Xuepeng Huang

Xuepeng Huang

Auto-generated profile, based on publicly available information

Xuepeng Huang

Department of Mechanical and Electrical Engineering, Xiamen University, Xiamen 361005, China

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

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

Representative Publications

View All Publications
27 August 2023 in Journal of Manufacturing Processes
Verified
Journal Article
Closed access
ZWZiwei Wu
Ziwei Wu
JSJianyun Shen
Jianyun Shen
XWXian Wu
Xian Wu
YPYunfeng Peng
Yunfeng Peng
SLShaolong Lin
Shaolong Lin
LHLinbin Huang
Linbin Huang

5 December 2023
Verified
Conference Paper
Closed access
XHXuepeng Huang
Xuepeng Huang
ZHZexuan Hao
Zexuan Hao
YPYu Pan
Yu Pan
WDWeibei Dou
Weibei Dou
Pre-processing is a fundamental step for any tasks reliant on scalp EEG data. The presence of various artifacts in acquired EEG data, which mask the expected features of brain activity, underscores the pivotal role of artifact removal in pre-processing. Recently, deep learning methods have demonstrated superior efficacy in artifact removal compared to conventional methods such as regression, classical filtering, and signal decomposition. While EEG signals, characterized as time series, differ from extensively explored modalities like photos or videos in multimodal machine learning, a suitable network architecture is necessary for the utilization of deep learning methods in EEG artifact removal tasks. Therefore, in this study, we propose a neural network architecture utilizing self-learned state distinction criteria for time series segmentation and tested its artifact removal performance on semi-simulated and real EEG datasets. Notably, our proposed network architecture outperforms the state-of-the-art network in artifact removal performance. Furthermore, the proposed model demonstrates acceptable real-time processing capabilities, thus highlighting its potential applications in real clinical and research settings as an online pre-processing step.

13 November 2021 in Micromachines
Verified
Journal Article
Open access
PDF file
XHXuepeng Huang
Xuepeng Huang
Zhenzhong WangZhenzhong Wang
Zhenzhong Wang
BSBingyi Shen
Bingyi Shen
PLPengli Lei
Pengli Lei
Laser fusion research requires a large number of high-precision large-diameter aspherical components. To improve the grinding efficiency in the component production process, the manual operation time during the grinding process needs to be reduced. The grinding process requires the installation of the dressed grinding wheel onto the grinding machine spindle, and the off-line dressing results in installation errors during the loading and unloading process, which requires more time for manual alignment. To achieve self-aligning, the circumferential contour of the grinding wheel was first restored by the reversal method, then noise reduction and circle fitting were performed to obtain the eccentricity value and eccentricity position between the flange and the spindle, and finally, the flange was adjusted finely by three piezoelectric actuators installed inside the flange to reduce the eccentricity. Three repetitive experiments were conducted to verify that the self-aligning flange can reduce the eccentricity value by retracting the piezoelectric actuators so that the proper alignment between the flange and the spindle could meet the requirements; the average eccentricity value of the three experiments decreased by 74%, which greatly improved the efficiency of the grinding wheel alignment.

30 March 2012 in Advanced Science Letters
Verified
Journal Article
Closed access
JLJianhui Lin
Jianhui Lin
JCJin Chen
Jin Chen
THTianshu Huang
Tianshu Huang
XHXuepeng Huang
Xuepeng Huang

24 October 2026 in The International Journal of Advanced Manufacturing Technology
Verified
Journal Article
Closed access
PDF file
BZBo Zhong
Bo Zhong
PLPengli Lei
Pengli Lei
XZXiaoping Zheng
Xiaoping Zheng
WDWenhui Deng
Wenhui Deng
FFFei Fan
Fei Fan
XHXuepeng Huang
Xuepeng Huang