A5101588260- Adaptive Control of Nonlinear Systems
- Adaptive Dynamic Programming Control
- Muscle activation and electromyography studies
- EEG and Brain-Computer Interfaces
- Machine Learning in Bioinformatics
- Control and Dynamics of Mobile Robots
- Influenza Virus Research Studies
- Hand Gesture Recognition Systems
- Extremum Seeking Control Systems
- Advanced Control Systems Optimization
- Hydraulic and Pneumatic Systems
- Computational Drug Discovery Methods
- Distributed Control Multi-Agent Systems
- Elevator Systems and Control
- Reinforcement Learning in Robotics
- Iterative Learning Control Systems
- Spectroscopy and Chemometric Analyses
- Viral Infections and Vectors
- vaccines and immunoinformatics approaches
- Soft Robotics and Applications
- Advanced Sensor and Energy Harvesting Materials
- Robot Manipulation and Learning
- RNA and protein synthesis mechanisms
- Food Quality and Safety Studies
- Water Quality Monitoring and Analysis
Nanjing Polytechnic Institute
2024
Nanjing University of Aeronautics and Astronautics
2018-2021
Luohe Medical College
2020
Liaoning University
2017-2019
Lysine succinylation is an extremely important protein post-translational modification that plays a fundamental role in regulating various biological reactions, and dysfunction of this process associated with number diseases. Thus, determining which Lys residues uncharacterized sequence are succinylated underpins both basic research drug development endeavors. To solve problem, we have developed predictor called pSuc-PseRat. The features the pSuc-PseRat derived from two aspects: (1) binary...
Abstract This paper discusses the problem of force estimation represented by surface electromyography (sEMG) signals collected from an armband-like collection device. The scheme is proposed for sake two dimensions sEMG signals: spatial and temporal information. From point space, first, appropriate channel number across all subjects investigated. During this progress, electrode selection method based on Spearman’s rank order correlation coefficient utilized to detect active muscle. Then,...
Abstract This paper discusses the problem of decoding gestures represented by surface electromyography (sEMG) signals in presence variable force levels. It is an attempt that multi-task learning (MTL) proposed to recognize and levels synchronously. First, methods gesture recognition with different are investigated. Then, MTL framework presented improve performance give information about Last but not least, solve using greedy principle MTL, a modified pseudo-task augmentation (PTA) trajectory...
This study presents a predictor‐based adaptive feedback control for class of systems with known input time delay, an arbitrary large unknown output unmeasurable states, unmodelled dynamics and disturbances. First, predictor is employed to cope the delay‐free system was established. Then, overcome arbitrarily delay augmented descriptor observer developed new system. Finally, neural network constructed estimate lumped term by backstepping obtain preliminary estimated model, which can...
Abstract In this article, we discuss a near‐optimal tracking control problem (NOTCP) of robots used for inspecting aircraft skin with partially unknown systems, unmeasurable states, disturbances, and output delay. A novel observer based on an augmented neural network is designed to overcome the delay, internal states. An system state, composed error reference proposed introduce new nonquadratic discounted performance function NOTCP. Due complexity in solving Hamilton–Jacobi–Bellman equation,...
Neural decoding is a technology to analyze intentions produced by neural activities, which has important applications in military, medical, entertainment and so on. As typical application, electromyogram (EMG) signals into corresponding gestures an content. In order impro ve the accuracy of EMG recognition, researchers often extract effective features from classify constructing reasonable classifier. However, because stochasticity signals, this method not robust enough. This paper proposes...
In this paper, a flexible switching control for the adsorption systems of an aircraft skin inspection robot (ASIR) suffers from problem that input saturation and state/output disturbances. This issue can be formulated as multi-agent tracking problem. An augmented disturbance observer (ADO) is designed to reconstruct original reduce effects unknown The global asymptotic stability ADO guaranteed by appropriate assumptions on system parameters physical structure. error uniformly ultimately...
A kind of adjustable external fixation device for lower extremity is designed. The circuit mainly composed TEC1-00703 semiconductor refrigeration chip, HZC-30A pressure sensor, STC89C52RC single chip microcomputer and other electrical components. It can realize the timing intelligent temperature control meet local fixed-point refrigeration. design structure application air cushion satisfy full limbs different individuals. Its operation does not need much medical knowledge. solve problem...
An aircraft skin inspection robot with double frames which crawls on the by switching between two is used to damage of skin. In this paper, a model adsorption system established. To reduce time process for frameworks, flexible control strategy proposed. Taking into account complexity and uncertainty operating environment, reinforcement learning adopted operate based interaction environment. Moreover, in order improve training efficiency, we add prior knowledge. Simulation results show...
A flexible switching mode control scheme is introduced for the two adsorption systems of aircraft skin inspection robot (ASIR) with completely unknown system dynamics. This issue converted into a two-subsystem tracking issue. The original and their desired trajectories are reformed as new augmented systems. An algebraic Riccati equation (ARE) derived based on performance function adaptive policy using integral reinforcement learning (IRL) developed to overcome optimal problem simulation...