A5102978234- Face and Expression Recognition
- Industrial Vision Systems and Defect Detection
- Parasite Biology and Host Interactions
- Aquaculture disease management and microbiota
- Advanced Neural Network Applications
- Complex Network Analysis Techniques
- Robotics and Sensor-Based Localization
- Aquaculture Nutrition and Growth
- Advanced Algorithms and Applications
- Advanced Image Fusion Techniques
- Emotion and Mood Recognition
- Viral gastroenteritis research and epidemiology
- Biological Research and Disease Studies
- Video Surveillance and Tracking Methods
- Vibration Control and Rheological Fluids
- Cutaneous Melanoma Detection and Management
- Network Security and Intrusion Detection
- Animal Virus Infections Studies
- Advanced Image and Video Retrieval Techniques
- Advanced Sensor and Control Systems
- Remote Sensing and Land Use
- Face recognition and analysis
- Invertebrate Immune Response Mechanisms
- Image and Video Stabilization
- Advanced Vision and Imaging
Huzhou University
2023-2025
China Geological Survey
2025
Jiangxi University of Science and Technology
2013-2024
Jiangxi University of Technology
2024
Beijing Tongren Hospital
2022-2024
Capital Medical University
2022-2024
Xi'an Aeronautical University
2024
Guangzhou University
2024
Guilin University of Technology
2023-2024
Chinese Academy of Fishery Sciences
2023
A tomato automatic detection method based on an improved YOLOv8s model is proposed to address the low automation level in harvesting agriculture. The provides technical support for and classification of tomatoes agricultural production activities. has three key components. Firstly, depthwise separable convolution (DSConv) technique replaces ordinary convolution, which reduces computational complexity by generating a large number feature maps with small amount calculation. Secondly, dual-path...
In recent years, deep–penetrating geochemical exploration techniques have played a crucial role in the detection of concealed minerals. These methods effectively detect deep−seated anomalies and been tested various landscape–covered areas, yielding remarkable results. This study focuses on covered areas southern margin Kuqa Basin, utilizing for systematic sampling to explore potassium salt. examines chemical composition several underground brine samples, revealing salinity levels ranging...
In recent years, overlapping community detection algorithms have been paid more and attention, which not only reveal the real social relations, but also expose possible communication channels between communities. Those individuals (or people) in area are very important to communities that can promote two or On other hand, from privacy perspective, some people may want be found out areas. With this mind, we raise a question "Can modify their relationships avoid discovery locating them into...
Skin color detection is an important subject in computer vision research. Color segmentation takes a great attention because effective and robust visual cue for characterizing object from the others. To aim at existing skin algorithms considering luminance information not enough, reliable modeling approach was proposed. It based on fact that distribution of single-colored invariant with respect to variations even Cb-Cr plane does ignore influence Y component YCbCr space. Firstly, according...
This study investigated the temporal and spatial variations of precipitation duration intensity in Jiangsu Province from 1960 to 2020 using IDW interpolation method Kendall’s tau trend test, based on daily data collected 22 meteorological stations. Additionally, a Pearson correlation analysis was conducted examine correlations between occurrence rate contribution with different durations grades, as well five large-scale climate indices. The results indicated following trends: (1) An increase...
Little is known about the relationship between social comparison orientation and mental health, especially in psychological capital context. We proposed a theoretical model to examine impact of ability- opinion-based on health using data from 304 undergraduates. also examined mediating effect four components hope, self-efficacy, resilience, optimism health. Results show that an ability (vs. opinion) was negatively positively) related components. Further, resilience fully mediated...
Image dehazing based on convolutional neural networks has achieved significant success; however, there are still some problems, such as incomplete dehazing, color deviation, and loss of detailed information. To address these issues, in this study, we propose a multi-scale network with dark channel priors (MSDN-DCP). First, introduce feature extraction module (FEM), which effectively enhances the ability correlation through two-branch residual structure. Second, fusion (FFM) is devised to...
Existing knowledge distillation (KD) methods are mainly based on features, logic, or attention, where features and logic represent the results of reasoning at different stages a convolutional neural network, attention maps symbolize process. Because continuity two in time, transferring only one them to student network will lead unsatisfactory results. We study transfer between teacher-student degrees, revealing importance simultaneously related process providing new perspective for KD. On...
The problem of finite-time vibration control earthquake excited linear structures with input time-delay and saturation is concerned in this paper. objective designing controllers to guarantee the stability closed-loop systems while attenuating earthquake-induced structures. First, based on matrix transformation, structural system described as a state-space model, which contains actuator time-delay. Then, Lyapunov functional analysis method, some sufficient conditions for existence...
It is difficult for humans to recognize recessive diseases in navel oranges. Therefore, deep neural networks are applied plant disease identification. To improve the feature extraction ability of convolutional networks, Parameter Exponential Nonlinear Activation Unit (PENLU) proposed replace activated function network. This not only adds multiple parameters but also brings better generalization In addition, can be updated by inverse Stochastic Gradient Descent (SGD) algorithm, which has...
To further investigate the immune response of Macrobrachium rosenbergii against Aeromonas veronii, comparative transcriptomic analyses M. hepatopancreas were conducted on challenge and control groups at 6, 12, 24 h post-infection (hpi), independently. A total 51,707 high-quality unigenes collected from RNA-seq data, 8060 differentially expressed genes (DEGs) discovered through paired comparisons. Among three comparison groups, a KEGG pathway enrichment analysis showed that 173 immune-related...
Optical flow is an important method of motion image analysis and has a widely application in machine vision processing. The extended optical constraint based on the continuity equation fluid robust to changes brightness deformation objects. In this paper, basis constraint, novel approach for estimating facial expression presented. First-order second-order div-curl splines as additional conditions are introduced calculation non-rigid field, used calculated field expressions sequences,...
To further investigate the immune response of Macrobrachium rosenbergii against Aeromonas veronii, comparative transcriptomic analyses M. hepatopancreas were conducted on challenge and control groups at 6, 12, 24 h post-infection (hpi), independently. A total 51,707 high-quality unigenes collected from RNA-seq data, 8,060 differentially expressed genes (DEGs) discovered through paired comparisons. Among three comparison groups, KEGG pathway enrichment analysis showed that 173 immune-related...
The problem of finite-time vibration-attenuation controller design for buildings structural systems with parameter uncertainties is the concern this paper. objective designing controllers to guarantee stability closed-loop a prescribed level disturbance attenuation. First, based on matrix transformation, system described as state-space model, which contains uncertainties. Then, analysis method, some sufficient conditions existence are obtained. By solving these conditions, desired can be...