Chunyong Li

Chunyong Li

Auto-generated profile, based on publicly available information

Chunyong Li

Beijing Institute of Radiation Medicine, Beijing, China

Research Focus & Metrics

Academic Career Length

22Years (2005-Present)

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

Representative Publications

View All Publications
30 May 2023 in Frontiers in Physiology
Verified
Journal Article
Open access
DYDuanyang Yuan
Duanyang Yuan
JYJingwei Yue
Jingwei Yue
XXXuefeng Xiong
Xuefeng Xiong
YJYibi Jiang
Yibi Jiang
PZPeng Zan
Peng Zan
CLChunyong Li
Chunyong Li
Introduction: Fatigue is dangerous for certain jobs requiring continuous concentration. When faced with new datasets, the existing fatigue detection model needs a large amount of electroencephalogram (EEG) data for training, which is resource-consuming and impractical. Although the cross-dataset fatigue detection model does not need to be retrained, no one has studied this problem previously. Therefore, this study will focus on the design of the cross-dataset fatigue detection model.Methods: This study proposes a regression method for EEG-based cross-dataset fatigue detection. This method is similar to self-supervised learning and can be divided into two steps: pre-training and the domain-specific adaptive step. To extract specific features for different datasets, a pretext task is proposed to distinguish data on different datasets in the pre-training step. Then, in the domain-specific adaptation stage, these specific features are projected into a shared subspace. Moreover, the maximum mean discrepancy (MMD) is exploited to continuously narrow the differences in the subspace so that an inherent connection can be built between datasets. In addition, the attention mechanism is introduced to extract continuous information on spatial features, and the gated recurrent unit (GRU) is used to capture time series information.Results: The accuracy and root mean square error (RMSE) achieved by the proposed method are 59.10% and 0.27, respectively, which significantly outperforms state-of-the-art domain adaptation methods.Discussion: In addition, this study discusses the effect of labeled samples. When the number of labeled samples is 10% of the total number, the accuracy of the proposed model can reach 66.21%. This study fills a vacancy in the field of fatigue detection. In addition, the EEG-based cross-dataset fatigue detection method can be used for reference by other EEG-based deep learning research practices.

1 September 2023 in Review of Scientific Instruments
Verified
Journal Article
Closed access
PDF file
DYDuanyang Yuan
Duanyang Yuan
JYJingwei Yue
Jingwei Yue
HXHuiyan Xu
Huiyan Xu
YWYuanbo Wang
Yuanbo Wang
PZPeng Zan
Peng Zan
CLChunyong Li
Chunyong Li
Fatigue, one of the most important factors affecting road safety, has attracted many researchers’ attention. Most existing fatigue detection methods are based on feature engineering and classification models. The feature engineering is greatly influenced by researchers’ domain knowledge, which will lead to a poor performance in fatigue detection, especially in cross-subject experiment design. In addition, fatigue detection is often simplified as a classification problem of several discrete states. Models based on deep learning can realize automatic feature extraction without the limitation of researcher’s domain knowledge. Therefore, this paper proposes a regression model combined convolutional neural network and recurrent neural network for electroencephalogram-based (EEG-based) cross-subject fatigue detection. At the same time, a twofold random-offset zero-overlapping sampling method is proposed to train a bigger model and reduce overfitting. Compared with existing results, the proposed method achieves a much better result of 0.94 correlation coefficient (COR) and 0.09 root mean square error (RMSE) in a within-subject experiment design. What is more, there is no misclassification between awake and drowsy states. For cross-subject experiment design, the COR and RMSE are 0.79 and 0.15, respectively, which are close to the existing within-subject results and better than similar cross-subject results. The cross-subject regression model is very important for fatigue detection application since the fatigue indication is more precise than several discrete states and no model calibration is required for a new user. The twofold random-offset zero-overlapping sampling method can also be used as a reference by other EEG-based deep learning research.

