Yibai Wang

Yibai Wang

Auto-generated profile, based on publicly available information

Yibai Wang

School of Information Engineering

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

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

Representative Publications

View All Publications
17 May 2022 in Mobile Information Systems
Verified
Journal Article
Open access
PDF file
FZFangqin Zeng
Fangqin Zeng
RTRong Tang
Rong Tang
YWYibai Wang
Yibai Wang
Efficient and accurate personalized recommendation algorithms can effectively improve user experience satisfaction, in order to improve the performance of user personalized recommendation algorithm, this study proposes a user personalized recommendation algorithm based on deep learning network. The algorithm uses Gate Recurrent Unit (GRU) network to build the main model of personalized recommendation algorithm to reduce the influence of over fitting of multi-layer network; The attention mechanism is introduced into GRU network, so that the recommendation model can obtain the feature information of user data more accurately and reduce the influence of irrelevant data on the model; At the same time, due to the introduction of variable length mini-batch allocation method, the model training data is more complete and reliable, which can effectively improve the accuracy of user personalized recommendation. The simulation experiment is based on Amazon dataset and MovieLens dataset. The experimental results show that the proposed method has good personalized recommendation ability.

1 May 2022 in Plasma Sources Science and Technology
Verified
Journal Article
Closed access
ZCZhiyuan Chen
Zhiyuan Chen
YWYibai Wang
Yibai Wang
JRJunxue Ren
Junxue Ren
HTHaibin Tang
Haibin Tang
PWPeng Wu
Peng Wu
MLMin Li
Min Li
A fully kinetic particle-in-cell study is conducted to investigate the ion acceleration mechanisms in an electron-driven magnetic nozzle. All five powers contributing to the axial kinetic energy of ions are derived and evaluated under different magnetic field strength and inlet density profiles. Among them, the electrothermal and electromagnetic acceleration contributes over 98% of the total accelerating power. The dominating acceleration mechanism is found to be the electrothermal acceleration, covering two thirds of the axial accelerating power in the electron-driven magnetic nozzle. The electromagnetic mechanism is found to originate from four sources, among which the major accelerating and decelerating one are the diamagnetic acceleration driven by radial gradient of electron pressure and the E × B mechanism due to the inward ion detachment. The power induced by the viscous-stress of electrons contributes 14%–23% of the decelerating power, indicating the non-negligible influence of finite electron Larmor radius effect on the ion acceleration. Results indicates that the net effect of electromagnetic mechanism can even be decelerating when the magnetic field is too high with a uniform inlet. Finally, the conversion efficiency from the inlet thermal energy to the ion axial kinetic energy is derived and evaluated, which can reach as high as 65.0% under 0.25 T with a Gaussian-profile inlet. Raising the magnetic field to 0.75 T or a uniform inlet will decrease the conversion efficiency.

1 January 2013 in Aerospace Science and Technology
Verified
Journal Article
Closed access
WZWen-Dian Zhang
Wen-Dian Zhang
YWYi-Bai Wang
Yi-Bai Wang
YLYu Liu
Yu Liu

1 May 2023 in International Journal of Engineering and Technology
Verified
Journal Article
Closed access
GLGuodong Luo
Guodong Luo
JHJirong He
Jirong He
TLTianwen Lin
Tianwen Lin
YWYibai Wang
Yibai Wang
Starting from the construction of an intelligent medical and health system for elderly care, it is proposed to use improved Particle Swarm Optimization Algorithm (PSOA) data fusion algorithm, network video surveillance technology, and hardware equipment such as Radio-Frequency Identification (RFID) smart bracelets and intelligent mobile robots to establish a distributed elderly care The intelligent service system collects vital signs, human movements, human posture characteristics, and position change information of the elderly, and uses improved PSOA data fusion algorithm, the data fusion processing of different types of human body information is completed, which not only greatly improves the utilization rate of medical resources for the elderly, but also ensures the data fusion accuracy of human health detection for the elderly. The improved PSOA neural network data fusion results can provide support for the intelligent care of the elderly care institutions.