Jian Li

Jian Li

Auto-generated profile, based on publicly available information

Jian Li

Capital University of Physical Education and Sports, No.11, North Third Ring West Road, Haidian District, Beijing, 100191, China, 86 010 82099489

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
5 August 2024 in Journal of Medical Internet Research
Verified
Journal Article
Open access
JZJinxi Zhang
Jinxi Zhang
ZLZhen LI
Zhen LI
YLYu Liu
Yu Liu
JLJian Li
Jian Li
HQHualong Qiu
Hualong Qiu
ZZZhixiong Zhou
Zhixiong Zhou
Background: Fall detection is of great significance in safeguarding human health. By monitoring the motion data, a fall detection system (FDS) can detect a fall accident. Recently, wearable sensors–based FDSs have become the mainstream of research, which can be categorized into threshold-based FDSs using experience, machine learning–based FDSs using manual feature extraction, and deep learning (DL)–based FDSs using automatic feature extraction. However, most FDSs focus on the global information of sensor data, neglecting the fact that different segments of the data contribute variably to fall detection. This shortcoming makes it challenging for FDSs to accurately distinguish between similar human motion patterns of actual falls and fall-like actions, leading to a decrease in detection accuracy. Objective: This study aims to develop and validate a DL framework to accurately detect falls using acceleration and gyroscope data from wearable sensors. We aim to explore the essential contributing features extracted from sensor data to distinguish falls from activities of daily life. The significance of this study lies in reforming the FDS by designing a weighted feature representation using DL methods to effectively differentiate between fall events and fall-like activities. Methods: Based on the 3-axis acceleration and gyroscope data, we proposed a new DL architecture, the dual-stream convolutional neural network self-attention (DSCS) model. Unlike previous studies, the used architecture can extract global feature information from acceleration and gyroscope data. Additionally, we incorporated a self-attention module to assign different weights to the original feature vector, enabling the model to learn the contribution effect of the sensor data and enhance classification accuracy. The proposed model was trained and tested on 2 public data sets: SisFall and MobiFall. In addition, 10 participants were recruited to carry out practical validation of the DSCS model. A total of 1700 trials were performed to test the generalization ability of the model. Results: The fall detection accuracy of the DSCS model was 99.32% (recall=99.15%; precision=98.58%) and 99.65% (recall=100%; precision=98.39%) on the test sets of SisFall and MobiFall, respectively. In the ablation experiment, we compared the DSCS model with state-of-the-art machine learning and DL models. On the SisFall data set, the DSCS model achieved the second-best accuracy; on the MobiFall data set, the DSCS model achieved the best accuracy, recall, and precision. In practical validation, the accuracy of the DSCS model was 96.41% (recall=95.12%; specificity=97.55%). Conclusions: This study demonstrates that the DSCS model can significantly improve the accuracy of fall detection on 2 publicly available data sets and performs robustly in practical validation.

