Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Cai Chen has a total of 82 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    EEG Subject Identification and Open-Set Rejection Across Paradigms

    by Cai Chen, Danyang Lv, Jiazheng Sun, Lijun Liu, Shuxian Li, Mufeng Pan, Chongxuan Tian, Zhi Li, Fengxia Wu, Ningling Zhang, et al.

    Objective: To compare electroencephalography (EEG)-based subject-identification and open-set rejection performance across experimental paradigms while examining model robustness and cross-session generalization. Methods: The M3CV database was analyzed across resting state, transient sensory stimulation, steady-state sensory stimulation, P300 Oddball, and motor execution. Closed-set identification was evaluated across feature representations, conventional machine-learning models, and raw-EEG deep-learning baselines. Open-set performance was further assessed using an identity-first leakage-free nested procedure with 60 enrolled identities, 15 development unknown identities, and 20 final-test unknown identities. Results: Under the P4 within-session protocol, transient sensory stimulation achieved the highest Rank-1 accuracy (98.10%). Differential entropy and shrinkage linear discriminant analysis achieved mean Rank-1 accuracies of 98.01% and 98.29%, respectively. Under leakage-free nested open-set evaluation, transient sensory stimulation achieved DIR@FPIR = 5%, DIR@FPIR = 1%, and AU-OSCR values of 91.75%, 77.32%, and 97.36%, respectively. Deep-learning analyses confirmed strong within-session identity discrimination but showed model-dependent open-set paradigm rankings. In contrast, strict cross-session transfer produced marked degradation across all model families, with Rank-1 accuracy falling to approximately 1.9–5.4% and verification AUC to approximately 0.53–0.56; unsupervised target normalization provided little recovery. Conclusions: EEG paradigms exhibited strong but largely session-dependent identity discriminability. Transient sensory stimulation provided the most favorable within-session open-set performance under the primary conventional framework, whereas cross-session variability dominated paradigm-dependent differences under zero-shot transfer.

  • Open Access

    Pandemic-Associated Shifts and Spatial Inequality in Public Attention to Pulmonary Function Testing in China: A 14-Year Baidu Index Study

    by Cai Chen, Dedong Ma, Tao Jing

    Background/Objectives: Pulmonary function tests (PFTs), especially spirometry, are important for chronic respiratory disease diagnosis and management, but Baidu-based online search interest in PFT-related information remains insufficiently characterized. This study examined long-term Baidu search activity for a selected PFT-related keyword in China from 2011 to 2024, with attention to pandemic-period changes, provincial variation, spatial inequality, and associated socioeconomic factors. Methods: We analyzed Baidu Index data from 1 January 2011 to 31 December 2024. The selected PFT-related keyword, “pulmonary function instrument,” was compared with “blood pressure monitor” and “blood glucose meter.” Daily Baidu Index values were aggregated into monthly and annual series. Temporal trends, relative search-intensity ratios, interrupted time-series analysis, inequality indices, fixed-effects regression, subgroup heterogeneity, and convergence dynamics were assessed. Results: PFT-related Baidu search activity remained lower than that for blood pressure and glucose monitoring, with relative search-intensity ratios below 0.35. Descriptively, PFT-related searches increased during 2020–2022; however, the re-specified seasonality-adjusted ITSA using unsmoothed monthly observations did not provide strong statistical evidence for an immediate level change at pandemic onset or a sustained slope change. Provincial differences persisted, with higher values generally observed in several eastern coastal provinces. Inequality indices were lower on average during 2020–2022 but fluctuated over time, and beta-convergence analyses provided limited statistical evidence of systematic catch-up among initially low-index provinces. Urbanization, per capita GDP, and population aging were positively associated with PFT-related Baidu Index values, while subgroup findings were interpreted as exploratory ecological associations. Conclusions: PFT-related Baidu search activity in China remained lower than search activity for blood pressure and glucose monitoring and showed persistent provincial variation. These findings suggest lower visibility of PFT-related information within the Baidu-based online environment.

