A5085295698- Machine Learning and ELM
- Fault Detection and Control Systems
- Mineral Processing and Grinding
- Neural Networks and Applications
- Service-Oriented Architecture and Web Services
- Advanced Control Systems Optimization
- Adaptive Dynamic Programming Control
- Semantic Web and Ontologies
- Smart Grid Security and Resilience
- Multi-Agent Systems and Negotiation
- Business Process Modeling and Analysis
- Face and Expression Recognition
- Control Systems and Identification
- Complex Network Analysis Techniques
- Network Time Synchronization Technologies
- Mobile Crowdsensing and Crowdsourcing
- Target Tracking and Data Fusion in Sensor Networks
- Mobile Agent-Based Network Management
- Context-Aware Activity Recognition Systems
- Data Management and Algorithms
- Recommender Systems and Techniques
- Advanced Algorithms and Applications
- AI-based Problem Solving and Planning
- Privacy-Preserving Technologies in Data
- Adaptive Control of Nonlinear Systems
China University of Mining and Technology
2016-2025
Beijing Academy of Artificial Intelligence
2025
Purdue University Northwest
2024
Wuhan College
2024
Wenhua College
2024
George Mason University
2024
Hohai University
2011-2023
Northeastern University
2013-2023
China Medical University
2023
Ministry of Education of the People's Republic of China
2022
As a class of randomized learner model, stochastic configuration networks (SCNs) have been successfully applied in few data analytics tasks. Given the industrial big modeling tasks, however, original SCNs potentially lead to excessive training time. To this end, article extends hybrid parallel version, termed (HPSCNs). In learning algorithm, two are synchronously constructed. The difference between them is that one employs point-incremental and another adopts block-incremental algorithm....
Incremental random weight networks (IRWNs) face the issues of weak generalization and complicated network structure. There is an important reason: learning parameters IRWNs are determined in a fashion without guidance, which may increase many redundant hidden nodes, thereby leading to inferior performance. To resolve this issue, novel IRWN with compact constraint that guides assignment (CCIRWN) developed brief. Using iteration method Greville, simultaneously assures quality generated nodes...
Grinding particle size (GPS) of a hematite grinding process (HGP) is characteristic sensitivity to disturbances ore hardness and distribution, difficulty in establishing mathematic model, absence measurement, which make the existing operational optimization control approaches difficult be applied. This leads that it always obtain proper feed rate water flow during operation, consequently, overload fault often occurs. To tackle this problem, based on analysis GPS, GPS prediction algorithm...
This brief is concerned with the problem of observed-based asynchronous control for a class semi-Markov jump systems (SMJSs) in continuous-time domain. There exists an phenomenon between system modes and controller due to limitations actual environment. System are usually described as hidden observable modes, respectively. Their relationship can be exhibited by emission probabilities. In this brief, model used describe such phenomenon. A conventional approach employed improved result derived...
This article investigates the optimal operational control (OOC) problem for a class of industrial systems consisting multiple unit devices with fast dynamics and an unknown process slow dynamics. First, OOC is formulated as noncascade two-time-scale novel performance function. Second, using singular perturbation theory, decentralized composite scheme proposed by decomposing original into reduced-order subsystem problems. Then, in framework reinforcement learning, online controller design...
The subject of attack detection for industrial cyber-physical systems (IPCSs) is covered in this paper, which addresses threats from transient covert attacks (TCAs), also referred to as the second version replay with a specific frequency and short duration. A comprehensive model TCAs built using active instant period attacks, well dynamics virtual system replicate IPCS function produce signals. Though watermarking-based algorithms have been shown be effective detecting TCAs, induced...
Dynamic memristor (DM)-cellular neural networks (CNNs), which replace a linear resistor with flux-controlled in the architecture of each cell traditional CNNs, have attracted researchers' attention. Compared common networks, DM-CNNs an outstanding merit: when steady state is reached, all voltages, currents, and power consumption disappeared, meantime, can store computation results by serving as nonvolatile memories. The previous study on stability rarely considered time delay, while delay...
This article is concerned with the event-based security control problem for a class of multi-time-scale cyber physical systems (MTSCPSs) subject to DoS attacks. To tackle difficulties caused by attacks and feature (MTSF), framework developed co-design switched controller event-triggered mechanism (ETM). An improved dynamic ETM proposed, which closed-loop system can achieve better performance than traditional ETMs in transient process. A novel <inline-formula...
This paper takes the case study of “Digital Signal Processing” to explore educational applications collaborative innovation under engineering accreditation. Digital signal processing is an emerging discipline that involves multiple disciplines and widely applied in many fields. course core foundational communication engineering, but it highly theoretical, difficult understand, hard master. To solve these issues, this explores teaching reform solutions from ability, creativity, classroom...
Design of advanced feedback control (AFC) for optimal process operation has been mostly based on a hierarchical structure many years. Since algorithms (such as the model predictive control) do not handle disturbances directly in their design phase, it is difficult to achieve satisfactory performance controlling complex operations presence heavy and large uncertainties. Focused this practical challenge, paper we propose novel multivariable disturbance observer (MDOB) improve rejection...
BACKGROUND:The aim of this study was to evaluate the efficacy, safety, and cost treatment traditional Chinese herbal medicine, catalpol, in patients following surgical resection for locally advanced colon cancer. MATERIAL AND METHODS:The 345 who had undergone adenocarcinoma, were divided into three groups: a placebo-treated group (n=115); treated with an intraperitoneal injection 10 mg/kg catalpol twice day 12 weeks (treatment group) 5 intravenous bevacizumab week (control (n=115). Serum...
Summary In this article, using singular perturbation theory and adaptive dynamic programming (ADP) approach, an composite suboptimal control method is proposed for linear singularly perturbed systems (SPSs) with unknown slow dynamics. First, the system decomposed into fast‐ slow‐subsystems original optimal problem reduced to two subproblems in different time‐scales. Afterward, fast subproblem solved based on known model of fast‐subsystem a law designed by solving algebraic Riccati equation...
The carrying capacity of the geological environment to human activities is limited, and maximum limit this capacity. It necessary scientifically understand concept from two dimensions: environmental conditions (the carrier) load). To date, research on has focused establishment evaluation methods indicator systems, seldom deals with driving mechanism This paper evaluates background state in Dongning-Suifenhe region by using hierarchical comprehensive index method. On basis, weighted...