-resistant epilepsy
- 19 April 2024
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 95
Vagus nerve stimulation modulating the directed brain network of patients with drug-resistant epilepsy
- 20 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 28  (6) , 3446-3456
An EEG Study on $\boldsymbol{\upbeta\!\!-\!\!\upgamma}$ Phase-Amplitude Coupling-Based Functional Brain Network in Epilepsy PatientsEpilepsy, a chronic neuropsychiatric brain disorder characterized with recurrent seizures, is closely associated with abnormal neural communications within the brain. Despite that the phase-amplitude coupling (PAC) has been suggested to offer a new way to observe neural interactions during epilepsy, however, few studies pay attention to alterations of the epileptic functional brain network based on PAC, especially on the β-γ PAC. Therefore, we use scalp electroencephalography (EEG) data of epileptic patients and the β-γ PAC modulation index (MI) to construct functional brain networks to examine variations of neural interactions during different epileptic phases. Statistically, the findings show that between-channel MI values in the post-ictal period significantly increase compared to that in the pre-ictal period, and the between-channel MI value has a close association with the information of phase and amplitude provided by the channels. Importantly, in both the phase-amplitude and amplitude-phase functional brain networks, the average node degree is remarkably higher in the post-ictal period than that in the pre-ictal period, whereas the characteristic path length in the ictal and post-ictal periods is significantly lower than that in the pre-ictal period. Besides, the average betweenness centrality in the post-ictal period is remarkably higher than that in the ictal period. Interestingly, the positive correlations between within-channel MI values and between-channel MI values can be observed during the pre-ictal, ictal and post-ictal periods. These findings suggest that the β-γ PAC-based functional brain network may provide a novel perspective to understanding alterations of neural interactions during the epileptic evolution, and may contribute to effectively controlling the spread of epileptic seizures.
- 20 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 28  (6) , 3446-3456
An EEG Study on $\boldsymbol{\upbeta\!\!-\!\!\upgamma}$ Phase-Amplitude Coupling-Based Functional Brain Network in Epilepsy PatientsEpilepsy, a chronic neuropsychiatric brain disorder characterized with recurrent seizures, is closely associated with abnormal neural communications within the brain. Despite that the phase-amplitude coupling (PAC) has been suggested to offer a new way to observe neural interactions during epilepsy, however, few studies pay attention to alterations of the epileptic functional brain network based on PAC, especially on the β-γ PAC. Therefore, we use scalp electroencephalography (EEG) data of epileptic patients and the β-γ PAC modulation index (MI) to construct functional brain networks to examine variations of neural interactions during different epileptic phases. Statistically, the findings show that between-channel MI values in the post-ictal period significantly increase compared to that in the pre-ictal period, and the between-channel MI value has a close association with the information of phase and amplitude provided by the channels. Importantly, in both the phase-amplitude and amplitude-phase functional brain networks, the average node degree is remarkably higher in the post-ictal period than that in the pre-ictal period, whereas the characteristic path length in the ictal and post-ictal periods is significantly lower than that in the pre-ictal period. Besides, the average betweenness centrality in the post-ictal period is remarkably higher than that in the ictal period. Interestingly, the positive correlations between within-channel MI values and between-channel MI values can be observed during the pre-ictal, ictal and post-ictal periods. These findings suggest that the β-γ PAC-based functional brain network may provide a novel perspective to understanding alterations of neural interactions during the epileptic evolution, and may contribute to effectively controlling the spread of epileptic seizures.
- Open Access
- 12 February 2024
- Published by Elsevier in Brain Research Bulletin
- Vol. 208, 110901
MGFKD: A semi-supervised multi-source domain adaptation algorithm for cross-subject EEG emotion recognition
- 12 February 2024
- Published by Elsevier in Brain Research Bulletin
- Vol. 208, 110901
Open AccessMGFKD: A semi-supervised multi-source domain adaptation algorithm for cross-subject EEG emotion recognition
- 1 February 2024
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 21  (1) , 016029
Multilayer network-based channel selection for motor imagery brain–computer interface
Objective. The number of electrode channels in a motor imagery-based brain–computer interface (MI-BCI) system influences not only its decoding performance, but also its convenience for use in applications. Although many channel selection methods have been proposed in the literature, they are usually based on the univariate features of a single channel. This leads to a loss of the interaction between channels and the exchange of information between networks operating at different frequency bands. Approach. We integrate brain networks containing four frequency bands into a multilayer network framework and propose a multilayer network-based channel selection (MNCS) method for MI-BCI systems. A graph learning-based method is used to estimate the multilayer network from electroencephalogram (EEG) data that are filtered by multiple frequency bands. The multilayer participation coefficient of the multilayer network is then computed to select EEG channels that do not contain redundant information. Furthermore, the common spatial pattern (CSP) method is used to extract effective features. Finally, a support vector machine classifier with a linear kernel is trained to accurately identify MI tasks. Main results. We used three publicly available datasets from the BCI Competition containing data on 12 healthy subjects and one dataset containing data on 15 stroke patients to validate the effectiveness of our proposed method. The results showed that the proposed MNCS method outperforms all channels (85.8% vs. 93.1%, 84.4% vs. 89.0%, 71.7% vs. 79.4%, and 72.7% vs. 84.0%). Moreover, it achieved significantly higher decoding accuracies on MI-BCI systems than state-of-the-art methods (paired t-tests, p < 0.05). Significance. The experimental results showed that the proposed MNCS method can select appropriate channels to improve the decoding performance as well as the convenience of the application of MI-BCI systems.
- 1 February 2024
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 21  (1) , 016029
Multilayer network-based channel selection for motor imagery brain–computer interface
Objective. The number of electrode channels in a motor imagery-based brain–computer interface (MI-BCI) system influences not only its decoding performance, but also its convenience for use in applications. Although many channel selection methods have been proposed in the literature, they are usually based on the univariate features of a single channel. This leads to a loss of the interaction between channels and the exchange of information between networks operating at different frequency bands. Approach. We integrate brain networks containing four frequency bands into a multilayer network framework and propose a multilayer network-based channel selection (MNCS) method for MI-BCI systems. A graph learning-based method is used to estimate the multilayer network from electroencephalogram (EEG) data that are filtered by multiple frequency bands. The multilayer participation coefficient of the multilayer network is then computed to select EEG channels that do not contain redundant information. Furthermore, the common spatial pattern (CSP) method is used to extract effective features. Finally, a support vector machine classifier with a linear kernel is trained to accurately identify MI tasks. Main results. We used three publicly available datasets from the BCI Competition containing data on 12 healthy subjects and one dataset containing data on 15 stroke patients to validate the effectiveness of our proposed method. The results showed that the proposed MNCS method outperforms all channels (85.8% vs. 93.1%, 84.4% vs. 89.0%, 71.7% vs. 79.4%, and 72.7% vs. 84.0%). Moreover, it achieved significantly higher decoding accuracies on MI-BCI systems than state-of-the-art methods (paired t-tests, p < 0.05). Significance. The experimental results showed that the proposed MNCS method can select appropriate channels to improve the decoding performance as well as the convenience of the application of MI-BCI systems.