  • Open Access

    Interpretable Spectral Features for Cross-Session EEG Biometric Identification and Verification

    by Cai Chen, Jiazheng Sun, Danyang Lv, Chongxuan Tian, Shuxian Li, Ningling Zhang, Tao Jing

    Electroencephalogram (EEG)-based biometric sensing provides a promising pathway for secure and user-specific human authentication, but practical deployment remains limited by cross-session non-stationarity and potentially optimistic evaluation protocols caused by window- or event-level leakage. This study developed a cross-session EEG biometric sensing framework using interpretable spectral features and target-session calibration, with trial-level non-overlapping data partitioning to prevent overlap between training, calibration, and blind-test sets. Multi-channel EEG events were segmented into non-overlapping 2 s windows and aggregated into event-level samples to ensure strict isolation among training, validation, calibration, and blind testing subsets. Power spectral density, differential entropy, and log-variance features were evaluated using support vector machine, linear discriminant analysis, logistic regression, random forest, and a compact convolutional neural network designed for EEG decoding (EEGNet). Both closed-set identification and biometric verification were assessed using Rank-N accuracy, cumulative match characteristic curves, macro-F1, equal error rate, area under the curve, and true acceptance rate (TAR) at fixed false acceptance rate (FAR) levels. In the in-house cross-day dataset, limited target-session calibration improved Rank-1 accuracy from 44.82% to 98.70% for support vector machine (SVM) and from 19.93% to 99.94% for linear discriminant analysis (LDA). SVM with differential entropy achieved an equal error rate (EER) of 1.04 ± 0.60%, area under the receiver operating characteristic curve (AUC) of 0.9985 ± 0.0008, and TAR@FAR = 0.1% of 98.44 ± 1.06%. External validation on the public multi-session motor imagery dataset confirmed the calibration benefit. These results demonstrate strong closed-set identification and score-level verification performance under a cohort-wide, calibration-assisted cross-session experimental protocol.

  • Open Access

    Rapid Nasal Breathing as a Biometric Trigger: High‐Accuracy Electroencephalogram‐Based Authentication for Clinical Applications

    by Cai Chen, Xianghong Kong, Danyang Lv, Xiangwei Meng, Chongxuan Tian, Zhi Li, Fengxia Wu, Ningling Zhang, Dedong Ma

    Background: Traditional biometric systems are vulnerable to forgery, highlighting the need for secure alternatives. Electroencephalography (EEG) offers inherent advantages in liveness detection and antispoofing but typically requires external stimuli. We propose a novel paradigm leveraging intrinsic respiratory‐evoked EEG signals for identity authentication, with potential applications in clinical settings where unobtrusive monitoring is critical. Methods: We developed a 64‐channel EEG acquisition system with synchronized respiratory event monitoring. Thirteen healthy volunteers performed four breathing patterns: oral, nasal, slow nasal, and rapid nasal breathing. A hybrid deep learning model was designed to optimize spatial–temporal feature extraction from EEG signals. Results: The model achieved 98.3% accuracy in identity recognition using rapid nasal breathing‐evoked EEG, outperforming traditional biometric methods. Nasal breathing patterns consistently yielded higher accuracy than oral breathing, with rapid nasal breathing showing the strongest discriminative power. Conclusions: Respiratory‐evoked EEG signals provide a viable, noninvasive biometric identifier. The high accuracy of rapid nasal breathing opens avenues for clinical integration, such as continuous patient authentication in respiratory monitoring devices or secure access to electronic health records.


  • Open Access

    MF-AHFNet: A Fatigue Driving Detection Method Based on Multi-Feature Asymptotic Hierarchical Fusion Network

    by Jiazheng Sun, Cai Chen, Lijun Liu, Danyang Lv, Xikun Zhang, Oluwarotimi Williams Samuel, Ningling Zhang, Fulai Peng

  • Open Access

    Ensemble Extreme Learning Machine Method for Hemoglobin Estimation Based on PhotoPlethysmoGraphic Signals

    by Fulai Peng, Ningling Zhang, Cai Chen, Fengxia Wu, Weidong Wang

    Non-invasive detection of hemoglobin (Hb) concentration is of great clinical value for health screening and intraoperative blood transfusion. However, the accuracy and stability of non-invasive detection still need to be improved to meet clinical requirement. This paper proposes a non-invasive Hb detection method using ensemble extreme learning machine (EELM) regression based on eight-wavelength PhotoPlethysmoGraphic (PPG) signals. Firstly, a mathematical model for non-invasive Hb detection based on the Beer-Lambert law is established. Secondly, the captured eight-channel PPG signals are denoised and fifty-six feature values are extracted according to the derived mathematical model. Thirdly, a recursive feature elimination (RFE) algorithm is used to select the features that contribute most to the Hb prediction. Finally, a regression model is built by integrating several independent ELM models to improve prediction stability and accuracy. Experiments conducted on 249 clinical data points (199 cases as the training dataset and 50 cases as the test dataset) evaluate the proposed method, achieving a root mean square error (RMSE) of 1.72 g/dL and a Pearson correlation coefficient (PCC) of 0.76 (p < 0.01) between predicted and reference values. The results demonstrate that the proposed non-invasive Hb detection method exhibits a strong correlation with traditional invasive methods, suggesting its potential for non-invasive detection of Hb concentration.


