Jiarong Chen

Mr. Jiarong Chen

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
5 May 2022 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
JCJiarong Chen
Jiarong Chen
YZYingfang Zheng
Yingfang Zheng
YLYingshan Liang
Yingshan Liang
ZZZehui Zhan
Zehui Zhan
MJMingzhe Jiang
Mingzhe Jiang
Victor Hugo C. AlburquerqueVictor Hugo C. Alburquerque
Victor Hugo C. Alburquerque
Atrial fibrillation (AF) is a serious medical condition of the heart potentially leading to stroke, which can be diagnosed by analyzing electrocardiograms (ECG). Technologies of Artificial Intelligence of Things (AIoT) enable smart abnormality detection by analyzing streaming healthcare data from the sensor end of users. Analyzing streaming data in the cloud leads to challenges of response latency and privacy issues, and local inference by a model deployed on the user end brings difficulties in model update and customization. Therefore, we propose an AIoT Platform with AF recognition neural networks on the sensor edge with model retraining ability on a resource-constrained embedded system. To this aim, we proposed to combine simple but effective neural networks and an ECG feature selection strategy to reduce computing complexity while maintaining recognition performance. Based on the platform, we evaluated and discussed the performance, response time, and requirements for model retraining in the scenario of AF detection from ECG recordings. The proposed lightweight solution was validated with two public datasets and an ECG data stream simulation on an ATmega2560 processor, proving the feasibility of analysis and training on edge.

6 December 2022 in Expert Systems with Applications
Verified
Journal Article
Closed access
JCJiarong Chen
Jiarong Chen
MJMingzhe Jiang
Mingzhe Jiang
XZXianbin Zhang
Xianbin Zhang
DSDaniel S. da Silva
Daniel S. da Silva
Victor Hugo C. AlburquerqueVictor Hugo C. Alburquerque
Victor Hugo C. Alburquerque
Wanqing WuWanqing Wu
Wanqing Wu

30 April 2024 in Biomedical Signal Processing and Control
Verified
Journal Article
Closed access
ZZZehui Zhan
Zehui Zhan
JCJiarong Chen
Jiarong Chen
KLKangming Li
Kangming Li
LHLinfei Huang
Linfei Huang
LXLin Xu
Lin Xu
WWWanqing Wu
Wanqing Wu

14 February 2024 in Applied Soft Computing
Verified
Journal Article
Closed access
JCJiarong Chen
Jiarong Chen
XZXianbin Zhang
Xianbin Zhang
LXLin Xu
Lin Xu
Victor Hugo C. AlburquerqueVictor Hugo C. Alburquerque
Victor Hugo C. Alburquerque
Wanqing WuWanqing Wu
Wanqing Wu

13 October 2025 in Sensors
Verified
Journal Article
Open access
PDF file
MWMin Wang
Min Wang
WSWenqi Shi
Wenqi Shi
JZJianyu Zhang
Jianyu Zhang
JCJiarong Chen
Jiarong Chen
QLQingliang Lin
Qingliang Lin
GWGuoxing Wang
Guoxing Wang
Cardiovascular disease (CVD) remains the leading cause of global mortality, highlighting the need for continuous vital sign monitoring. Photoplethysmography (PPG) is well suited for wearable devices. Smart rings, benefiting from dense capillary distribution and minimal tissue interference, can capture high-quality PPG signals with comfort, making them a promising next-generation wearable. However, ring rotation relative to the finger alters the optical path, especially for multi-wavelength light, thus reducing accuracy. This paper proposes a rotation-robust PPG sensor for smart rings. Monte Carlo simulations analyze photon transmission under different LED–photodiode (PD) angles, showing that at ±60°, green, red, and infrared light achieve optimal penetration into the microcirculation layer. Considering non-ideal conditions, the green-light angle is adjusted to ±30°, and a symmetrical sensor design is adopted. A prototype smart ring is developed, capable of recording 4-channel PPG, 3-axis acceleration, and 4-channel temperature signals at 100, 25, and 0.2 Hz, respectively. The system achieves reliable PPG acquisition with only 0.59 mA average current consumption. In continuous testing, heart rate estimation reached mean absolute errors of 0.82, 0.79, and 0.78 bpm for green, red, and IR light. The results provide a reference for future smart ring development.

25 December 2024 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
LHLinfei Huang
Linfei Huang
JCJiarong Chen
Jiarong Chen
XZXianbin Zhang
Xianbin Zhang
ZLZhen Li
Zhen Li
LXLin Xu
Lin Xu
Wanqing WuWanqing Wu
Wanqing Wu
The Electrocardiogram (ECG) is a crucial tool for cardiac health monitoring, but existing ECG monitoring systems often lack effective signal conditioning coordination between hardware (HW) and software (SW), resulting in poor signal quality and monitoring effectiveness. To address this issue, this study presents a novel single-arm ECG monitoring system based on the Internet of Things that comprehensively considers both hardware and software aspects. The system mainly consists of an ECG measurement device and a signal reconstruction algorithm. For the device, impedance matching circuits and pre-amplifier circuits were specially designed to measure the weak single-arm ECG signal. Additionally, to improve wearing comfort, a metal dry electrode and an armband were developed. On the software side, an ECG signal reconstruction algorithm based on a diffusion model is proposed, and the reverse process of the diffusion model and the noise prediction model are improved according to the characteristics of the ECG signal. The feasibility of the system was verified through monitoring experiments conducted in real environments on healthy subjects and heart disease patients. The experimental results show that the proposed measurement device is capable of long-term ECG monitoring and that the signal reconstruction algorithm effectively removes various real-world noises. The R-wave detection precision, sensitivity, and F1-score of the reconstructed signal improved from 75.90% to 85.87%, 69.16% to 83.40%, and 72.37% to 84.62%, respectively. This demonstrates that the system provides a new solution for efficient cardiac monitoring in daily life. The open-source code is available at https://github.com/CHENJIAR3/ECG_Denoising/tree/Linfei.