Yunyi Jiang

Yunyi Jiang

Auto-generated profile, based on publicly available information

Yunyi Jiang

State Key Laboratory of Bioelectronics, School of Instrument Science and Engineering, Southeast University, Nanjing, China

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
27 January 2025 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
YJYunyi Jiang
Yunyi Jiang
ZXZhijun zhijun Xiao
Zhijun zhijun Xiao
YZYuwei Zhang
Yuwei Zhang
CMCaiyun Ma
Caiyun Ma
CYChenxi Yang
Chenxi Yang
CLChengyu Liu
Chengyu Liu
Noncontact capacitive electrocardiogram (cECG) is gaining recognition in cardiovascular disease monitoring for its comfort and non-invasiveness. Compared to the conventional ECG, cECG signal quality is prone to degradation in practical applications due to motion artifacts and power line interference (PLI). This study proposed an optimized signal quality assessment method to identify and remove low-quality cECG signals. Firstly, the human body-electrode interface is modeled to analyze the generation mechanism and influence of cECG motion artifacts and PLI. Then, distinct signal quality indices (SQIs) are proposed to target the characteristics of these interferences. Moreover, optimized cECG features and previously proposed ECG features were combined as multi-features and presented to XGBoost for binary classification training. Finally, Shapley Additive Explanations (SHAP) were utilized for feature optimization to reduce redundant information. Validation on a labelled noncontact cECG database yields an impressive binary classification accuracy of 98.786 %, F1-score of 98.845 %, and kappa of 97.567 %. Moreover, its performance on a subject-independent validation set is also excellent, with an accuracy of 99.130 %, an F1-score of 96.937 %, and a kappa of 96.430 %. The optimized multi-features also demonstrate favorable performance in a triple classification model. The experimental results show that our method offers a precise and convenient solution for cECG signal quality assessment.

25 August 2025 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
ZXZhijun zhijun Xiao
Zhijun zhijun Xiao
Maarten De VosMaarten De Vos
Maarten De Vos
Christos ChatzichristosChristos Chatzichristos
Christos Chatzichristos
YJYunyi Jiang
Yunyi Jiang
MZMinghui Zhao
Minghui Zhao
CLChengyu Liu
Chengyu Liu
In recent years, the demand for smart healthcare solutions have heightened the need for accuracy, reliability, and comfort in bedside ECG recording and analysis. This study presents a bedside non-direct contact ECG recording system based on capacitive coupling electrocardiography (cECG) and verifies its performance in accurately capturing Heart Rate Variability (HRV) during the night. Firstly, cECG collects ECG data through clothing, avoiding skin irritation from conventional wet electrodes. Secondly, leveraging the unique characteristics of cECG signals, a deep learning framework assesses the quality of cECG, filtering noise and identifying off-bed information, enhancing HRV analysis precision. Subsequently, the system was employed to recording sleep data from 6 subjects overnight, with our proposed algorithm utilized for signal quality assessment (SQA) and HRV analysis. Finally, HRV features were compared with synchronously collected wet electrode ECG signals, encompassing time domain features, frequency domain features, and nonlinear features, totaling 13 HRV features. Experimental findings demonstrate that for the SQA task, the model achieved a classification accuracy of 94.7%, with a Recall of 0.941, Precision of 0.940, F1 score of 0.941, and Cohen's Kappa of 0.927. The accuracy of on/off-bed monitoring reached 99.79%. Additionally, HRV features showed a strong correlation with the reference ECG. In the time-domain metrics, the largest mean absolute percentage error (MAPE) is for PNN50, with a value of 8.148%. In the frequency-domain features, the largest MAPE is for HF, with a value of 13.253%. For nonlinear features, the largest MAPE is for SD1, with a value of 5.182%. Generally, the system exhibited a reliable solution for cECG recording, on/off-bed status detection, and bedside HRV analysis.

28 May 2025 in Expert Systems with Applications
Verified
Journal Article
Closed access
ZXZhijun zhijun Xiao
Zhijun zhijun Xiao
MVMaarten De Vos
Maarten De Vos
CCChristos Chatzichristos
Christos Chatzichristos
KDKejun Dong
Kejun Dong
YJYunyi Jiang
Yunyi Jiang
CLChengyu Liu
Chengyu Liu

1 January 2026 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Verified
Journal Article
Open access
YJYunyi Jiang
Yunyi Jiang
JZJing Zhang
Jing Zhang
ZXZhijun Xiao
Zhijun Xiao
PFPanyu Fan
Panyu Fan
XWXinhong Wang
Xinhong Wang
CLChengyu Liu
Chengyu Liu