  • Open Access

    Asthma prevalence based on the Baidu index and China's Health Statistical Yearbook from 2011 to 2020 in China

    by Yahui Li, Ping Wang, Xuekun Shao, Fulai Peng, Danyang Lv, Haitao Du, Yi Wang, Xingchen Wang, Fengxia Wu, Cai Chen

    Background: Due to environmental pollution, changes in lifestyle, and advancements in diagnostic technology, the prevalence of asthma has been increasing over the years. Although China has made early efforts in asthma epidemiology and prevention, there is still a lack of unified and comprehensive epidemiological research within the country. The objective of the study is to determine the nationwide prevalence distribution of asthma using the Baidu Index and China's Health Statistical Yearbook.Methods: Based on China's Health Statistical Yearbook, we analyzed the gender and age distribution of asthma in China from 2011 to 2020, as well as the length of hospitalization and associated costs. By utilizing the Baidu Index and setting the covering all 31 provinces and autonomous regions in China, we obtained the Baidu Index for the keyword 'asthma'. Heatmaps and growth ratios described the prevalence and growth of asthma in mainland China.Results: The average expenditure for discharged asthma (standard deviation) patients was ¥5,870 (808). The average length of stay (standard deviation) was 7.9 (0.38) days. During the period of 2011 to 2020, hospitalization expenses for asthma increased while the length of hospital stay decreased. The proportion of discharged patients who were children under the age of 5 were 25.3% (2011), 19.4% (2012), 16% (2013), 17.9% (2014), 13.9% (2015), 11.3% (2016), 10.2% (2017), 9.4% (2018), 8.1% (2019), and 7.2% (2020), respectively. The prevalence of asthma among boys was higher than girls before the age of 14. In contrast, the proportion of women with asthma was larger than men after the age of 14. During the period from 2011 to 2020, the median [The first quartile (Q1)-the third quartile (Q3)] daily asthma Baidu index in Guangdong, Beijing, Jiangsu, Sichuan, and Zhejiang were 419 (279–476), 328 (258–376), 315 (227–365), 272 (166–313), and 312 (233–362) respectively. Coastal regions showed higher levels of attention toward asthma, indicating a higher incidence rate. Since 2014, there has been a rapid increase in the level of attention toward asthma, with the provinces of Qinghai, Sichuan, and Guangdong experiencing the fastest growth.Conclusion: There are regional variations in the prevalence of asthma among different provinces in China, and the overall prevalence of asthma is increasing.


  • The Contrastive Network With Convolution and Self-Attention Mechanisms for Unsupervised Cell Segmentation

    by Yuhang Zhao, Xianhao Shao, Cai Chen, Junlin Song, Chongxuan Tian, Wei Li

    Deep learning for cell instance segmentation is a significant research direction in biomedical image analysis. The traditional supervised learning methods rely on pixel-wise annotation of object images to train the models, which is often accompanied by time-consuming and labor-intensive. Various modified segmentation methods, based on weakly supervised or semi-supervised learning, have been proposed to recognize cell regions by only using rough annotations of cell positions. However, it is still hard to achieve the fully unsupervised in most approaches that the utilization of few annotations for training is still inevitable. In this paper, we propose an end-to-end unsupervised model that can segment individual cell regions on hematoxylin and eosin (H&E) stained slides without any annotation. Compared with weakly or semi-supervised methods, the input of our model is in the form of raw data without any identifiers and there is no need to generate pseudo-labelling during training. We demonstrated that the performance of our model is satisfactory and also has a great generalization ability on various validation sets compared with supervised models. The ablation experiment shows that our backbone has superior performance in capturing object edge and context information than pure CNN or transformer under our unsupervised method.


  • Open Access

    Prevalence, Economic Burden, and Neurophenotype of Asthma

    by Cai Chen, Guoqing Zhao, Danyang Lv, Jianpeng An, Chongxuan Tian, Yuhang Zhao, Ningling Zhang, Xingwei Wang, Xikun Zhang, Fulai Peng

    Asthma has become a serious global public health issue affecting approximately 14% of children worldwide. Asthma patients often accompany various mental disorders, such as depression, anxiety, and panic attacks, which could aggravate asthma symptoms. It can be summarized that in addition to pathological cellular and molecular immune processes, asthma also has a neural phenotype. The first part of this review summarizes the prevalence and economic burden of asthma in recent years. Then, the neurophenotype of asthma is described in terms of brain structural changes, molecular expression, and prevalence. Our literature search shows that the frontal lobe plays an essential role in asthma-related neurophenotypes. Finally, we assume that an electroencephalogram signal could be one of the directions of asthma neurophenotype diagnosis.