- Sparse and Compressive Sensing Techniques
- Photoacoustic and Ultrasonic Imaging
- Image Enhancement Techniques
- Water Quality Monitoring Technologies
- Video Surveillance and Tracking Methods
- Metaheuristic Optimization Algorithms Research
- Biofuel production and bioconversion
- Advanced MIMO Systems Optimization
- Advanced Multi-Objective Optimization Algorithms
- Optical measurement and interference techniques
- Robotic Path Planning Algorithms
- Fire Detection and Safety Systems
- Advanced Image Fusion Techniques
- Advanced Neural Network Applications
- Advanced MRI Techniques and Applications
- Advanced Image and Video Retrieval Techniques
- Aquatic Ecosystems and Phytoplankton Dynamics
- Machine Learning and ELM
- Infrared Target Detection Methodologies
- Metamaterials and Metasurfaces Applications
- Electromagnetic wave absorption materials
- Advanced Vision and Imaging
- Chaos-based Image/Signal Encryption
- Evaluation Methods in Various Fields
- Advanced Data Compression Techniques
Hunan Institute of Technology
2024
Shandong University
2022-2024
University of Electronic Science and Technology of China
2019-2023
Xinyang Normal University
2016-2022
Lanzhou University
2014-2022
Chinese Academy of Fishery Sciences
2021-2022
Shanghai Ocean University
2021-2022
Xiamen Tobacco Industry (China)
2022
China Tobacco
2020-2022
Yunnan University
2022
Ionic liquid (IL) pretreatment is receiving significant attention as a potential process that enables fractionation of lignocellulosic biomass and produces high yields fermentable sugars suitable for the production renewable fuels. However, successful optimization scale up IL involves challenges, such solids loading, handling transfer, washing pretreated formation inhibitors, which are not addressed during development stages at small in laboratory environment. As first research community,...
Abstract Detecting safety helmet wearing in surveillance videos is an essential task for management, compliance with regulations, and reducing the death rate from construction industry accidents. However, it much challenged by some factors like interocclusion, scale variances, perspective distortion, small object detection, carrier recognition of helmet. Traditional image‐based methods suffer them. This article proposes a new methodology detecting wearing, which makes use convolutional...
The sequential recommendation systems capture users' dynamic behavior patterns to predict their next interaction behaviors. Most existing methods only exploit the local context information of an individual sequence and learn model parameters solely based on item prediction loss. Thus, they usually fail appropriate representations. This paper proposes a novel framework, namely Graph Contrastive Learning for Sequential Recommendation (GCL4SR). Specifically, GCL4SR employs Weighted Item...
In the production of poly(vinyl alcohol), raw materials methyl acetate (MeOAc) and methanol (MeOH) exist as a homogeneous azeotropic mixture. Twenty-five kinds ionic liquids, composed five types cations anions, were studied using COSMO-SAC method. The σ-profile data for each component selectivity at infinite dilution (S∞) calculated analyzed, respectively. 1-Hexyl-3-methylimidazolium chloride ([HMIM][Cl]) 1-butyl-3-methylimidazolium ([BMIM][Cl]) selected suitable entrainers based on binary...
To accommodate the ever-increasing wireless capacity, terahertz (THz) orbital angular momentum (OAM) beam that combines THz radiation and OAM technologies has attracted much attention recently, with contributing efforts to explore new dimensions in region. In this paper, we provide an overview of generation detection techniques THz-OAM beams, as well their applications communications. The principle research status typical methods are surveyed, advantages disadvantages each method summarized...
Chicken swarm optimization is a new intelligent bionic algorithm, simulating the chicken searching for food in nature. Basic algorithm likely to fall into local optimum and has slow convergence rate. Aiming at these deficiencies, an improved based on elite opposition‐based learning proposed. In cock swarm, random search adaptive t distribution adopted replace that Gaussian so as balance global exploitation ability development of algorithm. hen introduced promote population diversity....
This letter proposes a gradient-enhanced softmax supervisor for face recognition (FR) based on deep convolutional neural network (DCNN). The proposed conducts the constant-normalized cosine to obtain score each class using combination of intra-class and soft maximum inter-class scores as objective function. mitigates vanishing gradient problem in conventional classifier. experiments public Labeled Faces Wild (LFW) database denote that achieves better results when compared with those achieved...
Underwater spectral imaging is a promising method for mapping, classification and health monitoring of coral reefs seafloor inhabitants. However, the spectrum light distorted during underwater process due to wavelength-dependent attenuation by water. This paper presents model-based that accurately restores brightness images captured with narrowband filters. A model built imaging. The structure derived from physical principles, representing absorption, scattering refraction water optical...
Compressive Sensing (CS) realizes a low-complex image encoding architecture, which is suitable for resource-constrained wireless sensor networks. However, due to the nonstationary statistics of images, images reconstructed by CS-based codec have many blocking artifacts and blurs. To overcome these negative effects, we propose an Adaptive Block (ABCS) system based on spatial entropy. Spatial entropy measures amount information, used allocate measuring resources various regions. The scheme...
Sediment resuspension is an important internal lake process in regulating nutrient cycling and ecosystem structure. Tubificid worms are widely abundantly distributed freshwater ecosystems able to alter the sediment characteristics. This study was conducted verify hypothesis that alteration of sediments by tubificids may substantially influence process. Specifically, we investigated Limnodrilus hoffmeisteri (Tubificidae) on using apparatus designed simulate Lake Taihu (China). We examined L....
The densities of AOT/isooctane micelles and water/AOT/isooctane microemulsions with the molar ratios R water to AOT being 2, 8, 10, 12, 16, 18, 20, 25, 30, 40 were measured at 303.15 K. apparent specific volumes quasi-component water/AOT various concentrations calculated used estimate volumetric properties in droplets continuous oil phase, discuss interaction between droplets, determine critical micelle concentration microemulsion concentrations. A thermodynamic model was proposed analysis...
Energy density measurements using bomb calorimetry were applied along with mass yields to calculate energy from and lignocellulosic feedstocks conversion processes.
Intelligent security expects to avoid the occurrence of robbery, theft, and other undesirable situations through video surveillance. In surveillance, images human faces undimmed are not easily available, so pedestrian re-identification (person ReID) is an alternative technique which attracts a mount researchers attention. Person ReID used match across cameras. Due interference shooting angle camera quality, it difficult obtain high resolution, no obstructions, simple backgrounds similar...
The involvement of gut microbiota composition in ulcerative colitis is strongly supported by previous research. Growing evidence suggests that probiotic therapy protects against inflammatory bowel disease animal models and patients. However, as a probiotic, the role Enterococcus faecium (E. faecium) UC remains unclear. Nevertheless, potential mechanism protective effect E. unknown. In this study, dextran sulphate sodium-induced (DSS-induced) model was used to detect underlying maintaining...
In order to measure the heart rate and breath of human-body evaluate fatigue level in real-time, a noncontact human assessment system based on millimeter wave radar AWR1642 is proposed this paper assess health condition conveniently. It has characteristics high classification accuracy accuracy. The function mainly includes getting accurate by AWR1642, establishing data set, extracting features, annotating predicting Particle Swarm optimization Back Propagation (PSO-BP) neural network model....