A5101469248- Titanium Alloys Microstructure and Properties
- Advanced Welding Techniques Analysis
- Aluminum Alloys Composites Properties
- Mineral Processing and Grinding
- Robot Manipulation and Learning
- Autonomous Vehicle Technology and Safety
- Video Surveillance and Tracking Methods
- Reinforcement Learning in Robotics
- Machine Learning in Materials Science
- Robotic Path Planning Algorithms
- MXene and MAX Phase Materials
- Industrial Vision Systems and Defect Detection
- Environmental DNA in Biodiversity Studies
- Mine drainage and remediation techniques
- Adaptive Dynamic Programming Control
- Muscle activation and electromyography studies
- Automated Road and Building Extraction
- Visual Attention and Saliency Detection
- Magnesium Alloys: Properties and Applications
- Impact of Light on Environment and Health
- Imbalanced Data Classification Techniques
- Mining and Gasification Technologies
- Cellular and Composite Structures
- Image Retrieval and Classification Techniques
- Coal Properties and Utilization
Nanjing Tech University
2024
Lanzhou University
2024
Zhongyuan University of Technology
2024
Carnegie Mellon University
2017-2023
Soochow University
2020-2023
University of Science and Technology of China
2023
Beijing Institute of Technology
2021-2022
Jiangxi University of Science and Technology
2022
Xidian University
2021
Shanghai Jiao Tong University
2016-2019
Forming stable anti-corrosion surface layer and homogenized microstructure on the of material has become a major challenge in developing biomedical β titanium alloy. In study, TiO2/Ti-35Nb-2Ta-3Zr micro/nano-composites with different amount TiO2 particles were successfully fabricated by one-pass friction stir processing (FSP). The composition, electrochemical properties are characterized systematically. particular, compact passive oxide films formed after corrosion elaborated from...
<abstract><p>A multi-objective pedestrian tracking method based on you only look once-v8 (YOLOv8) and the improved simple online real time with a deep association metric (DeepSORT) was proposed purpose of coping issues local occlusion ID dynamic transformation that frequently arise when target pedestrians in complex traffic scenarios. To begin with, order to enhance feature extraction network's capacity learn information busy situations, detector implemented YOLOv8 high level...
Microstructures, mechanical, and biological properties of a novel Ti-6V-4V/zinc surface nanocomposite prepared by friction stir processing Chenyuan Zhu,1,2,* Yuting Lv,3,4,* Chao Qian,1,2,* Zihao Ding,3,5 Ting Jiao,1,2 Xiaoyu Gu,1,2 Eryi Lu,6 Liqiang Wang,3 Fuqiang Zhang1,2 1Department Prosthodontics, Ninth People's Hospital, Shanghai Jiao Tong University School Medicine, 2Shanghai Key Laboratory Stomatology, Research Institute National Clinical Center 3State Metal Matrix Composites,...
In this paper, we present a novel data-driven design method for the human-robot interaction (HRI) system, where given task is achieved by cooperation between human and robot. The presented HRI controller two-level control approach consisting of task-oriented performance optimization plant-oriented impedance design. minimizes effort guarantees perfect tracking in outer-loop, while achieves desired from to robot manipulator end-effector inner-loop. Data-driven reinforcement learning techniques...
Current explanation techniques towards a transparent Convolutional Neural Network (CNN) mainly focuses on building connections between the human-understandable input features with models' prediction, overlooking an alternative representation of input, frequency components decomposition. In this work, we present analysis connection distribution in dataset and reasoning process model learns from data. We further provide quantification about contribution different toward model's prediction....
Low‐carbon steel is an important commodity material, but poor corrosion resistance has a strong impact on its service life, which leads to great loss in economic development. Polymer coatings serve as barrier layers that confer resistance. However, robust adhesion between steels and polymer films operating complex fluids challenging. This study evaluates the utility of composed polydopamine, organic film formed through simultaneous deposition, polymerization aqueous phases. Here,...
Coal is an indispensable energy source for humans. As important part of the mining industry, intelligent separation coal and gangue will promote development. The traditional methods recognition do not consider interference created by a dynamic environment. There are many problems such as noise, complex backgrounds occlusion, which lead to low accuracy cannot satisfy real-time requirements in mining. Aiming at environments, multilevel fusion system was built this paper. First, we introduced...
A recent paradigm shift in the electron diffraction community has benefited from accessibility of large data sets and ever more complex designs convolutional neural networks (CNNs). However, this conventional feature engineering to analyzing high-level features extracted CNN is often accompanied by a reduction accuracy sensitivity. Particularly, based crystal orientation indexing using backscatter sensitive noise, reducing overall accuracy. In study, new hybrid approach been developed...
Coal is one of the most important sources in China. The separation coal and gangue a key link mining, its intellectualization promotes intelligent development mining. But it difficult to sort quickly accurately because some reasons, such as fast running speed belt, different shapes sizes gangue, so on. To solve problem, an online flexible sorting model based on multi-information fusion proposed. We use near-infrared camera identify combine with depth obtain height pose information gangue....
In this work, a biomedical Ti-6Al-4V (TC4)/Zn composite with gradient microstructures was successfully prepared by friction stir processing (FSP). The and mechanical properties of the were systematically studied using scanning electron microscope (SEM), X-ray diffractometer (XRD), transmission (TEM), atom probe tomography (APT), microhardness test. results show that TC4/Zn can be prepared, varying from coarse grain to nanocrystalline is formed bottom upper surface. During FSP, adding Zn...
Abstract Road extraction from high‐resolution remote sensing images (HRSIs) has great importance in various practical applications. However, most existing road methods have considerable limitation capturing long‐range shape feature of road, and thus, they are ineffective extracting region under complex scenes. To address this issue, a novel model called context‐aware neural network (LR‐RoadNet) is proposed. LR‐RoadNet takes advantage strip pooling to capture context horizontal vertical...
The use of robots in various industries is evolving from mechanization to intelligence and precision. These systems often comprise parts made different materials thus require accurate comprehensive target identification. While humans perceive the world through a highly diverse perceptual system can rapidly identify deformable objects vision touch prevent slipping or excessive deformation during grasping, robot recognition technology mainly relies on visual sensors, which lack critical...
This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219433.