A5100702870- Metaheuristic Optimization Algorithms Research
- Advanced Multi-Objective Optimization Algorithms
- Evolutionary Algorithms and Applications
- Video Surveillance and Tracking Methods
- Advanced Vision and Imaging
- Infrared Target Detection Methodologies
- DNA and Biological Computing
- Advanced Measurement and Detection Methods
- Advanced biosensing and bioanalysis techniques
- Advanced Image Processing Techniques
- Image Processing Techniques and Applications
- RNA and protein synthesis mechanisms
- Video Coding and Compression Technologies
- Face and Expression Recognition
- RNA modifications and cancer
- Vehicle Routing Optimization Methods
- Advanced Image Fusion Techniques
- Advanced Data Compression Techniques
- AI in cancer detection
- Image and Signal Denoising Methods
- Remote-Sensing Image Classification
- Brain Tumor Detection and Classification
- Scheduling and Timetabling Solutions
- Gait Recognition and Analysis
- Protein Structure and Dynamics
Wuhan University of Science and Technology
2015-2025
Nanjing University of Science and Technology
2025
China University of Geosciences (Beijing)
2020-2025
Macau University of Science and Technology
2024
Anhui Agricultural University
2024
National University of Defense Technology
2024
Australian National University
2023
Qufu Normal University
2023
Northwestern Polytechnical University
2018-2021
Shenyang University of Chemical Technology
2021
This article presents a novel evolution strategy-based evolutionary algorithm, named DMOES, which can efficiently and effectively solve multiobjective optimization problems in dynamic environments. First, an efficient self-adaptive precision controllable mutation operator is designed for individuals to explore exploit the decision space. Second, simulated isotropic magnetic particles niching guide keep uniform distance extent approximate entire Pareto front automatically. Third, nondominated...
Abstract In recent years, evolutionary algorithms have shown great advantages in the field of feature selection because their simplicity and potential global search capability. However, most existing based on computation are wrapper methods, which computationally expensive, especially for high-dimensional biomedical data. To significantly reduce computational cost, it is essential to study an effective evaluation method. this paper, a two-stage improved gray wolf optimization (IGWO)...
In recent years, numerous efficient and effective multimodal multiobjective evolutionary algorithms (MMOEAs) have been developed to search for multiple equivalent sets of Pareto optimal solutions simultaneously. However, some the MMOEAs prefer convergent individuals over diversified construct mating pool, with slightly better decision space distribution may be replaced by significantly objective distribution. Therefore, diversity in become deteriorated, spite diversities taken into account...
For the past many years, several constrained multiobjective evolutionary algorithms (CMOEAs) have been designed for solving multi-objective optimization problems (CMOPs). In these CMOEAs, some constraint-handling techniques (CHTs) were proposed to balance convergence and satisfaction, however, they still face serious challenges, such as premature local optimal region labor-intensive tuning of parameters a specific CMOP. Furthermore, most existing CHTs are derived by single-objective...
Optical coherence tomography (OCT) is a high-resolution and noninvasive imaging modality that has become one of the most prevalent techniques for ophthalmic diagnosis. Retinal layer segmentation very crucial doctors to diagnose study retinal diseases. However, manual often time-consuming subjective process. In this work, we propose new method automatically segmenting OCT images, which integrates deep features hand-designed train structured random forests classifier. The convolutional are...
Although numerous effective and efficient multiobjective evolutionary algorithms have been developed in recent years to search for a well-converged well-diversified Pareto optimal front, most of these designs are computationally expensive maintain large population individuals throughout the process. Once front is found satisfactorily, cognitive burden then imposed upon decision makers handpick one solution implementation among massive number candidates even with powerful multicriteria...
Formulae display:?Mathematical formulae have been encoded as MathML and are displayed in this HTML version using MathJax order to improve their display. Uncheck the box turn off. This feature requires Javascript. Click on a formula zoom.
In recent years, numerous efficient many-objective optimization evolutionary algorithms have been proposed to find well-converged and well-distributed nondominated optimal solutions. However, their scalability performance may deteriorate drastically solve large-scale problems (LSMaOPs). Encountering high-dimensional solution space with more than 100 decision variables, some of them lose diversity trap into local optima, while others achieve poor convergence performance. This article proposes...
The biggest bottleneck in DNA computing is exponential explosion, which the molecules used as data information processing grow exponentially with an increase of problem size. To overcome this and improve speed, we propose a model to solve graph vertex coloring problem. main points are follows: ① explosion solved by dividing subgraphs, reducing colors without losing solutions, ordering vertices subgraphs; ② bio-operation times reduced considerably designed parallel polymerase chain reaction...
In recent years, numerous many-objective evolutionary algorithms (MaOEAs) have been developed to search for well-diversified and well-converged Pareto optimal solutions high-dimensional optimization problems (MaOPs). However, existing MaOEAs tackle some daunting challenges, including the emergence of dominance resistance solutions, effective diversity preservation scheme, management a large population size, extremely high computational complexity, sensitivity shape front (PF), overly relying...
Abstract This article focuses on setting ‘green’ boundaries for green finance in China—the scope of eligible projects to be supported by Chinese finance. China started building its system 2015, and 23 provinces issued guidelines between 2016 2020. Applying multi‐level governance as our analytical framework, this study collects data from a broad range publicly available sources, including 64 policies state ministries, or pilot zones, transcripts relevant press conferences, streamed speeches...
Diffusion Transformers have emerged as the preeminent models for a wide array of generative tasks, demonstrating superior performance and efficacy across various applications. The promising results come at cost slow inference, each denoising step requires running whole transformer model with large amount parameters. In this paper, we show that performing full computation diffusion is unnecessary, some computations can be skipped by lazily reusing previous steps. Furthermore, lower bound...
In this paper, a new pansharpening method is proposed by constructing set of multiscale geometric support tensor filters (MGSTFs). First, least-square ridgelet machine developed to derive series MGSTFs. Then the source images are formulated as tensors and filtered MGSTFs capture salient features images. These then fused at each scale direction obtain products. The distortions can be reduced exploring formulation multispectral data endowing filters' directionality details Some experiments...
COVID-19 has been spread around the world and caused a huge number of deaths. Early detection this disease is most efficient way to prevent its rapid spread. Due development internet technology edge intelligence, developing an early system for in medical environment Internet Things (IoT) can effectively alleviate disease. In paper, algorithm developed, which detect by utilizing features from Chest X-ray (CXR) images. First, pre-trained model (ResNet18) adopted feature extraction. Then,...