A5100703114- Iterative Learning Control Systems
- Industrial Technology and Control Systems
- Robot Manipulation and Learning
- Advanced Surface Polishing Techniques
- Piezoelectric Actuators and Control
- Soft Robotics and Applications
- Advanced Vision and Imaging
- Adaptive Control of Nonlinear Systems
- Robotic Mechanisms and Dynamics
- Peptidase Inhibition and Analysis
- Glycosylation and Glycoproteins Research
- Advanced machining processes and optimization
- Pediatric health and respiratory diseases
- Design Education and Practice
- Fault Detection and Control Systems
- Product Development and Customization
- Protein Hydrolysis and Bioactive Peptides
- Optical Coherence Tomography Applications
- Anomaly Detection Techniques and Applications
- Advanced Sensor and Control Systems
- Chemical Synthesis and Analysis
- Trauma and Emergency Care Studies
- Emergency and Acute Care Studies
- Advanced Control Systems Optimization
- Control Systems in Engineering
Hefei University of Technology
2024
Shenzhen Luohu People's Hospital
2024
Toshiba (Japan)
2020-2024
Kunming University of Science and Technology
2024
Hebei University
2022
The University of Tokyo
2019
Yangzhou University
2019
Nanjing Medical University
2019
Jiangsu Province Hospital
2019
Shanghai Municipal Commission of Health and Family Planning
2017
Multiple-suction-cup grasping can improve the efficiency of bin picking in cluttered scenes. In this paper, we propose a grasp planner for vacuum gripper to use multiple suction cups simultaneously objects or an object with large surface. To take on challenge determining where and which activate when grasping, used 3D convolution convolve affordable areas inferred by neural network kernel order find graspable positions sampled orientations. The work was encoded, including cup ID information,...
Bin-picking of small parcels and other textureless planar-faced objects is a common task at warehouses. A general color image–based vision-guided robot picking system requires feature extraction goal image preparation various objects. However, for matching difficult Further, prior huge numbers images impractical warehouse. In this paper, we propose novel depth bin-picking Our method uses deep convolutional neural network (DCNN) model that trained on 15,000 annotated synthetically generated...
This paper presents a discrete learning controller for vision-guided robot trajectory imitation with no prior knowledge of the camera-robot model. A teacher demonstrates desired movement in front camera, and then, is tasked to replay it by repetitive tracking. The procedure considered as tracking control problem image plane, an unknown time-varying Jacobian matrix. Instead updating signal directly, usually done iterative (ILC), series neural networks are used approximate matrix around every...
Background With an increasing number of motor vehicle crashes, there is urgent need in emergency departments (EDs) to assess patients with multiple trauma quickly, easily, and reliably. Trauma severity can range from a minor major threats life or bodily function. In-hospital mortality prediction such cases crucial the ED for management improvement outcome these patients. Previous studies have examined performance Modified Early Warning Score (MEWS) Circulation, Respiration, Abdomen, Motor,...
Deep learning has been widely used for inferring robust grasps. Although human-labeled RGB-D datasets were initially to learn grasp configurations, preparation of this kind large dataset is expensive. To address problem, images generated by a physical simulator, and physically inspired model (e.g., contact between suction vacuum cup object) was as quality evaluation metric annotate the synthesized images. However, complicated requires parameter identification experiments ensure real world...
Addressing trajectory and attitude control challenges in quadrotor UAVs amid compound faults unknown external disturbances, this paper introduces a fault-tolerant method predicated on nonlinear extended state observers. Initially, the UAV’s dynamic model is optimized decoupled, forming rapid non-singular terminal sliding mode surface that circumvents singular phenomena typical conventional controls. A observer then deployed to estimate states triggered by disturbances within system....
In this paper, we investigate trajectory tracking in a multi-input nonlinear system, where there is little knowledge of the system parameters and form function. An identification-based iterative learning control (ILC) scheme to repetitively estimate linearity neighborhood desired presented. Based on estimation, original can track perfectly by aid regional training scheme. Just like adaptive control, singularity exists ILC when input coupling matrix estimated. Singularity avoidance discussed....
