A5101678567- Rough Sets and Fuzzy Logic
- Text and Document Classification Technologies
- Image Retrieval and Classification Techniques
- Data Mining Algorithms and Applications
- Particle physics theoretical and experimental studies
- Quantum Chromodynamics and Particle Interactions
- Face and Expression Recognition
- High-Energy Particle Collisions Research
- Advanced Computational Techniques and Applications
- Multi-Criteria Decision Making
- Web Data Mining and Analysis
- Adsorption and biosorption for pollutant removal
- Analytical Chemistry and Chromatography
- Machine Learning in Bioinformatics
- Saffron Plant Research Studies
- Advanced Image and Video Retrieval Techniques
- Music and Audio Processing
- Imbalanced Data Classification Techniques
- Spam and Phishing Detection
- Machine Learning and Data Classification
- Computer Graphics and Visualization Techniques
- Microbial Metabolic Engineering and Bioproduction
- Data Management and Algorithms
- Advanced Neural Network Applications
- Advanced Decision-Making Techniques
Jiangxi Agricultural University
2015-2025
Chongqing University
2024
Hubei University of Science and Technology
2016-2023
University of Science and Technology Beijing
2010-2019
University of Warwick
2017-2018
University of Oxford
2016
China National Center for Biotechnology Development
2010-2013
Nanjing Tech University
2010-2013
State Key Laboratory of Materials-Oriented Chemical Engineering
2012-2013
Aviation Industry Corporation of China (China)
2012
Underwater target detection holds a noteworthy role in the field of marine exploration. However, it is difficult to extract useful feature information from blurred images with complex backgrounds, resulting suboptimal and unsatisfactory conventional models. Among them, YOLOv5 leverages advantages fast performs better detecting underwater samples. Nevertheless, still faces difficulties including missed incorrect detections due environment's small scale objects, dense distribution organisms,...
Abstract BACKGROUND: Owing to the rapid depletion of petroleum fuel, production bio‐butanol has attracted much attention. However, low butanol productivity severely limits its potential industrial application. It is important establish an approach for recovering low‐concentration from fermentation broth. Experiments were conducted using batch adsorption mode under different conditions initial concentration and temperature. Batch data fitted Langmuir Freundlich isotherms macropore diffusion,...
Multi-label feature selection can effectively resolve the challenges of high or even ultra-high dimensionality in multi-label data. However, most existing algorithms only handle a single data type, assume all labels are equally significant and utilize heuristic search strategies, which results inefficient relatively unsatisfactory classification accuracy. In view above shortcomings, this paper proposes new algorithm that resolves algorithms' issues through three innovative procedures. First,...
Mirror detection is of great significance for avoiding false recognition reflected objects in computer vision tasks. Existing mirror frameworks usually follow a supervised setting, which relies heavily on high quality labels and suffers from poor generalization. To resolve this, we instead propose the first weakly-supervised framework also provide scribble-based dataset. Specifically, relabel 10,158 images, most have labeled pixel ratio less than 0.01 take only about 8 seconds to label....
The traditional distillation method for recovery of butanol from fermentation broth is an energy-intensive process. Separation based on adsorption methodology has advantages in terms biocompatibility and stability, as well economy, therefore gains much attention. However, the application commercial adsorbents integrated acetone-butanol-ethanol (ABE) process restricted due to low (less than 85%) weak capability enrichment eluent (3-4 times). In this study, we investigated sorption properties...