Search

Your search keyword '"Xue, Chenyang"' showing total 1,087 results
Start Over Author "Xue, Chenyang"
1,087 results on '"Xue, Chenyang"'

1. Topological Feature Search Method for Multichannel EEG: Application in ADHD classification

Author

Cai, Tianming, Zhao, Guoying, Zang, Junbin, Zong, Chen, Zhang, Zhidong, and Xue, Chenyang

Subjects
Computer Science - Machine Learning, Electrical Engineering and Systems Science - Signal Processing, Statistics - Applications
Abstract

In recent years, the preliminary diagnosis of Attention Deficit Hyperactivity Disorder (ADHD) using electroencephalography (EEG) has garnered attention from researchers. EEG, known for its expediency and efficiency, plays a pivotal role in the diagnosis and treatment of ADHD. However, the non-stationarity of EEG signals and inter-subject variability pose challenges to the diagnostic and classification processes. Topological Data Analysis (TDA) offers a novel perspective for ADHD classification, diverging from traditional time-frequency domain features. Yet, conventional TDA models are restricted to single-channel time series and are susceptible to noise, leading to the loss of topological features in persistence diagrams.This paper presents an enhanced TDA approach applicable to multi-channel EEG in ADHD. Initially, optimal input parameters for multi-channel EEG are determined. Subsequently, each channel's EEG undergoes phase space reconstruction (PSR) followed by the utilization of k-Power Distance to Measure (k-PDTM) for approximating ideal point clouds. Then, multi-dimensional time series are re-embedded, and TDA is applied to obtain topological feature information. Gaussian function-based Multivariate Kernel Density Estimation (MKDE) is employed in the merger persistence diagram to filter out desired topological feature mappings. Finally, persistence image (PI) method is utilized to extract topological features, and the influence of various weighting functions on the results is discussed.The effectiveness of our method is evaluated using the IEEE ADHD dataset. Results demonstrate that the accuracy, sensitivity, and specificity reach 85.60%, 83.61%, and 88.33%, respectively. Compared to traditional TDA methods, our method was effectively improved and outperforms typical nonlinear descriptors. These findings indicate that our method exhibits higher precision and robustness.

Published
2024

6. Interpretable CNN-Multilevel Attention Transformer for Rapid Recognition of Pneumonia from Chest X-Ray Images

Author

Chen, Shengchao, Ren, Sufen, Wang, Guanjun, Huang, Mengxing, and Xue, Chenyang

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning
Abstract

Chest imaging plays an essential role in diagnosing and predicting patients with COVID-19 with evidence of worsening respiratory status. Many deep learning-based approaches for pneumonia recognition have been developed to enable computer-aided diagnosis. However, the long training and inference time makes them inflexible, and the lack of interpretability reduces their credibility in clinical medical practice. This paper aims to develop a pneumonia recognition framework with interpretability, which can understand the complex relationship between lung features and related diseases in chest X-ray (CXR) images to provide high-speed analytics support for medical practice. To reduce the computational complexity to accelerate the recognition process, a novel multi-level self-attention mechanism within Transformer has been proposed to accelerate convergence and emphasize the task-related feature regions. Moreover, a practical CXR image data augmentation has been adopted to address the scarcity of medical image data problems to boost the model's performance. The effectiveness of the proposed method has been demonstrated on the classic COVID-19 recognition task using the widespread pneumonia CXR image dataset. In addition, abundant ablation experiments validate the effectiveness and necessity of all of the components of the proposed method., Comment: Accepted by the IEEE Journal of Biomedical and Health Informatic, doi: 10.1109/JBHI.2023.3247949

Published
2022
Full Text
View/download PDF

17. Ligand recognition and G protein coupling of the human itch receptor MRGPRX1

Author

Guo, Lulu, Zhang, Yumu, Fang, Guoxing, Tie, Lu, Zhuang, Yuming, Xue, Chenyang, Liu, Qi, Zhang, Minghui, Zhu, Kongkai, You, Chongzhao, Xu, Peiyu, Yuan, Qingning, Zhang, Chao, Liu, Lei, Rong, Naikang, Peng, Shengxuan, Liu, Yuan, Wang, Chuanzheng, Luo, Xin, Lv, Zongyao, Kang, Dongwei, Yu, Xiao, Zhang, Cheng, Jiang, Yi, Dong, Xinzhong, Zhou, Jiuyao, Liu, Zhongmin, Yang, Fan, Eric Xu, H., and Sun, Jin-Peng

