Yun Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yun Wang has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Austin Lin Yee
If Medical & Technology Company Limited, Chengdu, China
1 shared publication - Lu Huang
Institute of Microelectronics, Chinese Academy of Sciences, Beijing, China
1 shared publication Yingdong Cao
School of Medicine, Sias University, Xinzheng, Henan, China
1 shared publication
Latest Publications
- Open Access
- 5 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 125557-125570
The Impact of Artificial Intelligence and Deep Learning-Based Family-Centered Care Interventions on the Healing of Chronic Lower Limb Wounds in Children
Currently, there are numerous challenges in the nursing and healing of children’s chronic lower limb wounds (CLLW), such as prolonged healing times, difficulties in pain management, high risk of infection, and insufficient parental caregiving knowledge. This study aims to investigate the impact of a family-centered care (FCC) system based on artificial intelligence (AI) and convolutional neural network (CNN) algorithms on the healing of CLLW. A FCC for Children’s CLLWs (CLLW FCC) system was designed, consisting primarily of four components: an interaction layer, a service layer, a data layer, and a hardware layer. The CNN algorithm was utilized to establish a segmentation method for chronic wound images, which was then applied to the wound management section of the CLLW FCC system, aiming to improve the nursing outcomes of children with CLLW, optimize wound management processes, and enhance the accuracy and efficiency of image processing and analysis. It focused on 92 pediatric patients with CLLW admitted to our hospital from January 2022 to June 2023. The patients were randomly assigned into a control (Con) group and an observation (Obs) group, with 46 cases in each. Patients in the Con group received routine care, while those in the Obs group received FCC system for CLLW. The wound infection rate (WIR), wound healing time (WHT), wound pain scores, parental knowledge scores, and satisfaction with care (SWC) were evaluated for both the Con and Obs groups. The results unveiled that the optimized CNN algorithm achieved mean intersection over union (mIOU) and Kappa values of 0.8965 and 0.8773, respectively, which were higher than those of other algorithms. Patients in the Obs group experienced a shorter WHT and lower wound pain scores in contrast to those in the Con group ( P <0.05). The parental knowledge scores were higher in the Obs group, showing great differences with those in the Con group ( P <0.05). The WIR in the Obs group was 2.17%, lower to 10.87% in the Con group ( P <0.05). Additionally, the overall SWC was 95.65% in the Obs group, being higher to 80.43% in the Con group. This indicated that the FCC system based on AI and CNN algorithms in this work could sharply shorten the pediatric WHT, reduce pain scores and WIR during care, and improve the parental knowledge scores and SWC.
- 5 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 125557-125570
Open AccessThe Impact of Artificial Intelligence and Deep Learning-Based Family-Centered Care Interventions on the Healing of Chronic Lower Limb Wounds in Children
Currently, there are numerous challenges in the nursing and healing of children’s chronic lower limb wounds (CLLW), such as prolonged healing times, difficulties in pain management, high risk of infection, and insufficient parental caregiving knowledge. This study aims to investigate the impact of a family-centered care (FCC) system based on artificial intelligence (AI) and convolutional neural network (CNN) algorithms on the healing of CLLW. A FCC for Children’s CLLWs (CLLW FCC) system was designed, consisting primarily of four components: an interaction layer, a service layer, a data layer, and a hardware layer. The CNN algorithm was utilized to establish a segmentation method for chronic wound images, which was then applied to the wound management section of the CLLW FCC system, aiming to improve the nursing outcomes of children with CLLW, optimize wound management processes, and enhance the accuracy and efficiency of image processing and analysis. It focused on 92 pediatric patients with CLLW admitted to our hospital from January 2022 to June 2023. The patients were randomly assigned into a control (Con) group and an observation (Obs) group, with 46 cases in each. Patients in the Con group received routine care, while those in the Obs group received FCC system for CLLW. The wound infection rate (WIR), wound healing time (WHT), wound pain scores, parental knowledge scores, and satisfaction with care (SWC) were evaluated for both the Con and Obs groups. The results unveiled that the optimized CNN algorithm achieved mean intersection over union (mIOU) and Kappa values of 0.8965 and 0.8773, respectively, which were higher than those of other algorithms. Patients in the Obs group experienced a shorter WHT and lower wound pain scores in contrast to those in the Con group ( P <0.05). The parental knowledge scores were higher in the Obs group, showing great differences with those in the Con group ( P <0.05). The WIR in the Obs group was 2.17%, lower to 10.87% in the Con group ( P <0.05). Additionally, the overall SWC was 95.65% in the Obs group, being higher to 80.43% in the Con group. This indicated that the FCC system based on AI and CNN algorithms in this work could sharply shorten the pediatric WHT, reduce pain scores and WIR during care, and improve the parental knowledge scores and SWC.
- 1 April 2022
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 78 (12) , 14343-14361
Full-convolution Siamese network algorithm under deep learning used in tracking of facial video image in newborns
This study was carried out with the aim of exploring the full-convolution Siamese network (SiamFC) in the application of neonatal facial video image tracking, achieving accurate recognition of neonatal pain and helping doctors evaluate neonatal emotions in an automatic manner. The current technology shows low accuracy on facial image recognition of newborns, so the SiamFC algorithm under the deep learning was optimized in this study. Besides, a newborn facial video image tracking model (FVIT model) was constructed based on the SiamFC algorithm in combination with the attention mechanism with face tracking algorithm, and the facial features of newborns were tracked and recognized. In addition, a newborn face database was constructed based on the adult face database to evaluate performance of the FVIT model. It was found that the accuracy of the improved algorithm is 0.889, higher by 0.036 in contrast to other models; the area under the curve (AUC) of success rate reaches 0.748, higher by 0.075 compared with other algorithms. What’s more, the improved algorithm shows good performance in tracking the facial occlusion, facial expression changes, and scale conversion of newborns. Therefore, the improved algorithm shows higher accuracy and success rate and has good effect in capturing and tracking the facial images of newborns, thereby providing an experimental basis for facial recognition and pain assessment of newborns in the later stage.
- 1 April 2022
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 78 (12) , 14343-14361
Full-convolution Siamese network algorithm under deep learning used in tracking of facial video image in newborns
This study was carried out with the aim of exploring the full-convolution Siamese network (SiamFC) in the application of neonatal facial video image tracking, achieving accurate recognition of neonatal pain and helping doctors evaluate neonatal emotions in an automatic manner. The current technology shows low accuracy on facial image recognition of newborns, so the SiamFC algorithm under the deep learning was optimized in this study. Besides, a newborn facial video image tracking model (FVIT model) was constructed based on the SiamFC algorithm in combination with the attention mechanism with face tracking algorithm, and the facial features of newborns were tracked and recognized. In addition, a newborn face database was constructed based on the adult face database to evaluate performance of the FVIT model. It was found that the accuracy of the improved algorithm is 0.889, higher by 0.036 in contrast to other models; the area under the curve (AUC) of success rate reaches 0.748, higher by 0.075 compared with other algorithms. What’s more, the improved algorithm shows good performance in tracking the facial occlusion, facial expression changes, and scale conversion of newborns. Therefore, the improved algorithm shows higher accuracy and success rate and has good effect in capturing and tracking the facial images of newborns, thereby providing an experimental basis for facial recognition and pain assessment of newborns in the later stage.