- Spectroscopy and Chemometric Analyses
- Smart Agriculture and AI
- Advanced Chemical Sensor Technologies
- Water Quality Monitoring and Analysis
- Spectroscopy Techniques in Biomedical and Chemical Research
- Meat and Animal Product Quality
- Peanut Plant Research Studies
- Remote Sensing in Agriculture
- Phytochemicals and Antioxidant Activities
- GABA and Rice Research
- Tea Polyphenols and Effects
- Tree Root and Stability Studies
- Sensor Technology and Measurement Systems
- Seed and Plant Biochemistry
- Food composition and properties
- 3D Surveying and Cultural Heritage
- Advanced Neural Network Applications
- Leaf Properties and Growth Measurement
- Fermentation and Sensory Analysis
- Handwritten Text Recognition Techniques
- Food Chemistry and Fat Analysis
- Turfgrass Adaptation and Management
- Robotics and Sensor-Based Localization
- Date Palm Research Studies
- Agricultural Engineering and Mechanization
Guangdong Academy of Agricultural Sciences
2020-2025
Oklahoma State University
2023-2024
Key Laboratory of Guangdong Province
2023
Lingnan Normal University
2023
South China Agricultural University
2018-2020
The viability and vigor of crop seeds are crucial indicators for evaluating seed quality, high-quality can increase agricultural yield. conventional methods assessing time consuming, destructive, labor intensive. Therefore, a rapid nondestructive technique testing has great potential benefits agriculture. In this study, single-kernel Fourier transform near-infrared (FT-NIR) spectroscopy with wavelength range 1000-2500 nm was used to distinguish viable nonviable supersweet corn seeds. Various...
Seed purity is a key indicator of crop seed quality. The conventional methods for cultivar identification are time-consuming, expensive, and destructive. Fourier transform near-infrared (FT-NIR) spectroscopy combined with discriminant analyses, was studied as rapid nondestructive technique to classify the cultivars sweet corn seeds. Spectra range 1000–2500 nm collected from 760 seeds two were used analyses. Thereafter, 126 feature wavelengths identified 1557 using genetic algorithm (GA)...
The accurate assessment of peanut seed plumpness is crucial for optimizing production and quality. current method mainly manual visual inspection, which very time-consuming causes deterioration. A novel imaging technique used to enhance the detection fullness using a non-destructive soft X-ray, suitable analysis surface or thin layer material. overall grayscale similar background, edge blurred. inaccuracy segmentation leads low accuracy detection. To improve in detecting seeds, based on...
For sheet metals, anisotropy is a significant property affecting metal forming processes. The of metals caused by the rolling process, and several anisotropic constitutive models have been proposed under non-associated flow rule to describe deformation stress anisotropies independently. However, most them are based on yield functions that only identified experimental data orthogonal axes, or applicable plane state. In this study, yld2004-18p function, which can be used analyze...
TSSC is one of the most important factors affecting loquat flavor, consumer satisfaction, and market competitiveness. To improve ability to assess loquats, a method leveraging near-infrared spectroscopy explainable artificial intelligence was proposed. The 900–1700 nm 156 fresh samples collected preprocessed using seven preprocessing techniques, significant wavelength extraction utilizing six feature methods eliminate data redundancy. Linear nonlinear models were employed establish...
Abstract Reading recognition for pointer-type pressure gauges based on computer vision is significant realizing unmanned monitoring and automatic calibration. Typical methods significantly rely identifying the scale ring pointer because they primarily obtain reading from angular displacement of pointer. For widely used economical gauges, errors can be caused by certain inherent defects, such as misalignment pointer’s rotation center center, which are insensitive to human eyes but fatal...
There are parasites found on sashimi which can cause a series of health problems to those who consume them. Because the too small be visible naked eye, labor and time-consuming use microscope is required for detection. This study proposes near-infrared (VIS/NIR) hyperspectral imaging method quickly intelligently detect in sashimi. The research results show that VIS/NIR spectrums fish meat parasite images were different at certain wavelengths. ability probabilistic neural network (PNN)...
Visible/near-infrared (VIS/NIR) spectroscopy is a powerful tool for rapid, nondestructive fruit quality detection. This technology has been widely applied detection of small, thin-peeled fruit, though less so large, thick-peeled due to weak spectral signal resulting in reduction accuracy. More modeling work should be focused on solving this problem. “Shatian” pomelo traditional Chinese and granulation water loss are two major internal factors that influence its storage quality. However,...
The traditional method used to determine the moisture content of tea leaves is time consuming and destructive. To address this problem, an effective non-destructive prediction based on near-infrared spectroscopy (NIRS) proposed in paper. This new combines discrete wavelet transforms (DWT) with bootstrap soft shrinkage algorithm (BOSS). eliminate uninformative or interfering variables, DWT applied remove noise spectral data by decomposing origin spectrum into six layers. BOSS select...