1 October 2005 in Optics & Laser Technology
Verified
Journal Article
Closed access
LZLing Zhang
Ling Zhang
CLChunyong Li
Chunyong Li
DLDehua Li
Dehua Li
PLPingxue Li
Pingxue Li
QZQiulin Zhang
Qiulin Zhang
ZZZhiguo Zhang
Zhiguo Zhang

29 October 2024 in The Visual Computer
Verified
Journal Article
Closed access
PDF file
WZWanjun Zhong
Wanjun Zhong
HHHaohao Hu
Haohao Hu
YWYuerong Wang
Yuerong Wang
LLLi Li
Li Li
THTianyu Han
Tianyu Han
PZPeng Zan
Peng Zan

21 July 2026 in Journal of Radiological Protection
Verified
Journal Article
Closed access
BHBotao Hu
Botao Hu
XXXu Xu
Xu Xu
TSTao Sun
Tao Sun
JYJingwei Yue
Jingwei Yue
CLChunyong Li
Chunyong Li
XZXiaomin Zhang
Xiaomin Zhang
Smartphones are widely available and can serve as opportunistic dosimeters in nuclear emergencies. However, the complex internal structures of smartphones lead to neutron moderation, scattering, absorption and gamma-ray self-absorption. These effects may induce substantial errors when conducting activation analysis in a neutron field. This study developed a neutron spectrum unfolding method using Geant4 Monte Carlo simulation with the SAND-II iterative algorithm. An equivalent smartphone model was established to approximate the real sample in both neutron transport and induced gamma-ray emission. The neutron spectrum simulated inside the smartphone was used as the initial input spectrum for unfolding. To verify this method, a smartphone sample was irradiated by a 252 Cf spontaneous fission source, and induced gamma rays from elements such as Au, Ni, Ti, and Al in the smartphone were measured by a high-purity germanium detector. The calculated reaction rates of the corresponding activation reactions agree with experimental values within 5%, and the unfolded neutron spectrum shows less than 2.1% deviation from the reference spectrum in the dose-dominant fast-neutron region. Based on the unfolded spectrum, the derived neutron effective dose rate was 0.761 Sv h −1 , representing a difference of just 2.2% from the reference value.

1 December 2025 in Journal of Radiological Protection
Verified
Journal Article
Closed access
XXXu Xu
Xu Xu
BHBotao Hu
Botao Hu
JYJingwei Yue
Jingwei Yue
CLChunyong Li
Chunyong Li
JNJing Ning
Jing Ning
XZXiaomin Zhang
Xiaomin Zhang
Neutron dose assessment in radiation accidents relies on measuring induced 2 ⁴Na activity via the 23 Na(n, γ ) 2 ⁴Na reaction. However, the effect of body size on neutron moderation, gamma self-absorption, and organ distribution—remains poorly quantified, with conflicting literature reports. To systematically evaluate the body size effect on neutron absorbed dose and 2 ⁴Na yield, four human voxel phantoms of different body sizes (5-, 10-, 15-, and 38 year-old individuals) were irradiated in MCNP simulations with 2 ⁵ 2 Cf and 28 monoenergetic neutron sources (10 −9 –20 MeV) under six geometries. The neutron absorbed dose, induced 2 ⁴Na activity per unit mass, and the conversion coefficients between 24 Na activity per unit mass and neutron absorbed dose were calculated. The results show that body size significantly affects the neutron dose. When the human body is irradiated with 2 ⁵ 2 Cf neutrons under different irradiation geometries, the conversion coefficients between 2 ⁴Na activity per unit mass and neutron absorbed dose are at least 48.3% larger in adults than in 5 year-old children. When the human body is irradiated with monoenergetic neutrons under isotropic irradiation geometry, these conversion coefficients decrease with increasing body size for neutron energies 0.1 MeV. For 10 −9 MeV neutron irradiation, the coefficient for adults is 26.5% smaller than that of 5 year-old children. Conversely, for 20 MeV neutron irradiation, the coefficient for adults is 114.2% larger than that for 5 year-old children.