A5007382298- Spectroscopy and Chemometric Analyses
- Water Quality Monitoring and Analysis
- Spectroscopy Techniques in Biomedical and Chemical Research
- Advanced Chemical Sensor Technologies
- Terahertz technology and applications
- Identification and Quantification in Food
- Meat and Animal Product Quality
- Plant and animal studies
- Industrial Vision Systems and Defect Detection
- Phytochemicals and Antioxidant Activities
- Remote Sensing and Land Use
- Date Palm Research Studies
- Advanced Algorithms and Applications
- Leaf Properties and Growth Measurement
- Postharvest Quality and Shelf Life Management
- Luminescence Properties of Advanced Materials
- Mathematical Analysis and Transform Methods
- Advanced Measurement and Detection Methods
- Remote Sensing in Agriculture
- Powdery Mildew Fungal Diseases
- Textile materials and evaluations
- Smart Agriculture and AI
- Pesticide Residue Analysis and Safety
- Image and Signal Denoising Methods
- Essential Oils and Antimicrobial Activity
East China Jiaotong University
2015-2024
Xidian University
2022
Central Queensland University
2020
Southern California University for Professional Studies
2019
University of Southern California
2019
Dalian University of Technology
2019
Donghua University
2015-2016
Shenyang Aerospace University
2016
Liaoning Shihua University
2012
Hohai University
2011
The application of visible (Vis; 400–750 nm) and near infrared red (NIR; 750–2500 region spectroscopy to assess fruit vegetables is reviewed in context 'point' spectroscopy, as opposed multi- or hyperspectral imaging. Vis targets colour assessment pigment analysis, while NIR has been applied macro constituents (principally water) fresh produce commercial practice, a wide range attributes the scientific literature. This review focusses key issues relevant widespread implementation Vis-NIR...
The automatic detection and identification of fish from underwater videos is great significance for fishery resource assessment ecological environment monitoring. However, due to the poor quality images unconstrained movement, traditional hand-designed feature extraction methods or convolutional neural network (CNN)-based object algorithms cannot meet requirements in real scenes. Therefore, realize recognition localization a complex environment, this paper proposes novel composite framework...
A relationship was established between the soluble solid content (SSC) of navel orange fruit determined by destructive measurement and visible–near infrared diffuse reflectance spectra in wavelength range 350–1800 nm. Multiplicative scatter correction (MSC) standard normal variate (SNV) were applied to spectra, partial least squares regression (PLSR) back propagation neural network (BPNN) based on principal component analysis (PCA) used develop models for predicting SSC intact fruit....
Abstract Background and objectives Current technology of X-ray imaging can recognize hard foreign materials (FMs) such as metal high-density plastic. However, low-density bodies are still a challenge for food quality safety assessment. Materials methods An electromagnetic vibration feeder aided by terahertz time-domain spectroscopy (THz-TDS) was investigated non-destructively detecting tea stalk insect FMs mixed with leaves. Results THz signals were employed directly to develop the K-nearest...
Non-destructive testing of low-density and organic foreign bodies is the main challenge for food safety control. Terahertz time-domain spectroscopy (THz-TDS) imaging technologies were applied to explore feasibility detection insect in finishing tea products. THz-TDS leaves insects demonstrated significant differences terms time domain frequency signals range 0.3-1.0 THz. These corrected by use adaptive iteratively reweighted penalized least squares (AirPLS), asymmetric (AsLS), baseline...
A portable near infrared spectroscopy system was developed for assessing the quality of Nanfeng mandarin fruit. One hundred and fifty-three samples were used to measure performance system. Several pretreatment methods adopted process spectra. Then Support Vector Machine (SVM), Back Propagation Neural Network (BPNN) Partial Least Square (PLS) build models soluble solids content (SSC), titratable acidity (TA), vitamin C surface color. The best results obtained by SVM. correlation coefficient...
The combination of near-infrared spectroscopy and pattern recognition methods, including soft independent modeling class analogy, least squares support machine, extreme learning was employed for textile fabrics classification. cotton, viscose, acrylic, polyamide, polyester, blend fabric cotton-viscose were divided into training prediction sets (60:60) developing models evaluating the classification abilities models. accuracy speed machine compared. Both achieved 100% set. However, performed...
Investigations were initiated to develop terahertz (THz) techniques associated with machine learning methods of generalized regression neural network (GRNN) and back-propagation (BPNN) rapidly measure benzoic acid (BA) content in wheat flour. The absorption coefficient exhibited a maximum peak at 1.94 THz, which generally increased the BA additive. THz spectra transformed into orthogonal principal component analysis (PCA) scores as input vectors GRNN BPNN models. best model was achieved...