Chen Wei
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chen Wei has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Quanying Liu
Southern University of Science and Technology
4 shared publications - Dante Mantini
Movement Control and Neuroplasticity Research Group, KU Leuven, Leuven, 3001, Belgium
2 shared publications - Mingqi Zhao
School of Information Science and Engineering, Lanzhou University, Lanzhou, China
2 shared publications Chenyi Li
Shenzhen Key Laboratory of Smart Healthcare Engineering, Department of Biomedical Engineering, Southern University of Science and Technology, Shenzhen 518055, People’s Republic of China
1 shared publicationChi Zhang
1 shared publicationDeng Haotian
1 shared publication
Latest Publications
- Open Access
- 29 June 2026
- Published by Center for Open Science in PsyArXiv
Controlled real-world object generation for visual memory experimentation and theory-building
Real-world objects are visually rich and semantically structured, but due to this complexity, theories of visual memory are generally tested with more tractable stimulus spaces, such as color. To address the challenge of studying real-world objects with high experimental control,we used a novel generative artificial intelligence (AI) Concept-based Controllable Generation (CoCoG) model, grounded in human similarity judgments, to create systematically structured object spaces. We then combined CoCoG-derived embeddings with a computational model of memory to predict memory error distributions. Across seven online visual-working-memory studies (N = 1,019), we found that these stimuli can be used to investigate established phenomena, such object-state versus -exemplar memory, and new phenomena, specifically memory for novel object morphs. These results build on recent work that bridges generative AI with cognitive modeling and demonstrate how architectures like CoCoG can be used as a methodological and theory-constraining tool for systematically studying real-world visual cognition.
- 29 June 2026
- Published by Center for Open Science in PsyArXiv
Open AccessControlled real-world object generation for visual memory experimentation and theory-building
Real-world objects are visually rich and semantically structured, but due to this complexity, theories of visual memory are generally tested with more tractable stimulus spaces, such as color. To address the challenge of studying real-world objects with high experimental control,we used a novel generative artificial intelligence (AI) Concept-based Controllable Generation (CoCoG) model, grounded in human similarity judgments, to create systematically structured object spaces. We then combined CoCoG-derived embeddings with a computational model of memory to predict memory error distributions. Across seven online visual-working-memory studies (N = 1,019), we found that these stimuli can be used to investigate established phenomena, such object-state versus -exemplar memory, and new phenomena, specifically memory for novel object morphs. These results build on recent work that bridges generative AI with cognitive modeling and demonstrate how architectures like CoCoG can be used as a methodological and theory-constraining tool for systematically studying real-world visual cognition.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 5577-5586
BrainFLORA: Uncovering Brain Concept Representation via Multimodal Neural Embeddings
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 5577-5586
Open AccessBrainFLORA: Uncovering Brain Concept Representation via Multimodal Neural Embeddings
- Top Cited PapersOpen Access
- 1 April 2022
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 19 (2) , 026052
Embedding decomposition for artifacts removal in EEG signals
Objective. Electroencephalogram (EEG) recordings are often contaminated with artifacts. Various methods have been developed to eliminate or weaken the influence of artifacts. However, most of them rely on prior experience for analysis. Approach. Here, we propose an deep learning framework to separate neural signal and artifacts in the embedding space and reconstruct the denoised signal, which is called DeepSeparator. DeepSeparator employs an encoder to extract and amplify the features in the raw EEG, a module called decomposer to extract the trend, detect and suppress artifact and a decoder to reconstruct the denoised signal. Besides, DeepSeparator can extract the artifact, which largely increases the model interpretability. Main results. The proposed method is tested with a semi-synthetic EEG dataset and a real task-related EEG dataset, suggesting that DeepSeparator outperforms the conventional models in both EOG and EMG artifact removal. Significance. DeepSeparator can be extended to multi-channel EEG and data with any arbitrary length. It may motivate future developments and application of deep learning-based EEG denoising. The code for DeepSeparator is available at https://github.com/ncclabsustech/DeepSeparator.
- 1 April 2022
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 19 (2) , 026052
Top Cited PapersOpen AccessEmbedding decomposition for artifacts removal in EEG signals
Objective. Electroencephalogram (EEG) recordings are often contaminated with artifacts. Various methods have been developed to eliminate or weaken the influence of artifacts. However, most of them rely on prior experience for analysis. Approach. Here, we propose an deep learning framework to separate neural signal and artifacts in the embedding space and reconstruct the denoised signal, which is called DeepSeparator. DeepSeparator employs an encoder to extract and amplify the features in the raw EEG, a module called decomposer to extract the trend, detect and suppress artifact and a decoder to reconstruct the denoised signal. Besides, DeepSeparator can extract the artifact, which largely increases the model interpretability. Main results. The proposed method is tested with a semi-synthetic EEG dataset and a real task-related EEG dataset, suggesting that DeepSeparator outperforms the conventional models in both EOG and EMG artifact removal. Significance. DeepSeparator can be extended to multi-channel EEG and data with any arbitrary length. It may motivate future developments and application of deep learning-based EEG denoising. The code for DeepSeparator is available at https://github.com/ncclabsustech/DeepSeparator.
