A5113692017- Radar Systems and Signal Processing
- Advanced SAR Imaging Techniques
- Geomagnetism and Paleomagnetism Studies
- Computational Fluid Dynamics and Aerodynamics
- Industrial Vision Systems and Defect Detection
- Geological and Geophysical Studies
- Spectroscopy and Chemometric Analyses
- Target Tracking and Data Fusion in Sensor Networks
- Geological and Geochemical Analysis
- RFID technology advancements
- Advanced Manufacturing and Logistics Optimization
- Indoor and Outdoor Localization Technologies
- Direction-of-Arrival Estimation Techniques
- Advanced Vision and Imaging
- Gas Dynamics and Kinetic Theory
- Advanced machining processes and optimization
- Photoacoustic and Ultrasonic Imaging
- Computational Drug Discovery Methods
- Advanced Measurement and Detection Methods
- Machine Fault Diagnosis Techniques
- Surface Roughness and Optical Measurements
- Advanced Image and Video Retrieval Techniques
- Infrared Target Detection Methodologies
- Microwave Imaging and Scattering Analysis
- Inertial Sensor and Navigation
Shenyang Institute of Automation
2016-2025
Chinese Academy of Sciences
2015-2025
Shandong University of Traditional Chinese Medicine
2024-2025
China Academy of Chinese Medical Sciences
2025
Tobacco Research Institute
2014-2024
China University of Geosciences
2015-2021
University of Chinese Academy of Sciences
2020
Institute of Atmospheric Physics
2012
Tsinghua University
2011
Institute of Engineering Thermophysics
1987
Pedestrian protection system plays an important role in perceptual of unmanned vehicles and Advanced Drive Assistant System. In order to get more details information about surrounding objects, such kind intelligence is usually equipped with different sensors, so technology fuse heterogeneous sensors very important. This paper proposed a novel way the radar image camera realize pedestrian detection acquire its dynamic information. Contribution this are as following First, new intra-frame...
P38α has been identified as a key target for drug design to treat wide range of diseases. In this study, multiple independent Gaussian accelerated molecular dynamics (GaMD) simulations, deep learning (DL), and the mechanics generalized Born surface area (MM-GBSA) method were used investigate binding mechanism inhibitors (SB2, SK8, BMU) DFG-in DFG-out clarify effect conformational differences in on inhibitor binding. GaMD trajectory-based DL effectively important functional domains, such...
Abstract For bearing fault diagnosis problems in extremely noisy environments, this paper proposes an innovative universal adversarial training method. This method dynamically introduces noise into the data, adaptively optimizing model’s robustness. It applies to any neural network without incurring additional computational overhead reasoning process. Additionally, we introduce multi-scale channel attention (MSCAN). employs stacked convolutional kernels of varying sizes extract features at...
Continuous waveform (CW) radar is widely used in intelligent transportation systems, vehicle assisted driving, and other fields because of its simple structure, low cost high integration. There are several waveforms which have been developed the last years. The chirp sequence has ability to extract range velocity parameters multiple targets. However, conventional suffer from Doppler ambiguity problem. This paper proposes a new that follows practical application requirements, precision system...
This paper considers the detection of fluctuating targets in heavy-tailed clutter through use dynamic programming based on track-before-detect (DP–TBD) radar systems. The is modeled terms K-distribution, which can be widely used to describe non-Gaussian received from high-resolution radars and working at small grazing angles. Swerling type 1 considered target fluctuation between scans. Conventional TBD techniques suffer significant performance loss environments due more frequent occurrences...
MIMO (multiple-input multiple-output) radar has been recently introduced as an important new system which emits orthogonal waveforms to cover a wide surveillance space. Therefore, the electronic reconnaissance technology for is of great significance in future war. In this paper, mode and identification algorithm proposed. detail, single aircraft used fly along circumference suspicious radar, collecting radiated signals on multiple positions. Furthermore, collected data analyzed number...
Unsupervised real-time stereo matching is of great research value in robot navigation due to its independence from ground truth and efficiency. The core challenge lies the design loss functions that can provide accurate guidance efficient network architectures. commonly used photometric prone incorrect because influence reflection, left-right color inconsistency, low texture, occlusion. As a weak supplement, smoothness ameliorate multi-solution problems caused by but it not effective for...
BACE1 has been regarded as an essential drug design target for treating Alzheimer's disease (AD). Multiple independent Gaussian accelerated molecular dynamics simulations (GaMD), deep learning (DL), and mechanics general Born surface area (MM-GBSA) method are integrated to elucidate the mechanism underlying effect of D93 D289 protonation on binding inhibitors OV6 4B2 BACE1. The GaMD trajectory-based DL successfully identifies significant function domains. Dynamic analysis shows that strongly...
Considering radar detection for multi-target recognition, a track before detect (TBD) algorithm based on Hough transform is adopted identifying and tracking radar. By increasing the dimensions of target characteristic parameters, accuracy increased. Also, by multilevel filtering processing, diverging points echo signal are condensed, which improves performance multiple targets. Simulation results show that compared with traditional TBD algorithms, presented has better in aspects tracking,...
This paper proposes an interacting multi-model (IMM) tracking algorithm based on the adaptive Markov transition probability matrix, which can be utilized in radar systems for maneuvering target tracking. The constructs likelihood ratio function of motion model, and presents probabilities calculated thought. Base "new information" structure model function, system online adjustment noise variance matrix adaptively. Monte Carlo simulation is carried out by software, shows that performance...