A5100627144- Metaheuristic Optimization Algorithms Research
- Advanced Multi-Objective Optimization Algorithms
- Evolutionary Algorithms and Applications
- Advanced Algorithms and Applications
- Computational Drug Discovery Methods
- Business Process Modeling and Analysis
- User Authentication and Security Systems
- Neural Networks and Applications
- Rough Sets and Fuzzy Logic
- Advanced Sensor and Control Systems
- Service-Oriented Architecture and Web Services
- Cryptography and Residue Arithmetic
- Context-Aware Activity Recognition Systems
- Cryptography and Data Security
- Optimization and Search Problems
- Petri Nets in System Modeling
- Remote Sensing and Land Use
- Industrial Technology and Control Systems
- Advanced Decision-Making Techniques
- Anomaly Detection Techniques and Applications
- Robotics and Automated Systems
- Image and Object Detection Techniques
- Time Series Analysis and Forecasting
- Reinforcement Learning in Robotics
- Evaluation and Optimization Models
Beijing University of Chemical Technology
2014-2025
China University of Geosciences
2005-2024
Hunan Normal University
2023-2024
Guizhou University
2013-2024
Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application
2024
Nanjing University
2012-2024
Dalian University of Technology
2008-2024
Dalian Maritime University
2024
Northeast Normal University
2011-2024
Xi'an Jiaotong University
2019-2024
Differential evolution (DE) is a simple, yet efficient, evolutionary algorithm for global numerical optimization, which has been widely used in many areas. However, the choice of best mutation strategy difficult specific problem. To alleviate this drawback and enhance performance DE, paper, we present family improved DE that attempts to adaptively choose more suitable problem at hand. In addition, our proposed adaptation mechanism (SaM), different parameter methods can be strategies. order...
Predictive modelling of mineral prospectivity, a critical, but challenging procedure for delineation undiscovered prospective targets in exploration, has been spurred by recent advancements spatial techniques and machine learning algorithms. In this study, set methods, including random forest (RF), support vector (SVM), artificial neural network (ANN), deep convolutional (CNN), were employed to conduct data-driven W prospectivity the southern Jiangxi Province, China. A total 118 known...
Air quality prediction is an important reference for meteorological forecast and air controlling, but over fitting often occurs in algorithms based on a single model. Aiming at the complexity of prediction, method integrated dual LSTM (Long Short-Term Memory) model was proposed this paper. Firstly, Seq2Seq (Sequence to Sequence) technology used establish single-factor which can obtain predicted value each component data, independently. Each regarded as time series data forecasting process....
Nature-inspired optimization is a modern technique in the past decades. Researchers report their successful applications various fields such as manufacturing, biomedical, and environmental engineering, while other researchers doubt its applicability. In this paper, we collect newly emerging nature-inspired algorithms proposed after 2008, present them unified way, implement them, evaluate on benchmark functions. Moreover, optimize behavioural parameters for these algorithms. Since it...
The application of machine learning and artificial intelligence to solve scientific challenges has significantly increased in recent years. A remarkable development is the use Physics-Informed Neural Networks (PINNs) Partial Differential Equations (PDEs) numerically. However, current PINN techniques often face problems with accuracy slow convergence. To address these problems, we propose an importance sampling method generate optimal interpolation points during training. Experimental results...
Abstract In machine learning (ML) problems, it is widely believed that more training samples lead to improved predictive accuracy but incur higher computational costs. Consequently, achieving better data efficiency , is, the trade-off between size of set and output model, becomes a key problem in ML applications. this research, we systematically investigate Univariate Time Series Anomaly Detection (UTS-AD) models. We first experimentally examine performance nine popular UTS-AD algorithms as...
In this paper, we propose a population-based implementation of simulated annealing to tackle multi-objective optimisation problems, in particular those combinatorial nature. The proposed algorithm is called Evolutionary Multi-objective Simulated Annealing Algorithm (EMOSA), which combines local and evolutionary search by incorporating two distinctive features. first feature tune the weight vectors scalarizing functions (i.e., directions) for selection during using two-phase strategy. second...
We introduce quadratically gated mixture of experts (QGME), a statistical model for multi-class nonlinear classification. The QGME is formulated in the setting incomplete data, where data values are partially observed. show that missing entail joint estimation manifold and classifier, which allows adaptive imputation during classifier learning. expectation maximization (EM) algorithm derived likelihood maximization, with performed analytically E-step. performance evaluated on three benchmark...