A5014595536- Industrial Vision Systems and Defect Detection
- Advanced Neural Network Applications
- Viral Infectious Diseases and Gene Expression in Insects
- Metabolomics and Mass Spectrometry Studies
- Bacterial Identification and Susceptibility Testing
- Advanced X-ray and CT Imaging
- Enzyme Structure and Function
- Image and Object Detection Techniques
- Molecular Biology Techniques and Applications
- Non-Destructive Testing Techniques
- Insect and Pesticide Research
- Biosensors and Analytical Detection
- Genomics and Phylogenetic Studies
- bioluminescence and chemiluminescence research
- Yersinia bacterium, plague, ectoparasites research
Sun Yat-sen University
2024-2025
Nanjing University of Aeronautics and Astronautics
2023
ZheJiang Institute For Food and Drug Control
2019-2022
In the testing of chips, defect diagnostics in X-ray images packaging chips is mainly performed by humans, which time-consuming and inefficient. To overcome abovementioned problems, a novel intelligent system based on hybrid deep learning for chip was proposed. The consists four successive stages: image segmentation normalization, reconstruction detection, contour matching, qualification diagnosis. first stage used to localize external contours target remove extraneous backgrounds through...
As a non-destructive detection method, X-rays are widely used in the field of electronic component inspection. However, subsequent defect needs to be completed manually, which leads poor efficiency and low reliability due large number components. To solve above problems, we propose X-ray image method based on deep learning. On one hand, have designed an algorithm for segmentation correction images. other case fewer samples variable forms, only use defect-free training. We unsupervised...
In the manufacturing of chips, accurate and effective detection internal bubble defects chips is essential to maintain product reliability. general, inspection performed manually by viewing X-ray images, which time-consuming less reliable. To solve above problems, an improved defect model YOLO-Xray based on YOLOv5 algorithm for chip images proposed. First, are preprocessed image segmentation construct dataset, namely, CXray. Then, in input stage, K-means++ used re-cluster CXray dataset...
Background Escherichia coli is currently unable to be reliably differentiated from Shigella species by routine matrix-assisted laser desorption ionization-time of flight mass spectrometry (MALDI-TOF MS) analysis. In the present study, a reliable and rapid identification method was established for based on short-term high-lactose culture using MALDI-TOF MS artificial neural networks (ANN). Materials methods The colonies, treated with (Condition 1)/without 2) an in-house developed fluid...
Matrix-assisted laser desorption ionization-time of flight mass spectrometry (MALDI-TOF MS) analysis is a rapid and reliable method for bacterial identification. Classification algorithms, as critical part the MALDI-TOF MS approach, have been developed using both traditional algorithms machine learning algorithms. In this study, that combined helix matrix transformation with convolutional neural network (CNN) algorithm was presented A total 14 species including 58 strains were selected to...
Objective: To detect the pyrogen in CAR-T cells product employing HL60-IL-6 assay. Method: The HL60 were incubated with injection or endotoxin standard for 48 hours. After then, secreted cytokine interleukin-6 (IL-6) from was determined by ELISA. According to four-parameter logistic curve fitted Optical Density (OD) value corresponding IL-6 and concentration, equivalents of content products can be measured. Then, method validated, including limit detection (LOD), quantitation, recovery rate...