A5082366420- Spectroscopy and Chemometric Analyses
- Smart Agriculture and AI
- Advanced Chemical Sensor Technologies
- Remote Sensing in Agriculture
- Plant Pathogenic Bacteria Studies
- Industrial Technology and Control Systems
- Advanced machining processes and optimization
- Phytoplasmas and Hemiptera pathogens
- Water Quality Monitoring and Analysis
- Leaf Properties and Growth Measurement
- Analog and Mixed-Signal Circuit Design
- Spectroscopy Techniques in Biomedical and Chemical Research
- Fault Detection and Control Systems
- Plant Pathogens and Fungal Diseases
- Advanced Sensor and Control Systems
- Chemical and Physical Studies
- Magnetic and Electromagnetic Effects
- Gear and Bearing Dynamics Analysis
- Biofield Effects and Biophysics
- Advanced Data Processing Techniques
- Mineral Processing and Grinding
- Terahertz technology and applications
- Ga2O3 and related materials
- Soil Mechanics and Vehicle Dynamics
- thermodynamics and calorimetric analyses
Fujian Academy of Agricultural Sciences
2022-2025
Fujian Agriculture and Forestry University
2016-2025
East China University of Science and Technology
1995
The flatness of the cut surface in enoki mushrooms (Flammulina filiformis Z.W. Ge, X.B. Liu & Zhu L. Yang) is a key factor quality classification. However, conventional automatic cutting equipment struggles with deformation issues due to its inability adjust grasping force based on individual mushroom sizes. To address this, we propose an improved method that integrates visual feedback dynamically execution end, enhancing precision. Our approach enhances YOLOv8n-seg Star Net, SPPECAN (a...
Rice blast is regarded as one of the major diseases rice. Screening rice genotypes with high resistance to a key option for ensuring global food security. Unmanned aerial vehicles (UAV)-based imaging, coupled deep learning, can high-throughput acquire imagery traits about infection. In this study, we developed segmented detection model (RiceblastSegMask) and evaluation. The feasibility different backbones target models was further investigated. RiceblastSegMask two-stage instance...
Rice adulteration is a severe problem in agro-products and food regulatory agencies, suppliers, consumers. In this study, to effectively distinguish whether high-quality rice mixed with low-quality rice, detection analysis of adulterated five levels different mixing proportions was conducted via terahertz spectroscopy pattern recognition algorithms. Initially, samples were prepared spectral data acquired by using the transmission mode, principal component (PCA) algorithm applied extract...
The activities of enzymes are the basis evaluating quality honey. Beekeepers usually use concentrators to process natural honey into concentrated by concentrating it under high temperatures. Active very sensitive temperatures and will lose their activity when they exceed a certain temperature. objective this work is study kinetic mechanism temperature effect on diastase develop nondestructive approach for quick determination through heating based visible near-infrared (Vis/NIR) spectroscopy....
Tea polyphenols are considered as an important indicator of tea quality. Rapid detection polyphenol content plays a valuable role for breeding and quality inspection during production. In this work, portable rapid non-destructive device in fresh leaves was developed, which integrated the fusion technology visible/short-wave (400–1050 nm) long-wave (1000–1650 near-infrared spectroscopy (Vis/NIR). Experimental results indicated that spectra within overlapping region (1000–1050 were assembled...
The objective of the present study was to characterize temporal and spatial variation biopolymers in cells infected by tea leaf blight using confocal Raman microspectroscopy. We investigated on serial sections infection part, four corresponding different stages were obtained for analysis. spectra extracted from selected regions (circumscribing vascular bundle) analyzed detail enable a semi-quantitative comparison micron-scale. As progressed, lignin other phenolic compounds decreased bundle,...
Biomass monitoring of mushroom liquid strains during the fermentation process demands real-time analysis with minimal manual intervention, highlighting urgent need for intelligent surveillance. This study introduced a soft sensor method based on edge computing machine vision, termed Edge CV, in situ non-invasive estimation biomass. In our experiment, hardware CV system includes Jetson Nano 4 GB RAM, 64 ROM, and 128-core Maxwell GPU executing vision tasks, along embedded cameras image data...
Abstract Background Rice blast is one of the most destructive diseases in rice cultivation, significantly threatening global food security. Timely and precise detection panicle crucial for effective disease management prevention crop losses. This study introduces ConvGAM, a novel semantic segmentation model leveraging ConvNeXt-Large backbone network Global Attention Mechanism (GAM). design aims to enhance feature extraction focus on critical image regions, addressing challenges detecting...
UAV image acquisition and deep learning techniques have been widely used in field hydrological monitoring to meet the increasing data volume demand refined quality. However, manual parameter training requires trial-and-error costs (T&E), existing auto-trainings adapt simple datasets network structures, which is low practicality unstructured environments, e.g., dry thermal valley environment (DTV). Therefore, this research combined a transfer (MTPI, maximum potential index method) an...
Environmental control based on growth stage is critical for enhancing the yield and quality of industrially cultivated Pleurotus pulmonarius. Challenges such as scene complexity overlapping mushroom clusters can impact accuracy detection target segmentation. This study introduces a lightweight method called real-time model stages P. pulmonarius (GSP-RTMDet). A spatial pyramid pooling fast network with simple parameter-free attention (SPPF-SAM) was proposed, which enhances backbone’s...
<title>Abstract</title> As the civilian drone market continues rapidly growing, operator training system standard is under developing. However, traditional evaluation methods based on processes and behaviors are no longer sufficient to dynamically cognitively classify competency levels. In this research, an experiment was designed conducted explore possibility of classifying level EEG signals deep learning models. Moreover, a model proposed called Bidirectional Custom Attention Mechanism...