A5103018219- Autonomous Vehicle Technology and Safety
- Photoacoustic and Ultrasonic Imaging
- Advanced Computational Techniques and Applications
- Advanced Algorithms and Applications
- Image and Signal Denoising Methods
- Spectroscopy and Chemometric Analyses
- Advanced Sensor and Control Systems
- Simulation and Modeling Applications
- Traffic and Road Safety
- Educational Technology and Assessment
- Higher Education and Teaching Methods
- Maritime Navigation and Safety
- Regional Economic and Spatial Analysis
- Anomaly Detection Techniques and Applications
- Wireless Sensor Networks and IoT
- Metaheuristic Optimization Algorithms Research
- Robotic Path Planning Algorithms
- Spectroscopy Techniques in Biomedical and Chemical Research
- Thermography and Photoacoustic Techniques
- Optical measurement and interference techniques
- Optical Systems and Laser Technology
- Data Mining Algorithms and Applications
- Advanced Measurement and Detection Methods
- Traffic Prediction and Management Techniques
- Face and Expression Recognition
University of Science and Technology of China
2025
Harbin Institute of Technology
2009-2025
Wuhan University of Technology
2010-2024
Wuhan Polytechnic University
2015-2024
National University of Defense Technology
2024
China University of Geosciences (Beijing)
2023
Tsinghua University
2009-2022
Hainan University
2022
Changcheng Institute of Metrology & Measurement
2021
Huazhong University of Science and Technology
2014-2021
Lithology identification based on conventional well-logging data is of great importance for geologic features characterization and reservoir quality evaluation in the exploration production development petroleum reservoirs. However, there are some limitations traditional lithology process: (1) It very time consuming to build a model so that it cannot realize real-time during well drilling, (2) must be modeled by experienced geologists, which consumes lot manpower material resources, (3)...
The obstacle avoidance system of a drone affects the quality its flight path. artificial potential field method can react quickly when facing obstacles; however, traditional lacks consideration position information between drones and obstacles during flight, issues including local minima, unreachable targets, unreasonable techniques that lengthen times consume more energy get encountered. Therefore, an improved is proposed. First, collision risk assessment mechanism was introduced to avoid...
Dangerous driving behavior detection can be used in video surveillance systems to identify dangerous patterns, such as Abrupt Double Lane Change (ALC), Retrograde Driving (RD), and Illegal U-Turn (IT), for traffic design, management, law enforcement. The purpose of this study is develop a method based on surveillance. First, novel named trajectory histogram proposed. A set histograms (e.g., control points velocity histogram) constructed represent vehicle motion. Then, frequently feature...
Light confinement induced by spontaneous near-surface resonance is inherently determined the location and geometry of metallic nanostructures (NSs), offering a facile effective approach to break through limitation light-mater interaction within photoactive layers. Here, we demonstrate high-performance Al NS/ZnO quantum dots (Al/ZnO) heterostructure UV photodetectors with controllable morphologies self-assembled NSs. The Al/ZnO heterostructures exhibit superior light utilization than ZnO/Al...
Infrared (IR) solar cells are promising devices for significantly improving the power conversion efficiency of common by harvesting low-energy IR photons. PbSe quantum dots (QDs) superior photon absorbing materials due to their strong confinement and thus interdot electronic coupling. However, high chemical activity QDs leads etching poor passivation in ligand exchange, resulting a trap-state density open circuit voltage (VOC) deficit. Here we develop hybrid co-passivation strategy...
Reaction optimization plays an essential role in chemical research and industrial production. To explore a large reaction system, practical issue is how to reduce the heavy experimental load for finding high-yield conditions. In this paper, we present efficient machine learning tool called "RS-Coreset", where key idea take advantage of deep representation techniques guide interactive procedure representing full space. Our proposed only uses small-scale data, say 2.5% 5% instances, predict...
Since the advantage of hidden Markov model in dealing with time series data and for sake identifying driving style, three style (aggressive, moderate mild) are modeled reasonably through based on driver braking characteristics to achieve efficient style. Firstly, impulse maximum unit area vacuum booster within a certain collected from operation, then general emergency extracted code characteristics. Secondly, behavior observation sequence is used describe initial parameters model, generation...
