Yu Wei

Dr. Yu Wei


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
11 October 2018 in International Journal of Distributed Sensor Networks
Verified
Journal Article
Open access
PDF file
LJLibin Jiao
Libin Jiao
RBRongfang Bie
Rongfang Bie
HWHao Wu
Hao Wu
YWYu Wei
Yu Wei
JMJixin Ma
Jixin Ma
AKAnton Kos
Anton Kos
The use of smart sports equipment and body sensory systems supervising daily sports training is gradually emerging in professional and amateur sports; however, the problem of processing large amounts of data from sensors used in sport and discovering constructive knowledge is a novel topic and the focus of our research. In this article, we investigate golf swing data classification methods based on varieties of representative convolutional neural networks (deep convolutional neural networks) which are fed with swing data from embedded multi-sensors, to group the multi-channel golf swing data labeled by hybrid categories from different golf players and swing shapes. In particular, four convolutional neural classifiers are customized: “GolfVanillaCNN” with the convolutional layers, “GolfVGG” with the stacked convolutional layers, “GolfInception” with the multi-scale convolutional layers, and “GolfResNet” with the residual learning. Testing on the real-world swing dataset sampled from the system integrating two strain gage sensors, three-axis accelerometer, and three-axis gyroscope, we explore the accuracy and performance of our convolutional neural network–based classifiers from two perspectives: classification implementations and sensor combinations. Besides, we further evaluate the performance of these four classifiers in terms of classification accuracy, precision–recall curves, and F1 scores. These common classification indicators illustrate that our convolutional neural network–based classifiers can basically group the golf swing predefined by the combination of shapes and golf players correctly and outperform support vector machine method representing traditional classification methods.

18 May 2023 in Molecules
Verified
Journal Article
Open access
PDF file
YHYinlong Hou
Yinlong Hou
Kai RenKai Ren
Kai Ren
YWYu Wei
Yu Wei
DYDan Yang
Dan Yang
ZCZhen Cui
Zhen Cui
KWKe Wang
Ke Wang
A biphenylene network is a novel 2D allotropy of carbon with periodic 4-6-8 rings, which was synthesized successfully in 2021. In recent years, although the mechanical properties and thermal transport received a lot of research attention, how to open the Dirac cone in the band structure of a biphenylene network is still a confused question. In this work, we utilized uniaxial and biaxial lattice strains to manipulate the electronic properties and phonon frequencies of biphenylene, and we found an indirect band gap under 10% biaxial strain through the first-principles calculations. This indirect band gap is caused by the competition between the band-edge state A and the Dirac cone for the conduction band minimum (CBM). Additionally, the lightest carrier’s effective mass in biphenylene is 0.184 m0 for electrons along x (Γ→X) direction, while the effective mass for holes shows a remarkable anisotropy, suggesting the holes in the tensile biphenylene monolayer are confined within a one-dimensional chain along x direction. For phonon dispersion, we discovered that the Raman-active Ag3 phonon mode shows a robust single phonon mode character under both compressive and tensile strain, but its frequency is sensitive to lattice strain, suggesting the lattice strain in biphenylene can be identified by Raman spectroscopy

4 April 2022 in Structural Health Monitoring
Verified
Journal Article
Closed access
YWYu Wei
Yu Wei
Xianzhi WangXianzhi Wang
Xianzhi Wang
YXYuanbo Xu
Yuanbo Xu
FFFan Fan
Fan Fan
Fault diagnosis of rotating machinery plays a significant role in the reliability and safety of modern industrial systems, which generally requires collaborative fault diagnosis by features extracted from multiple sensors since the multi-channel vibration signals carry a wealth of fault information. However, there is a remaining obstacle for fault diagnosis of multi-source monitoring data: integration of multisensory data. Hence, a novel framework is proposed for fault diagnosis of multi-source monitoring data. First, composite multivariate multi-scale symbolic dynamic entropy is proposed to extract fault features. Second, Laplacian score is introduced to select the distinguishing features with better clustering ability. Finally, the selected features are fed into a logistic regression classifier so that various faults of machinery are diagnosed. The simulation and two case studies using gearbox and pump data are performed to validate and demonstrate the superiority of the proposed method.

