A5100626646- Metaheuristic Optimization Algorithms Research
- Advanced Multi-Objective Optimization Algorithms
- Advanced Algorithms and Applications
- Evolutionary Algorithms and Applications
- Video Surveillance and Tracking Methods
- Vehicle Routing Optimization Methods
- Face and Expression Recognition
- Domain Adaptation and Few-Shot Learning
- Metallurgy and Material Forming
- Image Enhancement Techniques
- Data Management and Algorithms
- Anomaly Detection Techniques and Applications
- Scheduling and Optimization Algorithms
- Neural Networks and Applications
- Advanced Neural Network Applications
- Adversarial Robustness in Machine Learning
- Robotic Path Planning Algorithms
- Advanced Image Fusion Techniques
- Microstructure and mechanical properties
- IoT and Edge/Fog Computing
- Fire Detection and Safety Systems
- Aluminum Alloy Microstructure Properties
- Blind Source Separation Techniques
- Distributed Control Multi-Agent Systems
- Traffic Prediction and Management Techniques
Wuhan University
2014-2025
Xinjiang University
2023-2024
Nanyang Institute of Technology
2018-2020
Central South University
2018-2020
State Key Laboratory of High Performance Complex Manufacturing
2018
New Jersey Institute of Technology
2014
State Key Laboratory of Software Engineering
2012
Institute of Software
2012
Academia Sinica
2012
Wuhan Donghu University
2011
This paper presents an adaptive particle swarm optimization with supervised learning and control (APSO-SLC) for the parameter settings diversity maintenance of (PSO) to adaptively choose parameters, while improving its exploration competence. Although PSO is a powerful method, it faces such issues as difficult setting premature convergence. Inspired by predictive strategies from machine fields, we propose APSO-SLC that employs several address these issues. First, treat problem system be...
This paper presents a Gaussian classifier-based evolutionary strategy (GCES) to solve multimodal optimization problems. An technique for them must answer two crucial questions guarantee its success: how distinguish among the different basins of attraction and safeguard already discovered good-quality solutions including both global local optima. In GCES, problems are regarded as classification ones, mixture models employed save locations presently identified or A sequential estimation...
Feature selection is one of the most critical steps in big data analysis. Accurately extracting correct features from massive can effectively improve accuracy processing algorithms. However, traditional grey wolf optimizer (GWO) algorithms often suffer slow convergence and a tendency to fall into local optima, limiting their effectiveness high-dimensional feature tasks. To address these limitations, we propose novel algorithm called with self-repulsion strategy (GWO-SRS). In GWO-SRS,...
Deformation behavior and precipitation features of an Al-Cu alloy are investigated using uniaxial tensile tests at intermediate temperatures. It is found that the true stress drops with decreased strain rate or increased deformation temperature. The number substructures degree grain elongation decrease raised temperature rate. At high temperatures low rates, some dynamic recrystallized grains can be found. type precipitates influenced by heating process before hot deformation. content size...
Traditional algorithms, such as genetic algorithm and simulated annealing, have greatly attracted a lot of research studies due to their simplicity flexibility solve coloured travelling salesman problem (CTSP). However, performance is limited in solution quality convergence speed. To improve these limitations, this study presents fast effective ant colony optimisation (FEACO) algorithm. In the proposed FEACO, new pheromone updating mechanism incorporated into traditional (ACO) its...
Variational dropout (VD) is a generalization of Gaussian dropout, which aims at inferring the posterior network weights based on log-uniform prior them to learn these as well rate simultaneously. The not only interprets regularization capacity in training, but also underpins inference such posterior. However, an improper (i.e., its integral infinite), causes be ill-posed, thus restricting performance VD. To address this problem, we present new termed variational Bayesian (VBD), turns exploit...
This paper describes a novel crossover operator, Cut-blend crossover, for genetic algorithm the TSP. may be best in such kind crossovers that improve tour using sub-tour extracted from other or tours (PMX, OX et al.). The proposed operators are embedded new algorithm, which extracts sub-tours pool consisting of former and current population, to compare with crossovers. operator is evaluated on number well-known benchmarks, e.g. oliver30, eil76, ch130 pcb442 TSPLIB. Experimental results show...
Variational Bayesian (VB) learning has been successfully applied to instantaneous blind source separation. However, the traditional VB is restricted separation of independent signals. Moreover, it difficulty recover signals with a sizable number samples because its rapidly increasing computational requirement. To overcome such shortcomings, frame-based (FVB) proposed address both and dependent large in this paper. Specifically, Gaussian process (GP) employed model or our knowledge, GP only...
The Coloured Travelling Salesman Problem (CTSP), a generalised version of the Multiple (MTSP), has been proposed to model some real-world applications. This work proposes discrete ITÔ (DITÔ) algorithm solve CTSP. It combines continuous stochastic process with Ant Colony Optimisation (ACO) algorithm. First, drift and volatility terms are designed be suitable for solving combinatorial optimisation problems, such as TSP And then, inspired by ACO, generative feasible solution CTSP is constructed...