A5056456094- Machine Learning and ELM
- Neural Networks Stability and Synchronization
- Distributed Control Multi-Agent Systems
- Neural Networks and Applications
- Metaheuristic Optimization Algorithms Research
- Advanced Memory and Neural Computing
- Advanced Multi-Objective Optimization Algorithms
- Evolutionary Algorithms and Applications
- Sparse and Compressive Sensing Techniques
- Face and Expression Recognition
- Simulation and Modeling Applications
- Industrial Technology and Control Systems
- Mineral Processing and Grinding
- Opinion Dynamics and Social Influence
- Scheduling and Optimization Algorithms
- Iterative Learning Control Systems
- Mechanical Engineering and Vibrations Research
- Computational Geometry and Mesh Generation
- Advanced Measurement and Detection Methods
- Computer Graphics and Visualization Techniques
- Complex Network Analysis Techniques
- Soil, Finite Element Methods
- Aerodynamics and Fluid Dynamics Research
- Adaptive Control of Nonlinear Systems
- Advanced Numerical Analysis Techniques
Xidian University
2015-2024
Shenyang Aerospace University
2021
Northeastern University
2020
Hangzhou Dianzi University
2020
Xi'an Shiyou University
2019
Hubei Provincial Water Resources and Hydropower Planning Survey and Design Institute
2015
Henan University of Science and Technology
2011-2014
Sichuan University
2005
Principal component analysis (PCA) and independent (ICA) have been widely used for process monitoring in industry. Since the operation data of blast furnace (BF) ironmaking contain both non-Gaussian distribution Gaussian data, above single PCA or ICA method hardly describes information BF completely, which makes diagnosis abnormal working-conditions only with a prone to false positives negatives. In this article, novel integrated PCA-ICA is proposed diagnosing conditions by comprehensively...
This article studies the human-in-the-loop fuzzy iterative learning control of leader-following consensus for unknown mixed-order nonlinear multi-agent systems. The human operator participates in cooperative systems, which indirectly affects followers by directly controlling leader. Moreover, leader's input is to all followers. systems contain both first- and second-order agents, include special case By using logic approximate dynamics, a fully distributed controller with time-varying...
Binary Neural Networks (BNNs) using 1-bit weights and activations are emerging as a promising approach for mobile devices edge computing platforms. Concurrently, traditional Architecture Search (NAS) has gained widespread usage in automatically designing network architectures. However, the computation involved binary NAS is more complex than due to substantial information loss incurred by modules, different spaces required tasks. To address these challenges, universal neural architecture...
Evolutionary multitasking (EMT) with the ability to tackle multiple different tasks has attracted more and attention. The transferred knowledge among can simultaneously improve solving efficiency of all optimization problems in evolutionary process. However, if way transfer is inappropriate, negative will make a bad effect on performance EMT algorithms. It worth studying that how promote positive across tasks. In this paper, multiobjective algorithm named EMT-DAVT introduced. proposed...
A two-phase constraint-handling technique is integrated into the evolutionary algorithms to solve constrained optimization problems (called TPDE) in this article. In phase one, denoted as exploration phase, an exterior penalty function method with dynamic coefficients developed compare any two candidate solutions, which aims push population feasible region. To reduce computational burden, two, exploitation interior developed, enhances search ability by using information of constraints...
This paper aims to propose a framework for manifold regularization (MR) based distributed semi-supervised learning (DSSL) using single layer feed-forward neural network (SLFNN). The proposed framework, denoted as DSSL-SLFNN is on the SLFNN, MR and optimization strategy. Then, series of algorithms are derived solve DSSL problems. In problems, data consisting labeled unlabeled samples over communication network, where each node has only access its own can communicate with neighbors. some...
In an era of parallel computing, evolutionary multitasking optimization (EMT) has become a popular paradigm due to its ability optimize several tasks simultaneously. The common knowledge can improve the solving quality and efficiency for each component task when transferred among tasks. Therefore, performances traditional EMT algorithms mostly rely on correlation between field EMT, key issue needing be solved urgently is impact negative transfer tackling with low correlation. order overcome...