A5100617806- Antenna Design and Optimization
- Advanced Image and Video Retrieval Techniques
- Face and Expression Recognition
- Advanced ceramic materials synthesis
- Nuclear Materials and Properties
- Catalysis and Oxidation Reactions
- Fusion materials and technologies
- Music and Audio Processing
- Social Robot Interaction and HRI
- Thermal Radiation and Cooling Technologies
- High Temperature Alloys and Creep
- Laser and Thermal Forming Techniques
- Polymer Nanocomposites and Properties
- Remote Sensing and Land Use
- X-ray Diffraction in Crystallography
- Silicone and Siloxane Chemistry
- Image Processing Techniques and Applications
- Nanocluster Synthesis and Applications
- Machine Learning in Materials Science
- Speech and Audio Processing
- Advanced Materials Characterization Techniques
- Advanced Adaptive Filtering Techniques
- Mechanical Behavior of Composites
- E-commerce and Technology Innovations
- Polymer composites and self-healing
Chinese Academy of Medical Sciences & Peking Union Medical College
2025
Northwestern Polytechnical University
2023-2024
University of Science and Technology Beijing
2016-2021
Guizhou University
2020
Shanghai University
2020
Beijing University of Posts and Telecommunications
2019
Spinel oxides have attracted extensive attention due to their unique physical, chemical, optical, and electronic properties with applications in lithium batteries, photocatalysts, ferroelectricity. Owing a large number of possible cation substitutions, many novel potential are yet be discovered interesting properties. Inspired by the data-driven materials design approach, this work, we developed machine learning (ML) models based on first-principles computational data investigate energy...
A novel functional rubber vulcanization accelerator, petal-like ZnO nanobundles grown on porous silica (ZnO-g-SiO2), was fabricated via a facile and environmentally friendly process. The zinc sources were deposited in the pores used as seeds to form silica, which formed due nucleation growth of ZnO. With incorporation ZnO-g-SiO2 into matrix, curing time greatly reduced by 8.0–61.2% compared filling made from mixed nano-ZnO silica. interaction between filler improved because structures...
As Embodied AI advances, it increasingly enables robots to handle the complexity of household manipulation tasks more effectively. However, application in these settings remains limited due scarcity bimanual-mobile robot datasets. Existing datasets either focus solely on simple grasping using single-arm without mobility, or collect sensor data a narrow scope sensory inputs. result, often fail encapsulate intricate and dynamic nature real-world that are expected perform. To address...
In unconstrained scenes, the change of expression and pose may lead to mismatching human face ear images, recognition rate also decrease. A method fusing depth texture information is proposed deal with problem. We employ different strategies based on characteristics spherical map map. The learning rank approach applied select key points high repeatability stability. An improved SIFT a LBP-like algorithm are in following process. Sparse representation used for then Bayesian decision-level...
The generative adversarial networks can be used to recognize and eliminate noise from noisy speech after extensive training. most representative model is Speech Enhancement Generative Adversarial Network (SEGAN). However, eliminating the without distortion still a challenging task especially in low SNR environment. To solve such problems, this paper proposes Multi-scale Networks (SEMGAN), whose generator discriminator are structured on basis of fully convolutional neural (FCNNs). Compared...