This paper presents an iterative learning scheme for vision-guided robot trajectory tracking. First, a stability criterion designing controller is proposed. It can be used system with initial resetting error. By using the criterion, one convert design problem into finding positive definite discrete matrix kernel and more general form of control obtained. Then, three-dimensional (3D) tracking single static camera to realize movement imitation presented based on this criterion.
An adaptive iterative learning control approach is proposed for a class of single-input single-output uncertain nonlinear systems with completely unknown gain. Unlike the ordinary controls that require some preconditions on gain to stabilize dynamic systems, achieves convergence through in Nussbaum-type function estimation. This paper shows all tracking errors along desired trajectory finite time interval can converge into any given precision repetitive tracking. Simulations are carried out...
Graph Convolutional Network (GCN) and its variants emerged as powerful graph deep learning methods with promising performance on analysis tasks. Different improve by introducing efficient information propagation aggregation modules of GCN. To simplify the message passing modules, we propose Multi-Layer Perceptron (G-MLP), an innovative (MLP) method that uses contrastive to implicitly extract original features learn discriminative node representations. Firstly, concatenate topology attributes...
Healthcare-associated infections (HAIs) are still a major health threats worldwide. Traditional surveillance methods involving manual by infection control practitioners (ICPs) for data collection processes laborious, inefficient, and generate of variable quality. In this study, we sought to evaluate the impact interaction platform system (SIPS) HAIs compared survey in tertiary general hospitals.A large multi-center study including 21 hospitals 63 wards were performed electronic SIPS HAIs.We...
Effective triage tools are indispensable for doctors to make a prompt decision the treatment of multiple trauma patients in emergency departments (EDs). The Modified Early Warning Score (MEWS), National (NEWS), standardized early warning score (SEWS), Rapid Emergency Medicine (mREMS), and Revised Trauma (RTS) five common proposed management. However, few studies have compared these cohort investigated influence nighttime admission on performance tools. This retrospective study was aimed at...
Aiming at the problem of wind turbine generator fault early warning, a warning method based on nonlinear decreasing inertia weight and exponential change learning factor particle swarm optimization is proposed to optimize deep belief network (DBN). With data farm supervisory control acquisition (SCADA) as input, weights biases are pre-trained layer by layer. Then BP neural used fine-tune parameters whole network. The improved algorithm (IPSO) determine number neurons in hidden model,...
An attempt has been made to understand the conformational determinants that govern hydroxylation of selected lysyl residues in nascent collagen molecule by hydroxylase (EC 1.14.11.4).A series peptide substrates enzyme, ranging length from 3 12 residues, were synthesized.These included: tert-butyloxylcarbonyl (t-Boc)-Ile-Lys-Gly; Boc-Ala-Lys-Gly; N-acetyl-Ala-Lys-Gly-Ser; Hyp-Gly-Pro-Lys-Gly-Glu; Leu-Hyp-Gly-Ala-Lys-Gly-Glu;
Objective: To study the characteristics of patients hospitalized for asthma exacerbation in 29 teaching hospitals China and to evaluate hospitalization costs these patients. Methods: This was a retrospective involved throughout during 2013-2014. Information about demographic features, conditions before admission, outcome, complications, collected using pre-designed case report form. The influencing factors were analyzed. Results: 3 240 asthmatic (1 369 males 1 871 females) included data...
The patent design around is key to the company when launch a new product. So product development must not impinge right. TRIZ power tool for analysis and innovation. evolution patterns routes help find out current technologies' developing status imply next level of technologies. problem found with consideration how achieving generation technology. contradiction solving principles designer get primal solution which existing patents have higher perform would construct by matrix inventive...
An adaptive iterative learning control(ILC) approach is proposed for a class of uncertain nonlinear systems without prior knowledge about system control directions.The Nussbaum-type gain and the positive definite discrete matrix kernel are dealing with selection unknown repeatable uncertainties, respectively.Asymptotic convergence trajectory tracking within finite time interval achieved through repetitive tracking.Simulations carried out to show validity method.
Product conceptual design process modeling is a hot issue of engineering field researches. Contradiction solving the most important kind problems to be solved and it rooted philosophy in TRIZ. The essence contradictions appeared product structure that there are conflicts between functions product. introduced, which can by using A model for function contradiction proposed. An example illustrates process.