A5100666668- Advanced Chemical Physics Studies
- Catalytic Processes in Materials Science
- Parallel Computing and Optimization Techniques
- Advanced Physical and Chemical Molecular Interactions
- Quantum Information and Cryptography
- Effects of Environmental Stressors on Livestock
- Interconnection Networks and Systems
- Quantum optics and atomic interactions
- Orbital Angular Momentum in Optics
- Embedded Systems Design Techniques
- Water Quality Monitoring Technologies
- Nanocluster Synthesis and Applications
- Air Quality Monitoring and Forecasting
- Molecular Junctions and Nanostructures
- nanoparticles nucleation surface interactions
- Water Quality Monitoring and Analysis
- Luminescence Properties of Advanced Materials
- Advanced Data Storage Technologies
- Industrial Vision Systems and Defect Detection
- Hydrological Forecasting Using AI
- Advanced Vision and Imaging
- Glass properties and applications
- Video Coding and Compression Technologies
- Quantum Mechanics and Applications
- Animal Behavior and Welfare Studies
Chinese Academy of Sciences
2025
Hefei Institutes of Physical Science
2025
Zhongkai University of Agriculture and Engineering
2020-2024
Yantai University
2023
Shenhua Group (China)
2023
Taiyuan Heavy Industry (China)
2023
Key Laboratory of Guangdong Province
2022
Shihezi University
2022
Beijing University of Posts and Telecommunications
2019
South China Normal University
2014-2016
Recently, the attention mechanism combining spatial and channel information has been widely used in various deep convolutional neural networks (CNNs), proving its great potential improving model performance. However, this usually uses 2D global pooling operations to compress or scaling methods reduce computational overhead attention. These will result severe loss. Therefore, we propose a Spatial that captures cross-dimensional interaction, which does not involve dimensionality reduction...
Dissolved oxygen content is a key indicator of water quality in aquaculture environment. Because its nonlinearity, dynamics, and complexity, which makes traditional methods face challenges the accuracy speed dissolved prediction. As solution to these issues, this study introduces hybrid model consisting Light Gradient Boosting Machine (LightGBM) Bidirectional Simple Recurrent Unit (BiSRU). Firstly, Linear interpolation smoothing were used identify significant parameters. LightGBM algorithm...
There are some problems with estrus detection in ewes large-scale meat sheep farming: mainly, the manual method is labor-intensive and contact sensor causes stress reactions ewes. To solve abovementioned problems, we proposed a multi-objective layer neural network-based for ewe crawling behavior recognition. The approach has four main parts. Firstly, to address problem of mismatch between our constructed dataset YOLO v3 anchor box size, propose obtain new size by clustering using K-means++...
FLOWERING LOCUS D (FD) is a basic leucine zipper (bZIP) transcription factor known to be crucial in vernalization, flowering, and stress response across variety of plants, including biennial winter annual species. The TaFD-like (TaFDL) gene wheat the functional homologue Arabidopsis FD, yet research on TaFDL family still lacking. In this study, total 62 members were identified classified into 4 main subfamilies, these genes located 21 chromosomes. A comprehensive analysis physicochemical...
We propose a lightweight neural network-based method to detect the estrus behavior of ewes. Our suggested is mainly proposed solve problem not being able ewe in timely and accurate manner large-scale meat sheep farms. The three main steps our methodology include constructing dataset, improving network structure, detecting based on network. First, dataset was constructed by capturing images from videos with crawling behavior, data enhancement performed improve generalization ability model at...
We demonstrate, theoretically and experimentally, a new method to measure high-order topological charges (TCs) of Laguerre–Gaussian vortex beams, including the magnitude sign, by analyzing interference intensity patterns. The is determined patterns between beam its conjugate beam, using an improved Mach–Zehnder interferometer with dove prism. Counting number bright petals attests TCs through half petal number. After TC modulated spiral phase plate, sign acquired comparing counting results...
Silicon photomultiplier technology based on Geigermode avalanche in p-n junction has made unforeseen progress for the last 5-6 years. With its high gain and photon detection efficiency, it shown that could replace PMTs many applications including time-of-flight PET. Also, magnetic immunity compactness very suitable PET-MR detector. In this paper, we present detector silicon from selection, prototype test with discrete electronics, ASIC a module design. system performance data is presented.
In large-scale meat sheep farming, high CO2 concentrations in sheds can lead to stress and harm the healthy growth of sheep, so a timely accurate understanding trend concentration early regulation are essential ensure environmental safety welfare sheep. order accurately understand regulate barns, we propose prediction method based on RF-PSO-LSTM model. The approach has four main parts. First, address problems data packet loss, distortion, singular values, differences magnitude ambient air...
Accurate feeding control in aquaculture using fish behavior state is key to improving feed utilization efficiency and reducing water pollution. A hybrid method based on ResNet34-CBAM migration learning proposed this paper achieve tilapia classification. In order enhance the diversity of samples, pre-processing, such as scaling cropping, adding noise, was performed images. An underwater camera used for taking pictures behavior, followed by feature extraction a pre-trained ResNet34 residual...
The optical-absorption and EPR spectra of octahedral ${\mathrm{Fe}}^{3+}$ center in yttrium aluminum garnet have been studied by diagonalizing the complete energy matrices for a ${d}^{5}$ configuration ion trigonal ligand field. It is shown that local lattice structure around an octahedrally coordinated has expansion distortion. distortion may be attributed to fact radius larger than ${\mathrm{Al}}^{3+}$ ion, will push oxygen ligands outwards. Simultaneously, parameters...
SO2 ultraviolet (UV) camera technology has been successfully applied to the accurate imaging detection of pollutant gas concentration; however, actual ability this not intensively studied, especially accuracy and limit under influence light dilution effect. Here, we theoretically experimentally investigate UV scattering on concentration inversion. The radiation transfer model effect is reconstructed, concept optimized discussed. An outfield experiment conducted a ship exhaust, results are...
Durability and capacity of electrode materials, especially the anodes, are main challenges for aqueous Li-ion batteries. In this work, MoSe2 micron flowers have been synthesized investigated as anodes Li+ storage in LiCl aqueous-based electrolytes. solution, working potential anode can reach −1.0 V (vs Ag/AgCl). Yet, its reversible is only ∼14 mAh g−1 (50 C g−1), owing to absence Faradaic reactions fast deformation MoSe2. After gelation solution using poly vinyl alcohol (PVA), activity water...
The first-principles method based on density-functional theory is used to investigate the geometries of lowest-lying isomers AunAg2 (n = 1∼4) clusters. Several low-lying are determined, and many them in electronic configurations with a high spin multiplicity. stability trend Ag-doped Aun clusters compared that pure Our results indicate inclusion two Ag atoms lowers cluster stability, indicating higher as structures grow size. bigger energy difference between curves grows This information...
Accurate counting is difficult in the case of large numbers overlapping and adhering fry. In this study, we propose a lightweight target detection method based on deep learning methods that can meet deployment requirements edge computing device for automatic fry while obtaining high accuracy. We improve structure YOLOv4-tiny by embedding different attention mechanisms CSP blocks backbone network to enhance feature extraction performance. addition, low efficiency fusion original model also...