The ability to identify driving risk status plays an important role for reducing the number of traffic accidents. Bayesian networks (BNs) was applied extract main factors that significantly influence status. Five (driver state, sex, experience, vehicle and environment) were selected considered based on simulation experiments. Next, a logistic regression algorithm employed establish prediction model, receiver operating characteristic curve adopted evaluate performance model. area under 0.903,...
Permeability estimation plays an important role in reservoir evaluation, hydrocarbon development, etc. Traditional methods have problems of time consuming and high cost. At present, the application machine learning are more extensive, however, some models developed for permeability fewer samples, requiring prior knowledge, parameters need to be calculated indirectly. To this end, based on a certain scale dataset, hybrid method embedded feature selection light gradient boosting (EFS-LightGBM)...
Path planning is one of the core issues in autonomous navigation an Unmanned Surface Vehicle (USV), as accuracy results directly affects safety USV. Hence, this paper proposes a USV path algorithm that integrates improved Particle Swarm Optimisation (PSO) with Dynamic Window Approach (DWA). Firstly, order to advance solution and convergence speed PSO algorithm, nonlinear decreasing inertia weight adaptive learning factors are introduced. Secondly, solve problem long non-smoothness, fitness...
Vehicle behavior learning can be used in video surveillance systems to identify normal and abnormal vehicle motion patterns for the management of traffic operations, public services, law enforcement. The purpose this paper is develop a novel adaptive sparse reconstruction method based on systems. First, ℓ0 minimization problem relaxed ℓp (0 <; p 1). A hybrid algorithm orthogonal matching pursuit-quasi-Newton proposed effectively find solutions. Then, similarity-based trajectory classifier...
The parameter value chosen to measure driving performance affects the accuracy of estimated fatigue level. Methods analyze sensitivity these values were proposed. Standard deviation lane position (SDLP) and steering reversal rate (SRR) considered assess fatigue, parameters was analyzed from time domain domain. Thirty-six male drivers participated in a field test. Lane position, wheel angle data, self-reported level (scored on Karolinska sleepiness scale) recorded. SDLP results indicate that...
The artificial potential field method has efficient obstacle avoidance ability, but this traditional suffers from local minima, unreasonable paths, and sudden changes in heading angles during avoidance, leading to rough paths increased energy consumption. To enable autonomous mobile robots (AMR) escape minimum traps move along reasonable, smooth while reducing travel time consumption, paper, an based on subareas is proposed. First, the optimal virtual subgoal was obtained around obstacles...
In this article, a tunable pulsed laser induced photoacoustic measurement setup of monitoring glucose concentration was established in the forward mode. experiments, time-resolved signal aqueous solution with different concentrations 0-300 mg/dl were captured and averaged 512 times, peak-to-peak values recorded using wavelength scan NIR region 1300-2300 nm. The optimal characteristic wavelengths determined via difference spectral first derivative algorithm, correction models between...
Some studies of driving behavior have been based on data mining to create a mechanism that relates derived from vehicle monitoring, driver behavioral characteristics, and road safety each other. To make the best GPS collected by transportation businesses explore potential rules commercial parameters related characteristics are extracted according attributes factor analysis, eight transformed into few aggregated variables containing clear information about behavior. With these as indicators,...
The newly developed scientific complementary metal oxide semiconductor (sCMOS) cameras are capable of realizing fast single molecule localization microscopy without sacrificing field-of-view, benefiting from their readout speed which is significantly higher than that conventional charge-coupled device (CCD) cameras. However, the poor image uniformity (suffered fixed pattern noise, FPN) a major obstruction for widespread use sCMOS in microscopy. Here we present quantitative investigation on...
Ant colony optimization (ACO) algorithm is a metaheuristic and stochastic search technology, which has been one of the effective tools for solving discrete problems. However, there are two bottlenecks large-scaled problems: ACO needs too much time to convergent solutions may not be really optimal. This paper proposes novel multidimensional knapsack problems (MKP), employs new pheromone diffusion model mutation scheme. First, in light preference better solutions, association distances among...