30 November 2024 in Journal of Medical Internet Research
Verified
Journal Article
Open access
QZQinlong Zhang
Qinlong Zhang
ZLZhen LI
Zhen LI
LJLei Jiang
Lei Jiang
yanan Gaoyanan Gao
yanan Gao
TGTingjun Gong
Tingjun Gong
ZZZhixiong Zhou
Zhixiong Zhou
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Obesity has become one of today's global health challenges. According to the World Health Organisation, in 2022, 2.5 billion adults aged 18 years and older will be overweight, including more than 890 million adults with obesity. Objective: Exercise interventions based on mobile health technology are widely available, but the effectiveness and feasibility of interventions using mobile health apps and exercise watches to improve the physical health of overweight and obese male college students are unknown, and this study compares the effects of online interventions carried out by mobile health technology and offline interventions guided by physical trainers on the physical health of overweight and obese male college students. Methods: This study used a randomised controlled trial with a pre-test post-test design, and participants were randomly divided into an online group, an offline group and a control group. The online group exercised online through the fitness APP, and the offline group was instructed by a professional trainer to exercise offline, and both groups wore sports watches to monitor their activities, and the training content was the same. The control group did not carry out any intervention. Results: At the end of the intervention, the BMI of the online and offline groups decreased by 1.5 kg/m² and 1.6 kg/m², respectively (P<0.01), and the body fat rate decreased by 1.69% in the online group and 1.72% in the offline group (P<0.01). Several physical fitness indicators, such as muscle mass, increased significantly by an average of 1,115.23g in the online group and 1,120.56g in the offline group (P<0.05), and lung capacity improved by 5.2% and 5.5% in the online and offline groups, respectively (P0.05). Additionally, a dose-effect relationship was found between the amount of physical activity and the rate of change in body fat, with a 6.9 per cent increase in the rate of change in body fat for every 1 MET*h increase in moderate-intensity physical activity, and a 5.4 per cent increase in the rate of change in body fat for every 1 MET*h increase in high-intensity physical activity. Conclusions: Exercise intervention based on mobile health technology effectively improves the physical fitness of overweight and obese male college students, and the effect is consistent with offline intervention. There was a significant dose-effect relationship between the amount of physical activity and the rate of change in body fat, which provided a scientific basis for the development of personalised training programmes. Clinical Trial: The study was approved by the Ethics Committee of the Capital Institute of Sports (Code: 2024A063, Approval Date: 2017/12/26) and registered in the Chinese Clinical Trial Registry (Registration No.: ChiCTR2200063892).

25 January 2024 in JMIR Preprints
Verified
Preprint
Open access
JZJinxi Zhang
Jinxi Zhang
ZLZhen LI
Zhen LI
YLYu Liu
Yu Liu
JLJian Li
Jian Li
HQHualong Qiu
Hualong Qiu
ZZZhixiong Zhou
Zhixiong Zhou
BACKGROUND Fall detection is of great significance in safeguarding human health. By monitoring the motion data, a fall detection system (FDS) can detect a fall accident. Recently, wearable sensors–based FDSs have become the mainstream of research, which can be categorized into threshold-based FDSs using experience, machine learning–based FDSs using manual feature extraction, and deep learning (DL)–based FDSs using automatic feature extraction. However, most FDSs focus on the global information of sensor data, neglecting the fact that different segments of the data contribute variably to fall detection. This shortcoming makes it challenging for FDSs to accurately distinguish between similar human motion patterns of actual falls and fall-like actions, leading to a decrease in detection accuracy. OBJECTIVE This study aims to develop and validate a DL framework to accurately detect falls using acceleration and gyroscope data from wearable sensors. We aim to explore the essential contributing features extracted from sensor data to distinguish falls from activities of daily life. The significance of this study lies in reforming the FDS by designing a weighted feature representation using DL methods to effectively differentiate between fall events and fall-like activities. METHODS Based on the 3-axis acceleration and gyroscope data, we proposed a new DL architecture, the dual-stream convolutional neural network self-attention (DSCS) model. Unlike previous studies, the used architecture can extract global feature information from acceleration and gyroscope data. Additionally, we incorporated a self-attention module to assign different weights to the original feature vector, enabling the model to learn the contribution effect of the sensor data and enhance classification accuracy. The proposed model was trained and tested on 2 public data sets: SisFall and MobiFall. In addition, 10 participants were recruited to carry out practical validation of the DSCS model. A total of 1700 trials were performed to test the generalization ability of the model. RESULTS The fall detection accuracy of the DSCS model was 99.32% (recall=99.15%; precision=98.58%) and 99.65% (recall=100%; precision=98.39%) on the test sets of SisFall and MobiFall, respectively. In the ablation experiment, we compared the DSCS model with state-of-the-art machine learning and DL models. On the SisFall data set, the DSCS model achieved the second-best accuracy; on the MobiFall data set, the DSCS model achieved the best accuracy, recall, and precision. In practical validation, the accuracy of the DSCS model was 96.41% (recall=95.12%; specificity=97.55%). CONCLUSIONS This study demonstrates that the DSCS model can significantly improve the accuracy of fall detection on 2 publicly available data sets and performs robustly in practical validation.