A5089866078- Advanced Multi-Objective Optimization Algorithms
- Probabilistic and Robust Engineering Design
- Adversarial Robustness in Machine Learning
- Model Reduction and Neural Networks
- Reliability and Maintenance Optimization
- Neural Networks and Applications
- Spacecraft Design and Technology
- Anomaly Detection Techniques and Applications
- Topology Optimization in Engineering
- Metaheuristic Optimization Algorithms Research
- Distributed Control Multi-Agent Systems
- Advanced Neural Network Applications
- Fluid Dynamics and Turbulent Flows
- Software Reliability and Analysis Research
- Heat Transfer and Optimization
- Physical Unclonable Functions (PUFs) and Hardware Security
- Risk and Safety Analysis
- Building Energy and Comfort Optimization
- Structural Health Monitoring Techniques
- Fault Detection and Control Systems
- Optimal Experimental Design Methods
- Manufacturing Process and Optimization
- Adaptive Control of Nonlinear Systems
- UAV Applications and Optimization
- Space Satellite Systems and Control
Chinese People's Liberation Army
2021-2025
PLA Academy of Military Science
2022-2024
National University of Defense Technology
2011-2024
Academy of Military Medical Sciences
2022-2024
Northern Jiangsu People's Hospital
2024
Beijing Fengtai Hospital
2024
Nanjing Agricultural University
2023
Chongqing University
2021
Hunan University
2018
Chinese Academy of Meteorological Sciences
2015
Predicting other traffic participants trajectories is a crucial task for an autonomous vehicle, in order to avoid collisions on its planned trajectory. It also necessary many Advanced Driver Assistance Systems, where the ego-vehicle's trajectory has be predicted too. Even if prediction not deterministic task, it possible point out most likely This paper presents new method which combines based Constant Yaw Rate and Acceleration motion model maneuver recognition. takes benefit accuracy of...
Radio Frequency Identification (RFID) technology not only offers tracking capability to locate equipment and people in real time, but also provides efficient accurate access medical data for doctors other health professionals. However, the reality of RFID adoption is far behind earlier expectation. This study reviews literature on applications healthcare based a formal research framework. We aim identify current opportunities, potential benefits barriers. Our shows that most care providers...
Various evolutionary algorithms (EAs) have been proposed to address feature selection (FS) problems, in which a large number of fitness evaluations are needed. With the rapid growth data scales, evaluation becomes time consuming, makes FS problems expensive optimization problems. Surrogate-assisted EAs (SAEAs) widely used solve However, SAEAs still face difficulties solving due their high-dimensional discrete decision variables. To this issue, we propose an SAEA with parallel random grouping...
Physical adversarial attacks in object detection have attracted increasing attention. However, most previous works focus on hiding the objects from detector by generating an individual patch, which only covers planar part of vehicle’s surface and fails to attack physical scenarios for multi-view, long-distance partially occluded objects. To bridge gap between digital attacks, we exploit full 3D vehicle propose a robust Full-coverage Camouflage Attack (FCA) fool detectors. Specifically, first...
Recent studies show that deep neural networks are vulnerable to adversarial attacks in the form of subtle perturbations input image, which leads model output wrong prediction. Such an attack can easily succeed by existing white-box methods, where perturbation is calculated based on gradient target network. Unfortunately, often unavailable real-world scenarios, makes black-box problems practical and challenging. In fact, they be formulated as high-dimensional optimization at pixel level....
Data-driven prediction of laminar flow and turbulent in marine aerospace engineering has received extensive research demonstrated its potential real-time recently. However, usually large amounts high-fidelity data are required to describe accurately predict the complex physical information, while reality, only limited available due high experimental/computational cost. Therefore, this work proposes a novel multi-fidelity learning method based on Fourier neural operator by jointing abundant...
For complex system design [e.g., satellite layout optimization (SLOD)] in practical engineering, when launching a new instance with another parameter configuration from the intuition of designers, it is always executed scratch which wastes much time to repeat similar search process. Inspired by transfer learning can reuse past experiences solve relevant tasks, many researchers pay more attention explore how learn instances accelerate target one. In real-world applications, there have been...