A5083044658- 3D Surveying and Cultural Heritage
- 3D Shape Modeling and Analysis
- Advanced biosensing and bioanalysis techniques
- Remote Sensing and LiDAR Applications
- Biosensors and Analytical Detection
- Robotics and Sensor-Based Localization
- Manufacturing Process and Optimization
- Augmented Reality Applications
- Digital Transformation in Industry
- Advanced Biosensing Techniques and Applications
- Advanced Chemical Sensor Technologies
- Advanced Neural Network Applications
- Advanced Machining and Optimization Techniques
- Inertial Sensor and Navigation
- Industrial Vision Systems and Defect Detection
- BIM and Construction Integration
Xi’an Jiaotong-Liverpool University
2023-2025
University of Liverpool
2025
The present work aims to develop a digital twin system typical of intelligent manufacturing applications, which has integrated visualization technologies, as well the process parameter simulation solution. application under consideration is machining process, with gantry machine tool controlled by Siemens Programmable Logic Controller(PLC) S7-1200. With establishment dual-directional data communication between physical and its virtual counterpart based on TCP/IP protocol, real-time...
The integration of paper-based microfluidics with deep learning represents a pivotal trend in enhancing diagnostic capabilities. This paper introduces new approach to improve the performance microfluidic enzyme-linked immunosorbent assay (ELISA) by training temporal sequence colorimetric data rather than static conventionally, using learning. Traditional learning-assisted ELISA analysis methods usually rely on single snapshot reaction at its end, which limits further improvement sensitivity...
Lateral flow assays (LFAs) are widely used in point-of-care testing (POCT) due to their simplicity and rapid operation. However, reliance on passive capillary limits sensitivity, making it challenging detect low-abundance biomarkers accurately. Approaches such as computer signal processing, chemical modification, physical regulation have been explored improve LFA but they remain limited by capillary-driven uncontrollable rate. An alternative approach is actively regulate fluid dynamics...
The purpose of point cloud place recognition is to convert a into global descriptor which, in aotonomous driving application, can then be used locate the best-matched road scene from entire dataset. However, capturing an arbitrary view by robots or self-driving vehicles often involves rotations scenes, which makes existing deep learning-based methods susceptible errors. To compensate for this, we propose new approach: z-axis (upward direction) rotation-invariant recognition, as along...