- Top Cited PapersOpen Access
- 1 October 2021
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 18 (5) , 056057
EEGdenoiseNet: a benchmark dataset for deep learning solutions of EEG denoising
Objective.Deep learning (DL) networks are increasingly attracting attention across various fields, including electroencephalography (EEG) signal processing. These models provide comparable performance to that of traditional techniques. At present, however, there is a lack of well-structured and standardized datasets with specific benchmark limit the development of DL solutions for EEG denoising.Approach.Here, we present EEGdenoiseNet, a benchmark EEG dataset that is suited for training and testing DL-based denoising models, as well as for performance comparisons across models. EEGdenoiseNet contains 4514 clean EEG segments, 3400 ocular artifact segments and 5598 muscular artifact segments, allowing users to synthesize contaminated EEG segments with the ground-truth clean EEG.Main results.We used EEGdenoiseNet to evaluate denoising performance of four classical networks (a fully-connected network, a simple and a complex convolution network, and a recurrent neural network). Our results suggested that DL methods have great potential for EEG denoising even under high noise contamination.Significance.Through EEGdenoiseNet, we hope to accelerate the development of the emerging field of DL-based EEG denoising. The dataset and code are available athttps://github.com/ncclabsustech/EEGdenoiseNet.
- 1 October 2021
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 18 (5) , 056057
Top Cited PapersOpen AccessEEGdenoiseNet: a benchmark dataset for deep learning solutions of EEG denoising
Objective.Deep learning (DL) networks are increasingly attracting attention across various fields, including electroencephalography (EEG) signal processing. These models provide comparable performance to that of traditional techniques. At present, however, there is a lack of well-structured and standardized datasets with specific benchmark limit the development of DL solutions for EEG denoising.Approach.Here, we present EEGdenoiseNet, a benchmark EEG dataset that is suited for training and testing DL-based denoising models, as well as for performance comparisons across models. EEGdenoiseNet contains 4514 clean EEG segments, 3400 ocular artifact segments and 5598 muscular artifact segments, allowing users to synthesize contaminated EEG segments with the ground-truth clean EEG.Main results.We used EEGdenoiseNet to evaluate denoising performance of four classical networks (a fully-connected network, a simple and a complex convolution network, and a recurrent neural network). Our results suggested that DL methods have great potential for EEG denoising even under high noise contamination.Significance.Through EEGdenoiseNet, we hope to accelerate the development of the emerging field of DL-based EEG denoising. The dataset and code are available athttps://github.com/ncclabsustech/EEGdenoiseNet.
- Open Access
- 18 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Edge Sparse Basis Network: A Deep Learning Framework for EEG Source Localization
EEG source localization is an important technical issue in EEG analysis. Despite many numerical methods existed for EEG source localization, they all rely on strong priors and the deep sources are intractable. Here we propose a deep learning framework using spatial basis function decomposition for EEG source localization. This framework combines the edge sparsity prior and Gaussian source basis, called Edge Sparse Basis Network (ESBN). The performance of ESBN is validated by both synthetic data and real EEG data during motor tasks. The results suggest that the supervised ESBN outperforms the traditional numerical methods in synthetic data and the unsupervised fine-tuning provides more focal and accurate localizations in real data. Our proposed deep learning framework can be extended to account for other source priors, and the real-time property of ESBN can facilitate the applications of EEG in brain-computer interfaces and clinics.
- 18 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Open AccessEdge Sparse Basis Network: A Deep Learning Framework for EEG Source Localization
EEG source localization is an important technical issue in EEG analysis. Despite many numerical methods existed for EEG source localization, they all rely on strong priors and the deep sources are intractable. Here we propose a deep learning framework using spatial basis function decomposition for EEG source localization. This framework combines the edge sparsity prior and Gaussian source basis, called Edge Sparse Basis Network (ESBN). The performance of ESBN is validated by both synthetic data and real EEG data during motor tasks. The results suggest that the supervised ESBN outperforms the traditional numerical methods in synthetic data and the unsupervised fine-tuning provides more focal and accurate localizations in real data. Our proposed deep learning framework can be extended to account for other source priors, and the real-time property of ESBN can facilitate the applications of EEG in brain-computer interfaces and clinics.