Xiaochan Wang

Dr. Xiaochan Wang

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
8 September 2025 in IEEE Access
Verified
Journal Article
Open access
XWXiaochan Wang
Xiaochan Wang
LWLiyun Wang
Liyun Wang
PLPeifang Liu
Peifang Liu
The growing need for digitally preserving the cultural heritage of ethnic minorities has positioned the accurate segmentation and innovative utilization of traditional patterns as a pivotal challenge in both technological and cultural preservation domains. To tackle this challenge, a novel method for segmenting low-resolution batik patterns (MAR-Net) is proposed, and its potential applications in cultural and creative product design are investigated. Specifically, an adaptive rectangular convolution (ARConv) mechanism is incorporated into the conventional U-Net architecture to effectively capture the intricate and diverse texture features of batik patterns, while the AR-Net network is developed to facilitate improved feature extraction and the integration of local and global information. To further enhance segmentation precision, a mask attention mechanism (MaskAttention) is utilized to strengthen the network’s focus on critical regions, thereby improving detail restoration and pattern segmentation through dynamic adjustment of feature weights. To improve the model’s robustness and discriminative capacity, a composite loss function is formulated, integrating pixel-level cross-entropy loss with instance-contrast-based attention loss to enhance the discriminative power of the feature space. In terms of application, accurately segmented batik patterns are converted into resources for cultural and creative product design, and a digital batik pattern resource library is created, with the potential for incorporating traditional patterns into the AIGC creation process being explored. Experimental results indicate that the proposed MAR-Net method not only markedly enhances precision in low-resolution pattern segmentation tasks but also exhibits substantial potential for application in cultural and creative product design, offering a novel solution for the digital preservation and innovative utilization of batik patterns, thereby significantly contributing to the study and preservation of traditional ethnic minority arts.

1 October 2025 in Biomimetics
Verified
Journal Article
Open access
PDF file
XWXiaochan Wang
Xiaochan Wang
CCCheolhee Cho
Cheolhee Cho
PZPeng Zhang
Peng Zhang
SGShuyuan Ge
Shuyuan Ge
JCJiadi Chen
Jiadi Chen
Hand rehabilitation exoskeletons play a critical role in restoring motor function in patients with stroke or hand injuries. However, most existing designs rely on fixed-axis assumptions, neglecting the rolling–sliding coupling of finger joints that causes instantaneous center of rotation (ICOR) drift, leading to kinematic misalignment and localized pressure concentrations. This study proposes the Instant Radius Method (IRM) based on medical imaging to continuously model ICOR trajectories of the MCP, PIP, and DIP joints, followed by the construction of an equivalent ICOR through curve fitting. Crossing-type biomimetic kinematic pairs were designed according to the equivalent ICOR and integrated into a three-loop ten-linkage exoskeleton capable of dual DOFs per finger (flexion–extension and abduction–adduction, 10 DOFs in total). Kinematic validation was performed using IMU sensors (Delsys) to capture joint angles, and interface pressure distribution at MCP and PIP was measured using thin-film pressure sensors. Experimental results demonstrated that with biomimetic kinematic pairs, the exoskeleton’s fingertip trajectories matched physiological trajectories more closely, with significantly reduced RMSE. Pressure measurements showed a reduction of approximately 15–25% in mean pressure and 20–30% in peak pressure at MCP and PIP, with more uniform distributions. The integrated framework of IRM-based modeling–equivalent ICOR–biomimetic kinematic pairs–multi-DOF exoskeleton design effectively enhanced kinematic alignment and human–machine compatibility. This work highlights the importance and feasibility of ICOR alignment in rehabilitation robotics and provides a promising pathway toward personalized rehabilitation and clinical translation.