Published
2023
Full Text
View/download PDF

27. Fluid dynamics of controllable synthesis of micro-fine powder particles using Taylor-Couette flow reactors

Author

Xue, Chenyang

Subjects
620.1, TJ Mechanical engineering and machinery
Abstract

Synthesis of fine particles is widely encountered in many applications. Typical examples can be found in fabrication of pigments, ceramics, pharmaceuticals and bio-chemicals among others. During the whole process of particle synthesis, one particle will engage several periods such as nucleation, particle growth, aggregation and breakage. The reaction environment provided by chemical reactors plays a crucial role in particle synthesis. The control of particle properties such as size and morphology are mostly determined by the control of fluid dynamics in the reactors. Therefore, the purpose of this PhD research is to investigate the fluid dynamics in Taylor-Couette (TC) flow reactors for the application of controllable synthesis of micro-fine powder particles. The main work and outcomes can be summarised as: (1) In chapter 2, CFD modelling, flow visualization and conductivity experiment are performed to investigate the mixing behaviour with the adoption of non-circular cylinder. It shows that the use of non-circular inner cylinder can significantly improve macro-mixing throughout the reactor. Mass transfer is therefore enhanced and provides a better environment for micro-mixing between the embedded turbulent eddies in the Taylor vortices. As a result, the micro-mixing has been improved over the whole reactor. Such improvement on micro and macro-mixing behaviour implies that the production of micro particles can be effectively controlled when using a Taylor-Couette flow reactor for synthesis. (2) Following the work of Chapter 2, Chapter 3 is focused on the local fluid dynamics in a large Taylor Couette reactor. Particle Image Velocimetry (PIV) method is used to reveal the shear turbulence and hydrodynamics in the reactor. It is shown that centrifugal force has a larger influence in the flow patterns. In such cases, the instabilities are easily initiated so that the flow patterns experience huge changes. Gravity force due to vertical alignment of the reactor influences the flow both in its normal (radical) and parallel (axial) direction. The Taylor vortex structures tends to deform along the height as the spatial correlation coefficients along the axial direction still exhibit a regularly periodic pattern but gradually reduces. This change reflects the deformation of Taylor vortices. (3) In Chapter 4, by using PIV, the applications of rough surface and non-circular inner cylinder have very different influence on the vortex structures and shear turbulence generated in the Taylor Couette flow reactor. The adoption of the non-circular inner cylinder apparently changes the vortices in large scales. Turbulence is strongly enhanced using the non-circular inner cylinder but less enhancement was found for the use of the rough surface inner cylinder. The main effects of rough surface on the shear turbulence are that the spatial distribution of turbulence characters in the vicinity of the inner cylinder have changed their distribution. High turbulent kinetic energy (TKE) and high TKE dissipation rate region are not always to appear in the same locations due to strong convection. (4) Based on the basic understanding of fluid dynamics and mixing behaviour from Chapter 3 and Chapter 4, an example of the effect of fluid dynamics on synthesis of micro particles, barium sulphate particles are tracked using the Euler-Lagrange approach with consideration of the particle growth in the synthesis process with particle size changes with time. The particle trajectories change dramatically for particles when particle size changes with time. The particle trajectories tracked in the circular and non-circular inner cylinder Taylor-Couette flow reactors present helical movement but are entrapped and affected by the presence of Taylor vortices. The calculated dispersion coefficient for both types of inner cylinder Taylor-Couette flow reactors indicates that particle dispersion, especially in the axial direction, is not always improved by adoption of the non-circular inner cylinder. To sum up, this PhD work mainly provides a fundamental study focused on the characterization of fluid dynamics which affects particle synthesis process. Flow visualization, mixing experiment, PIV and CFD are used to study the key fluid dynamic characteristics in both circular and non-circular Taylor-Couette reactor. The main implication is that characters which affects particle synthesis process such as mixing, shear strain and particle dispersion can be better controlled by adopting non-circular inner cylinder Taylor Couette reactor. Meanwhile, various length scale turbulent eddies embedded in the Taylor vortices have is strongly affected by inner cylinder boundary conditions, thus influence the control and performance of the reactor. Focus should be placed on the key characters of flow which affects actual particle synthesis process when using the Taylor-Couette reactors.

Published
2021

Catalog

Books, media, physical & digital resources
See catalog results