A5059840979- Optical measurement and interference techniques
- Advanced Measurement and Metrology Techniques
- 3D Surveying and Cultural Heritage
- 3D Shape Modeling and Analysis
- Organic Light-Emitting Diodes Research
- Industrial Vision Systems and Defect Detection
- Green IT and Sustainability
- Advanced Sensor and Energy Harvesting Materials
- Robotics and Sensor-Based Localization
- Advanced Measurement and Detection Methods
- Conducting polymers and applications
- Image Processing and 3D Reconstruction
- Advanced Text Analysis Techniques
- Organic Electronics and Photovoltaics
- Advanced Numerical Analysis Techniques
- Human Pose and Action Recognition
- Acoustic Wave Phenomena Research
- Advanced Neural Network Applications
- Surface Roughness and Optical Measurements
- Noise Effects and Management
- Video Surveillance and Tracking Methods
- Image and Object Detection Techniques
- Berberine and alkaloids research
- Sentiment Analysis and Opinion Mining
- Advanced Vision and Imaging
Zhejiang Pharmaceutical College
2025
Sichuan University
2022-2024
Xi'an University of Science and Technology
2019
The internal defect detection of magnetic tile is extremely significant before mounting. Currently, this task completely realized by manual operation in the manufacturing industry, which results inefficiency and diseconomy. In work, we develop an intelligent system based on acoustic sound for to overcome these drawbacks. Due non-Gaussian non-stationary characteristics sound, adopting single modality data cannot achieve good accuracy. Therefore, design a multimodal fusion convolutional neural...
Optical measurement methods for blade profiles attract lots of interest in industry. Due to the nature thin-walled and twisted spatial freeform surfaces blades, accuracy would be significantly affected by accumulated error associated with geometric motion stability developed multiview system. To overcome these issues, this article proposes a deep feature interaction network fine registration data. In our network, we design two-branch structure integrate global local extraction branch encode...
Kelisha capsule (KLSC), listed in the Chinese Pharmacopoeia, has been employed for treatment of infectious diarrhea. Nevertheless, precise mechanism KLSC remains to be elucidated. This work was investigate antibacterial mode and therapeutic towards E. coli infected HPLC identified primary chemical constituents KLSC. A model diarrhea induced via injection. The impact on coli-induced evaluated using a score Babl/c mice. integrity intestinal barrier assessed through staining measuring levels...
Automated surface defect detection for products attracts lots of interest in the industry, which is typically an image classification task. Although convolutional neural networks (CNNs) with shift and scale invariance have become de-facto standard such task computer vision, their applications to millimeter-level tiny defects random orientation on dark complex texture magnetic tile remains limited. In this paper, we propose, first time, introducing rotation into convolution by rotating...
Currently, optical-based method provides a feasible means for blade reconstruction and measurement. However, as the key step, multi-view registration is still heavily reliant on measurement system's motion stability geometric accuracy. Moreover, complex high-reflective freeform surface of blades may result in both insufficient overlaps less prominent overlap-area features between adjacent views, making accurate data alignment difficult. Thus, we propose to realize 3-D profiles based scanning...
This Sentiment analysis is mainly found in the user's social platform for a hot event or product point of view and attitude. Most existing sentiment approaches heavily rely on large amount labeled data that usually involve time-consuming error-prone manual annotations. In order to avoid dependence annotation dictionary reduce human intervention machine learning process, this paper, Based researches deep learning, we propose hybrid framework AM-Bi-LSTM combines Attention Mechanism...
The optical measurement and precise 3-D reconstruction of the blade are crucial in ensuring its processing quality. However, complex highly reflective free-form surfaces blades may lead to inadequate overlaps less prominent overlap-area features among multiple scanning data. spatial sampling variance instruments can result different point cloud densities. These make it challenging achieve accurate registration data, which is currently a critical step profiles. To address these issues...
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI