A5037134973- Speech and Audio Processing
- Smart Parking Systems Research
- Robotic Path Planning Algorithms
- Autonomous Vehicle Technology and Safety
- Acoustic Wave Phenomena Research
- Aerodynamics and Acoustics in Jet Flows
- Electrochemical sensors and biosensors
- Barrier Structure and Function Studies
- Vehicle Noise and Vibration Control
- Enzyme Catalysis and Immobilization
- Neuroinflammation and Neurodegeneration Mechanisms
- Gut microbiota and health
- Image and Object Detection Techniques
- Intracerebral and Subarachnoid Hemorrhage Research
- Structural Health Monitoring Techniques
- Iterative Learning Control Systems
- Advanced Control Systems Optimization
- Glioma Diagnosis and Treatment
- Vehicle Dynamics and Control Systems
- Groundwater flow and contamination studies
- CO2 Sequestration and Geologic Interactions
- Advanced Image Fusion Techniques
- CO2 Reduction Techniques and Catalysts
- Supercapacitor Materials and Fabrication
- Methane Hydrates and Related Phenomena
Institute of Process Engineering
2022-2024
Jishou University
2022-2024
Shenyang University of Chemical Technology
2023
Tongji University
2020-2022
Chongqing University
2015-2020
China University of Geosciences
2016
National University of Defense Technology
2013
In automatic parking motion planning, multi-objective optimization including safety, comfort, efficiency, and final performance should be considered. Most of the current research relies on data from expert drivers or prior knowledge humans. However, it is challenging to obtain a large amount high-quality drivers' data. Furthermore, humans does not guarantee an optimal performance. this article, we propose model-based reinforcement learning method that learns policy data, by executing...
The use of biocompatible ionic liquids (bio-ILs) as a "green" solvent with uniquely tunable cations and anions, specific selectivity, many other desirable physicochemical properties in biocatalysis has shown great promises to address challenges. A plethora studies have demonstrated ILs possess range exceptional capabilities coordinating such stabilizing enzyme structure, enhancing enzyme-substrate interaction, increasing substrate solubility product separation/removal, improving...
Gut bacteria consists of 150 times more genes than humans that are vital for health. Several studies revealed gut associated with disease status and influence human behavior mentality. Whether brain injury alters the is yet unclear, we tested 20 fecal samples from patients cerebral intraparenchymal hemorrhage corresponding healthy controls through metagenomic shotgun sequencing. The composition patients’ changed significantly at phylum level; Verrucomicrobiota was specific colonized in gut....
Reinforcement learning (RL) is a promising direction in automated parking systems (APSs), as integrating planning and tracking control using RL can potentially maximize the overall performance. However, commonly used model-free requires many interactions to achieve acceptable performance, model-based APS cannot continuously learn. In this paper, data-efficient method constructed learn from data by use of method. The proposed uses truncated Monte Carlo tree search evaluate states select...
Automatic parallel parking is critical to increase safety in urban narrow spots, maximize the traffic efficiency, and provide human drivers with mobility convenience. Recent research integrates Monte Carlo tree search (MCTS) artificial neural networks (ANNs) calculate optimal lateral motions without considering longitudinal aspect spots; advances nonlinear programming-based (NPB) methods consider time-optimal motion spots using time-consuming optimization calculation. To address...
The clinical significance of immune-related antigen
Abstract Multi‐enzymatic cascade reaction provides a new avenue for C─C coupling directly from CO 2 under mild conditions. In this study, pathway with four enzymes including formate dehydrogenase (PaFDH), formaldehyde (BmFADH), glycolaldehyde synthase (PpGALS), and alcohol (GoADH) is developed converting gas molecules to ethylene glycol (EG) in vitro. A rhodium‐based NADH regeneration electrode constructed continuously provide the proton electron of multi‐enzymatic reaction. The prepared can...
Beamforming based on microphone array measurements is a popular method for identifying sound sources. However, beamforming has many limitations that limit their precision. These are addressed in research. To separate the contributions which come from two sides of more accurately, an innovative double-layer array, called functional generalized inverse (FGIB), proposed to improve performance. This method, involves use priori regularization matrix and function redefine problem, combined with...
The acoustic imaging (AI) technique could map the position and strength of sound source via signal processing microphone array. Conventional methods, including far-field beamforming (BF) near-field holography (NAH), are limited to frequency range measured objects. A method called Bregman iteration based (BI-AI) is proposed enhance performance two-dimensional in measurements. For large-scale ℓ1 norm problem, (BI) acquires sparse solution; fast iterative shrinkage-thresholding algorithm...
A convex minimisation model for image segmentation is proposed. The basic idea of this that objects will be detected automatically if background removed. local information every pixel used to make the applicable images with intensity inhomogeneity. Also, by using a approximation Heaviside function, energy function proposed obtained. Then it minimised applying split Bregman method, which fast technique obtain global minimiser. experimental results demonstrate powerful in efficiency and accuracy.
Automated parking system (APS) that explicitly considers the time efficiency of motion has received large amounts attention in recent years. Trajectory planning module these APS delivered trajectory, which was expected to be precisely tracked by tracking module. However, reference points frequently used trackers were selected spatial domain, resulting significant trajectory errors with temporal information. In this paper, a control method called ILC-MPC, combined model predictive (MPC) and...
Three-dimensional beamforming based on microphone array signal processing is the expansion of traditional 2D beamforming. However, its identification accuracy often badly reduced by effect grating lobes and side lobes. To overcome this problem, a method called hybrid (HMB) combining functional generalized inverse with multiplicative filter spatial cross-array proposed. In method, statistically optimal iterated regularized matrix function are utilized to obtain initial result. Then high order...