A5080213192- Spectroscopy and Chemometric Analyses
- Advanced Chemical Sensor Technologies
- Water Quality Monitoring and Analysis
- Smart Agriculture and AI
- Spectroscopy Techniques in Biomedical and Chemical Research
- Remote Sensing and Land Use
- Remote Sensing in Agriculture
- Identification and Quantification in Food
- Advanced Algorithms and Applications
- Meat and Animal Product Quality
- Remote-Sensing Image Classification
- Leaf Properties and Growth Measurement
- Pesticide Residue Analysis and Safety
- Phytochemicals and Antioxidant Activities
- Advanced Clustering Algorithms Research
- Horticultural and Viticultural Research
- Analytical Chemistry and Chromatography
- Essential Oils and Antimicrobial Activity
- Face and Expression Recognition
- Adsorption and biosorption for pollutant removal
- Biochemical Analysis and Sensing Techniques
- Advanced Sensor and Control Systems
- Insect and Pesticide Research
- Underwater Acoustics Research
- Bee Products Chemical Analysis
Jiangsu University
2016-2025
First Institute of Oceanography
2024-2025
Ministry of Natural Resources
2024-2025
National Engineering Research Center of Electromagnetic Radiation Control Materials
2024
Singapore Management University
2024
Northwest A&F University
2024
Kyushu University
2023
ZheJiang Academy of Agricultural Sciences
2023
Hunan Normal University
2023
State Grid Corporation of China (China)
2022
Northern maize leaf blight is one of the major diseases that endanger health maize. The complex background field and different light intensity make detection more difficult. A multi-scale feature fusion instance method, based on convolutional neural network, proposed to detect blight. technique incorporates three steps data set preprocessing part, fine-tuning network module. In first step, improved retinex used process sets, which successfully solves problem poor effects caused by...
Abstract Sugars are fundamental to plant developmental processes. For fruits, the accumulation and proportion of sugars play crucial roles in development quality attractiveness. In citrus (Citrus reticulata Blanco.), we found that difference sweetness between mature fruits “Gongchuan” its bud sport “Youliang” is related hexose contents. Expression a SuS (sucrose synthase) gene CitSUS5 SWEET (sugars will eventually be exported transporter) CitSWEET6, characterized by transcriptome analysis at...
Abstract BACKGROUND Mold contamination of grains not only contributes to inedible food, resulting in economic losses, but also leads mold humans and livestock, can even be carcinogenic them. Rice, as one the main grain varieties, if stored improperly, is easily susceptible mildew. In order detect total number colonies rice more accurately, a method based on hyperspectral imaging technology was investigated. RESULTS this paper, non‐destructive detection for performed from angle spectral...
Abstract In order to identify the freshness grade of eggs nondestructively and rapidly, hyperspectral imaging technology was used in this article. The data 200 samples three grades acquired by using image acquisition system (400.68–1,001.612 nm), then egg measured stoichiometry. First, Mahalanobis distance algorithm remove abnormal sample data. Second, savitzky–golay wavelet threshold denoising combined with standard normalized variable were pretreat spectral data, respectively. Third,...
Apple diseases cause a lot of economic losses to fruit growers in China. Early diagnosis and accurate recognition apple can control the spread disease reduce production costs. However, significance characteristic leaves complex environment is relatively weak, fine-grain among different high, conventional feature extraction methods will lose discrimination information. To solve these problems, an classification model based on multi-scale fusion proposed this paper. Firstly, information flow...
Abstract The potential of hyperspectral imaging system was evaluated for the rapid identification rice origin. 240 samples from four different regions C hina were imaged by a system. Hyperspectral images studied three principal aspects (spectral, morphological and texture features). Support vector machine used developing models. Seven models based on spectral, morphological, texture, combined spectral features developed seeking optimal feature combination. Nine important wavelengths...
Hierarchical carbon materials with ultrahigh specific surface area were synthesized by KOH activation from sustainable α-cellulose and employed as adsorbents for the effective removal of tetracycline (TC) sulfamethazine (SMZ) water.
Abstract In this study, a method for quantitative determination of rice moisture based on hyperspectral imaging technology was proposed. First, the system in spectral range 871–1766 nm used to collect images 120 samples 10 grades. Support vector regression (SVR), least‐squares support (LS‐SVR), and bacterial colony chemotaxis (BCC‐LS‐SVR) models were established determine content by using full wavelengths spectra data. Among all models, BCC‐LS‐SVR model showed best results. To simplify...
The impact of bank branch expansion on macroeconomic and micro-firm behaviour has been one the primary focuses in related research fields. However, thus far ignored unintended increased availability credit resources firms' pollution emissions. Therefore, based firm-level data China, we explore firm reduction. empirical results this study are as follows. (1) Increased to firms can significantly reduce This finding remains robust after a series robustness tests. (2) possible path reduced...
Maturity is a crucial indicator in assessing the quality of tomatoes, and it closely related to lycopene content. Using hyperspectral imaging, this study aimed monitor tomato maturity predict its content at different stages. Standard normal variable (SNV) transformation was applied preprocess data. Then, using competitive adaptive reweighted sampling (CARS), characteristic wavelengths were selected simplify calibration models. Based on full wavelengths, support vector classifier (SVC) model...