- Metaheuristic Optimization Algorithms Research
- Advanced Multi-Objective Optimization Algorithms
- Evolutionary Algorithms and Applications
- Additive Manufacturing Materials and Processes
- Smart Grid Energy Management
- Integrated Energy Systems Optimization
- Artificial Immune Systems Applications
- High Entropy Alloys Studies
- Additive Manufacturing and 3D Printing Technologies
- Advanced Algorithms and Applications
- Modular Robots and Swarm Intelligence
- Microgrid Control and Optimization
- High-Temperature Coating Behaviors
- Slime Mold and Myxomycetes Research
- Greenhouse Technology and Climate Control
- Handwritten Text Recognition Techniques
- Nanomaterials and Printing Technologies
- Electric Vehicles and Infrastructure
- Video Coding and Compression Technologies
- Spectroscopy and Chemometric Analyses
- Robotic Mechanisms and Dynamics
- Industrial Vision Systems and Defect Detection
- Energy Load and Power Forecasting
- Scheduling and Timetabling Solutions
- Robotic Path Planning Algorithms
Sun Yat-sen University
2025
Guizhou Normal University
2025
Tiangong University
2015-2024
Peng Cheng Laboratory
2024
University of Wisconsin–Madison
2019
For profit maximization, the model‐based stock price prediction can give valuable guidance to investors. However, due existence of high noise in financial data, it is inevitable that deep neural networks trained by original data fail accurately predict price. To address problem, wavelet threshold‐denoising method, which has been widely applied signal denoising, adopted preprocess training data. The preprocessing with soft/hard threshold method obviously restrain noise, and a new multioptimal...
Virtual try-on (VTON) technology has gained attention due to its potential transform online retail by enabling realistic clothing visualization of images and videos. However, most existing methods struggle achieve high-quality results across image video tasks, especially in long scenarios. In this work, we introduce CatV2TON, a simple effective vision-based virtual (V2TON) method that supports both tasks with single diffusion transformer model. By temporally concatenating garment person...
This paper proposes a novel optimization scheme by hybridizing an artificial bee colony optimizer (HABC) with life-cycle mechanism, for both stationary and dynamic problems. The main innovation of the proposed HABC is to develop cooperative population-varying scheme, in which individuals can dynamically shift their states birth, foraging, death, reproduction throughout life cycle. That is, size be adjusted according local fitness landscape during algorithm execution. new characteristic helps...
This paper proposes a novel artificial bee colony algorithm with dynamic population (ABC-DP), which synergizes the idea of extended life-cycle evolving model to balance exploration and exploitation tradeoff. The proposed ABC-DP is more bee-colony-realistic that can reproduce die dynamically throughout foraging process size varies as runs. then used for solving optimal power flow (OPF) problem in systems considers cost, loss, emission impacts objective functions. 30-bus IEEE test system...
The whale optimization algorithm (WOA) is a popular swarm intelligence which simulates the hunting behavior of humpback whales. WOA has deficiency easily falling into local optimal solutions. In order to overcome weakness WOA, modified variant called OCDWOA proposed. There are four main operators introduced enhance search performance WOA. include opposition-based learning method, nonlinear parameter design, density peak clustering strategy, and differential evolution. proposed tested on 19...
In the past few decades, metaheuristic algorithms (MA) have been developed tremendously and successfully applied in many fields. recent years, a large number of new MA proposed. Slime mould algorithm (SMA) is novel swarm-based intelligence optimization algorithm. SMA solves problem by imitating foraging movement behavior slime mould. It can effectively obtain promising global optimal solution. However, it still suffers some shortcomings such as unstable convergence speed, imprecise search...
Excellent mechanical properties, including residual stress, ductility and strength, are important requirements for bone implants. In order to achieve this effect, titanium samples were manufactured by selective laser melting, the prepared parts subsequently subjected three different heat treatment, which 550 °C, 650 °C 750 2 h, respectively. The results show that as-built sample, relatively short lath-shaped α grains a few needle-shaped α′ present. After became thicker longer, more. As...
The whale optimization algorithm (WOA) is inspired by humpback social behavior and WOA a popular swarm intelligence algorithm. Yet, the does have certain flaws, such as restricted global search capability an inconsistent convergence speed, when dealing with complex problems, easy to fall into local optimum. To address WOA’s shortcomings, modified exploitability enhancement called MWOA-CEE proposed. Three operators, opposition-based learning, exponentially decreasing function, elite-guided...
Recent advances in diffusion models can generate high-quality and stunning images from text. However, multi-turn image generation, which is of high demand real-world scenarios, still faces challenges maintaining semantic consistency between texts, as well contextual the same subject across multiple interactive turns. To address this issue, we introduce TheaterGen, a training-free framework that integrates large language (LLMs) text-to-image (T2I) to provide capability generation. Within...
Reducing the production makespan of modern small-batch, multi-variety jobs can be abstracted into a flexible job shop scheduling problem (FJSP). The organization greatly improve efficiency by according to optimal solution FJSP. However, due high computational complexity FJSP, it is often difficult achieve higher performance in actual production. To optimize hybrid remora optimization algorithm with variable neighborhood search (HROA-VNS) proposed this work. A initialization method based on...