5 May 2023 in Molecules
Verified
Journal Article
Open access
PDF file
YHYinlong Hou
Yinlong Hou
YWYu Wei
Yu Wei
DYDan Yang
Dan Yang
KWKe Wang
Ke Wang
Kai RenKai Ren
Kai Ren
Gang ZhangGang Zhang
Gang Zhang
In this work, we explore the impacts of charge doping on the magnetism of a Cr2Ge2Te6 monolayer using first-principles calculations. Our results reveal that doping with 0.3 electrons per unit cell can enhance the ferromagnetic exchange constant in a Cr2Ge2Te6 monolayer from 6.874 meV to 10.202 meV, which is accompanied by an increase in the Curie temperature from ~85 K to ~123 K. The enhanced ratio of the Curie temperature is up to 44.96%, even higher than that caused by surface functionalization on monolayer Cr2Ge2Te6, manifesting the effectiveness of charge doping by improving the magnetic stability of 2D magnets. This remarkable enhancement in the ferromagnetic exchange constant and Curie temperature can be attributed to the increase in the magnetic moment on the Te atom, enlarged Cr-Te-Cr bond angle, reduced Cr-Te distance, and the significant increase in super-exchange coupling between Cr and Te atoms. These results demonstrate that charge doping is a promising route to improve the magnetic stability of 2D magnets, which is beneficial to overcome the obstacles in the application of 2D magnets in spintronics.

8 September 2023 in Molecules
Verified
Journal Article
Open access
PDF file
YHYinlong Hou
Yinlong Hou
Kai RenKai Ren
Kai Ren
YWYu Wei
Yu Wei
DYDan Yang
Dan Yang
ZCZhen Cui
Zhen Cui
KWKe Wang
Ke Wang
In recent years, the two-dimensional (2D) orthorhombic SiP2 flake has been peeled off successfully by micromechanical exfoliation and it exhibits an excellent performance in photodetection. In this paper, we investigated the mechanical properties and the origin of its anisotropy in an orthorhombic SiP2 monolayer through first-principles calculations, which can provide a theoretical basis for utilizing and tailoring the physical properties of a 2D orthorhombic SiP2 in the future. We found that the Young’s modulus is up to 113.36 N/m along the a direction, while the smallest value is only 17.46 N/m in the b direction. The in-plane anisotropic ratio is calculated as 6.49, while a similar anisotropic ratio (~6.55) can also be observed in Poisson’s ratio. Meanwhile, the in-plane anisotropic ratio for the fracture stress of the orthorhombic SiP2 monolayer is up to 9.2. These in-plane anisotropic ratios are much larger than in black phosphorus, ReS2, and biphenylene. To explain the origin of strong in-plane anisotropy, the interatomic force constants were obtained using the finite-displacement method. It was found that the maximum of interatomic force constant along the a direction is 5.79 times of that in the b direction, which should be considered as the main origin of the in-plane anisotropy in the orthorhombic SiP2 monolayer. In addition, we also found some negative Poisson’s ratios in certain specific orientations, allowing the orthorhombic SiP2 monolayer to be applied in next-generation nanomechanics and nanoelectronics.

2 May 2024 in Structural Health Monitoring
Verified
Journal Article
Closed access
YWYu Wei
Yu Wei
Yongbo LiYongbo Li
Yongbo Li
Xianzhi WangXianzhi Wang
Xianzhi Wang
The impact components induced by faulty bearings can be readily concealed by environmental noise and other interferences due to their inherent weakness, especially during the incipient stages of fault development. A novel approach is presented in this study for the detection of incipient bearing faults, which combines an adaptive fast iterative filtering decomposition (FIFD) method with a modified Laplace of Gaussian filter. The first step involves proposing an adaptive FIFD (AFIFD) method employing improved sparrow search algorithm, enabling adaptive selection of the optimal parameter within the FIFD method. The AFIFD technique is able to adaptively decompose a complicated signal into a set of mono-components. Subsequently, a modified Laplace of Gaussian is used to highlight the fault-related cyclic impulse train from a sensitive mono-component decomposed by the AFIFD method. Finally, the envelope analysis performing on enhanced signals is applied to identify fault characteristic frequencies. Results from some case studies demonstrate that the proposed method is capable of extracting incipient fault signatures. The superiority of the proposed method is further validated through some comparative tests with recently developed fault detection methods.