Visible/near-infrared (VIS/NIR) spectroscopy is a powerful tool for rapid, nondestructive fruit quality detection. This technology has been widely applied detection of small thin-peel fruit, although less so large thick-peel because the low signal-to-noise ratio spectral signal, resulting in reduction accuracy. More modeling work should be focused on solving this problem. research explored method total soluble solid (TSS) content and acidity ‘Shatian’ pomelo, which are two major parameters...
Abstract. This article presents a fruiting branch shaker designed for litchi ( Sonn.) harvesting and field testing results of the mechanical with abscission chemical treatment. During mature season, experiments were conducted on Feizixiao trees without applying (Ethrel, 2-chloroethyl phosphoric acid). Fruit detachment force (FDF) fruit weight (W) measured to determine effect treatment FDF/W ratio. Fruits harvested by different methods transported laboratory in Guangzhou city stored at 6°C....
The autonomous navigation of unmanned vehicles in GPS denied environments is an incredibly challenging task. Because cameras are low price, obtain rich information, and passively sense the environment, vision based simultaneous localization mapping (VSLAM) has great potential to solve this problem. In paper, we propose a novel VSLAM framework on stereo camera. proposed approach combines direct indirect method for real-time forklift non-structured warehouse. Our hybrid uses photometric errors...
Effectively detecting the quality of blueberries is crucial for ensuring that high-quality products are supplied to fresh market. This study developed a nondestructive method determining soluble solids content (SSC) blueberry fruit by using near-infrared hyperspectral imaging technique. The reflection images in 900–1700 nm waveband range were collected from 480 samples. An image analysis pipeline was extract spectrums images. A regression model quantifying SSC values successfully established...
Pineapple is mainly grown in tropical regions and consumed fresh worldwide due to its attractive flavor health benefits. With increasing global production trade volume, there an urgent need for nondestructive techniques accurate efficient detection of the internal quality pineapples. Therefore, this study dedicated developing a method real-time determining pineapples by using VIS/NIR transmittance spectroscopy technique machine learning methodologies. The spectrums ranging 400–1100 nm total...
The flavor of Pomelo is highly variable and difficult to determine without peeling the fruit. quality pomelo due largely total soluble solid content (TSSC) in fruit there a commercial need for quick but nondestructive TSSC detection method industrial grading pomelo. Due large size thick mesocarp pomelo, determining internal manner difficult, accuracy further complicated by noise typically generated common methods other fruits. Thus, aim this study was optimal accurately detect find...
Since the first proposal to use spray-dried porcine plasma (SDPP) as an animal-based protein source feed additive for piglets in late 1980s, a large number of studies have been published on promotion effect SDPP piglets. contains biologically active components that support pig health during weaning stress and may be more economical compared similar bovine-milk-derived sources. Unfortunately, animal blood proteins suspected African Swine Fever Virus (ASFV) spread China. Furthermore, there are...
The maturity of seeds at harvest determines their intrinsic quality characteristics such as longevity and vigor, these are dominant factors for seed evaluation in the industry. However, little information is available on how to identify further classify maturation stage a way that nondestructive, precise, rapid, inexpensive, while also exactly meeting need uniform control performance industry improve crop yield. This study demonstrated nondestructive method detecting by using single-kernel...
<b><sc>Abstract.</sc></b> Seed purity is a key indicator of crop seed quality. The conventional methods for cultivars identification are time-consuming, expensive, and destructive. Fourier transform near-infrared (FT-NIR) spectroscopy combined with discriminant analyses, was studied as rapid nondestructive technique to classify the sweet corn seeds. Spectra range 1000â2500 nm collected from 760 seeds two were used analyses. Thereafter, 126 feature wavelengths identified 1557 using genetic...
Weeds are one of the greatest threats to growth rice, and loss crops is greater in early stage rice growth. Traditional large-area spraying cannot selectively spray weeds can easily cause herbicide waste environmental pollution. To realize transformation from precision fields, it necessary quickly efficiently detect distribution weeds. Benefiting rapid development vision technology deep learning, this study applies a computer method based on deep-learning-driven field weed target detection....
<b><sc>Abstract.</sc></b> <b>The coverage rate is one of the most important visual traits for turf grass quality screening. However, screening process still highly dependent on manual evaluation, which very time-consuming, laborious, and subjective. Digital image analysis (DIA) has been used by researchers to calculate turfgrass correlated with results from subjective evaluation. In this study, a new evaluation method was developed based two-stage k-means color classifier. Multi-parameters...