Shu-Ping Chen

Shu-Ping Chen

Auto-generated profile, based on publicly available information

Shu-Ping Chen

Health Science Center, School of Biomedical Engineering, Shenzhen University, Shenzhen, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
18 May 2022 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Verified
Journal Article
Open access
RFRuiqi Fu
Ruiqi Fu
YCYi-Feng Chen
Yi-Feng Chen
YHYongqi Huang
Yongqi Huang
SCShuping Chen
Shuping Chen
FDFeiyan Duan
Feiyan Duan
CCChunqi Chang
Chunqi Chang
Electroencephalography (EEG) is widely used for mental stress classification, but effective feature extraction and transfer across subjects remain challenging due to its variability. In this paper, a novel deep neural network combining convolutional neural network (CNN) and adversarial theory, named symmetric deep convolutional adversarial network (SDCAN), is proposed for stress classification based on EEG. The adversarial inference is introduced to automatically capture invariant and discriminative features from raw EEG, which aims to improve the classification accuracy and generalization ability across subjects. Experiments were conducted with 22 human subjects, where each participant’s stress was induced by the Trier Social Stress Test paradigm while EEG was collected. Stress states were then calibrated into four or five stages according to the changing trend of salivary cortisol concentration. The results show that the proposed network achieves improved accuracies of 87.62% and 81.45% on the classification of four and five stages, respectively, compared to conventional CNN methods. Euclidean space data alignment approach (EA) was applied and the improved generalization ability of EA-SDCAN across subjects was also validated via the leave-one-subject-out-cross-validation, with the accuracies of four and five stages being 60.52% and 48.17%, respectively. These findings indicate that the proposed SDCAN network is more feasible and effective for classifying the stages of mental stress based on EEG compared with other conventional methods.

Verified
Journal Article
Open access
PDF file
LYLu-Chen Yeh
Lu-Chen Yeh
SCShu-Ping Chen
Shu-Ping Chen
FLFang-Hsuean Liao
Fang-Hsuean Liao
TWTe-Haw Wu
Te-Haw Wu
YHYu-Ting Huang
Yu-Ting Huang
SLShu-Yi Lin
Shu-Yi Lin
The progress of wound regeneration relies on inflammation management, while neovascular angiogenesis is a critical aspect of wound healing. In this study, the bioactive core and corona synergism of quantized gold (QG) were developed to simultaneously address these complicated issues, combining the abilities to eliminate endotoxins and provide oxygen. The QG was constructed from ultrasmall nanogold and a loosely packed amine-based corona via a simple process, but it could nonetheless eliminate endotoxins (a vital factor in inflammation also called lipopolysaccharides) and provide oxygen in situ for the remodeling of wound sites. Even while capturing endotoxins through electrostatic interactions, the catalytic active sites inside the nanogold could maintain its surface accessibility to automatically transform the overexpressed hydrogen peroxide in hypoxic wound regions into oxygen. Since the inflammatory stage is an essential stage of wound healing, the provision of endotoxin clearance by the outer organic corona of the QG could slow inflammation in a way that subsequently promoted two other important stages of wound bed healing, namely proliferation and remodeling. Relatedly, the efficacy of two forms of the QG, a liquid form and a dressing form, was demonstrated at wound sites in this study, with both forms promoting the development of granulation, including angiogenesis and collagen deposition. Thus, the simply fabricated dual function nanocomposite presented herein not only offers reduced batch-to-batch variation but also increased options for homecare treatments.