P. Lin

ORCID: 0009-0003-3884-8832
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Spectroscopy and Chemometric Analyses
  • Smart Agriculture and AI
  • Meat and Animal Product Quality
  • Integrated Circuits and Semiconductor Failure Analysis
  • Diamond and Carbon-based Materials Research
  • Image Retrieval and Classification Techniques
  • Identification and Quantification in Food
  • VLSI and Analog Circuit Testing
  • Advanced Chemical Sensor Technologies
  • Industrial Vision Systems and Defect Detection
  • Spectroscopy Techniques in Biomedical and Chemical Research
  • Plasma Diagnostics and Applications
  • Water Quality Monitoring and Analysis
  • Metal and Thin Film Mechanics
  • Leaf Properties and Growth Measurement

Beijing Microelectronics Technology Institute
2024

Yancheng Institute of Technology
2014-2018

Zhejiang University
2016

Abstract This study was carried out for rapid and noninvasive determination of the class sorghum species by using manifold dimensionality reduction (MDR) method nonlinear regression least squares support vector machines (LS-SVM) combing with mid-infrared spectroscopy (MIRS) techniques. The methods Durbin Run test augmented partial residual plot (APaRP) were performed to diagnose nonlinearity raw spectral data. MDR isometric feature mapping (ISOMAP), local linear embedding, laplacian...

10.1038/srep19917 article EN cc-by Scientific Reports 2016-01-28

Abstract A novel strategy based on the near infrared hyperspectral imaging techniques and chemometrics were explored for fast quantifying collision strength index of ethylene-vinyl acetate copolymer (EVAC) coverings fields. The reflectance spectral data EVAC was obtained by using meter. analysis equipment employed to measure intensity materials. preprocessing algorithms firstly performed before calibration. random frog successive projection (SP) applied extracting fingerprint wavebands....

10.1038/srep20843 article EN cc-by Scientific Reports 2016-02-15

The defect detection of printed circuit board (PCB) images face challenges such as limited sample number, imbalanced types, and varying reliability. To address these issues, this paper proposes an uncertainty-aware unsupervised model on PCB images, short for U <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> D PCB. proposed method utilizes two U-Net networks to serve the reconstructive sub-network discriminative sub-network, respectively....

10.1109/tim.2024.3386210 article EN IEEE Transactions on Instrumentation and Measurement 2024-01-01
Coming Soon ...