Yongsheng Wu

Yongsheng Wu

Auto-generated profile, based on publicly available information

Yongsheng Wu

Shenzhen Center for Disease Control and Prevention, Shenzhen, China

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
1 August 2018 in Robotics and Autonomous Systems
Verified
Journal Article
Closed access
YZYaguang Zhu
Yaguang Zhu
YWYongsheng Wu
Yongsheng Wu
QLQiong Liu
Qiong Liu
TGTong Guo
Tong Guo
RQRui Qin
Rui Qin
JHJizhuang Hui
Jizhuang Hui

20 March 2025 in Journal of Medical Internet Research
Verified
Journal Article
Open access
LWLan Wei
Lan Wei
YWYongsheng Wu
Yongsheng Wu
LCLin Chen
Lin Chen
JCJinquan Cheng
Jinquan Cheng
JZJin Zhao
Jin Zhao
Background: The use of geosocial networking apps is linked to increased risky sexual behaviors among men who have sex with men, but their relationship with HIV and other sexually transmitted infections remains inconclusive. Since 2015, the prevalence of app use among men who have sex with men in Shenzhen has surged, highlighting the need for research on their spatiotemporal and behavioral patterns to inform targeted prevention and intervention strategies. Objective: This study aims to investigate the population size, spatiotemporal and behavioral patterns, and mobility of app-using men who have sex with men in Shenzhen using mobile big data. The goal is to inform enhanced and innovative intervention strategies and guide health resource allocation. Methods: By leveraging mobile big data application technology, we collected demographic and geographic location data from 3 target apps—Blued (Blued Inc), Jack'd (Online Buddies Inc), and Zank (Zank Group)—over continuous time periods. Spatial autocorrelation (Global Moran I) and hot spot analysis (Getis-Ord Gi) were used to identify the geographic clusters. The Geodetector tool (Chinese Academy of Sciences) was adopted to measure spatially stratified heterogeneity features. Results: From September 2017 to August 2018, a total of 158,387 males aged 15-69 years in Shenzhen used one of the 3 apps, with the majority (71,318, 45.03%) aged 25-34 years. The app user-to-male ratio was approximately 2.6% among all males aged 15-69 years. The estimated population of app-using men who have sex with men in Shenzhen during this period was 268,817. The geographic distribution of app-using men who have sex with men in Shenzhen was clustered, with hot spots primarily located in central and western Shenzhen, while the distribution of HIV testing and counseling was more concentrated in central-eastern Shenzhen. Approximately 60,202 (38%) app-using men who have sex with men left Shenzhen during the Spring Festival, and 37,756 (62.7%) of them returned after the holiday. The destination distribution showed a relatively centralized flow throughout the country, with the largest mobility within Guangdong province (67.7%), followed by lower mobility to Hunan province (7.9%) and other neighboring provinces (3%-5%), such as Jiangxi, Guangxi, and Hubei Provinces. Conclusions: Shenzhen has a large population of men who have sex with men. The variation and inconsistent spatiotemporal distribution of app use and HIV testing and counseling emphasize the need to adapt traditional venue-based prevention and intervention to identified hot spots and to launch outreach initiatives that extend beyond traditional healthcare settings. Given the relatively high internal and interprovincial mobility of app-using men who have sex with men, further smartphone-based behavioral monitoring could provide valuable insights for developing enhanced and innovative HIV prevention and intervention strategies. Moreover, our study demonstrates the potential of mobile big data to address critical research gaps often overlooked by traditional methods.

3 December 2024 in JMIR Preprints
Verified
Preprint
Open access
LWLan Wei
Lan Wei
YWYongsheng Wu
Yongsheng Wu
LCLin Chen
Lin Chen
JCJinquan Cheng
Jinquan Cheng
JZJin Zhao
Jin Zhao
BACKGROUND The use of geosocial networking apps is linked to increased risky sexual behaviors among men who have sex with men, but their relationship with HIV and other sexually transmitted infections remains inconclusive. Since 2015, the prevalence of app use among men who have sex with men in Shenzhen has surged, highlighting the need for research on their spatiotemporal and behavioral patterns to inform targeted prevention and intervention strategies. OBJECTIVE This study aims to investigate the population size, spatiotemporal and behavioral patterns, and mobility of app-using men who have sex with men in Shenzhen using mobile big data. The goal is to inform enhanced and innovative intervention strategies and guide health resource allocation. METHODS By leveraging mobile big data application technology, we collected demographic and geographic location data from 3 target apps—Blued (Blued Inc), Jack'd (Online Buddies Inc), and Zank (Zank Group)—over continuous time periods. Spatial autocorrelation (Global Moran I) and hot spot analysis (Getis-Ord Gi) were used to identify the geographic clusters. The Geodetector tool (Chinese Academy of Sciences) was adopted to measure spatially stratified heterogeneity features. RESULTS From September 2017 to August 2018, a total of 158,387 males aged 15-69 years in Shenzhen used one of the 3 apps, with the majority (71,318, 45.03%) aged 25-34 years. The app user-to-male ratio was approximately 2.6% among all males aged 15-69 years. The estimated population of app-using men who have sex with men in Shenzhen during this period was 268,817. The geographic distribution of app-using men who have sex with men in Shenzhen was clustered, with hot spots primarily located in central and western Shenzhen, while the distribution of HIV testing and counseling was more concentrated in central-eastern Shenzhen. Approximately 60,202 (38%) app-using men who have sex with men left Shenzhen during the Spring Festival, and 37,756 (62.7%) of them returned after the holiday. The destination distribution showed a relatively centralized flow throughout the country, with the largest mobility within Guangdong province (67.7%), followed by lower mobility to Hunan province (7.9%) and other neighboring provinces (3%-5%), such as Jiangxi, Guangxi, and Hubei Provinces. CONCLUSIONS Shenzhen has a large population of men who have sex with men. The variation and inconsistent spatiotemporal distribution of app use and HIV testing and counseling emphasize the need to adapt traditional venue-based prevention and intervention to identified hot spots and to launch outreach initiatives that extend beyond traditional healthcare settings. Given the relatively high internal and interprovincial mobility of app-using men who have sex with men, further smartphone-based behavioral monitoring could provide valuable insights for developing enhanced and innovative HIV prevention and intervention strategies. Moreover, our study demonstrates the potential of mobile big data to address critical research gaps often overlooked by traditional methods.

20 October 2023
Verified
Conference Paper
Open access
LWLan Wei
Lan Wei
YLYe Li
Ye Li
JGJianying Guo
Jianying Guo
XLXiang Li
Xiang Li
SMShujiang Mei
Shujiang Mei
TFTiejian Feng
Tiejian Feng
Influenza is a major public health concern, causing significant morbidity and mortality each year. Early and accurate prediction of influenza outbreaks is essential for effective public health intervention. The proposed algorithm will use historical influenza data to identify patterns and trends in influenza outbreaks. The algorithm will then use these patterns and trends to predict future influenza outbreaks. The proposed algorithm will be evaluated using a variety of metrics, including accuracy, precision, recall and F1 score. The results of this research will provide valuable insight into the potential of machine learning algorithms for influenza prediction. This research presents a machine learning algorithm for influenza in Shenzhen, China , using data from the Shenzhen Center of Disease Control and Prevention. The algorithm uses a combination of supervised and unsupervised learning techniques to identify patterns of the data and to make predictions about future influenza outbreaks. The results of the algorithm were compared to the actual influenza cases reported by the Shenzhen Center of Disease Control, and the accuracy of the predictions was evaluated.