A5104096588- Remote Sensing and Land Use
- Remote-Sensing Image Classification
- Electrochemical sensors and biosensors
- Concrete and Cement Materials Research
- Topic Modeling
- Advanced Nanomaterials in Catalysis
- Microbial Applications in Construction Materials
- Multimodal Machine Learning Applications
- Tribology and Wear Analysis
- Advanced Image Fusion Techniques
- Gaze Tracking and Assistive Technology
- Domain Adaptation and Few-Shot Learning
- Conducting polymers and applications
- Grouting, Rheology, and Soil Mechanics
- Metamaterials and Metasurfaces Applications
- Optical measurement and interference techniques
- Advanced Neural Network Applications
- Advanced Antenna and Metasurface Technologies
- Seismology and Earthquake Studies
- Quantum Dots Synthesis And Properties
- Electromagnetic wave absorption materials
- Fiber-reinforced polymer composites
- Gear and Bearing Dynamics Analysis
- Tactile and Sensory Interactions
- Advancements in Battery Materials
Beijing University of Posts and Telecommunications
2024
Xi'an University of Technology
2024
Northwestern Polytechnical University
2023
Shandong University
2022-2023
University of Michigan–Ann Arbor
2022
Nanjing University of Information Science and Technology
2019
Nanjing Foreign Language School
2018
Jiangnan University
2015
Kernel methods, e.g., composite kernels (CKs) and spatial-spectral (SSKs), have been demonstrated to be an effective way exploit the information nonlinearly for improving classification performance of hyperspectral image (HSI). However, these methods are always conducted with square-shaped window or superpixel techniques. Both techniques likely misclassify pixels that lie at boundaries class, thus a small target is smoothed away. To alleviate problems, in this paper, we propose novel...
The kernel-based spatial-spectral approach has been widely used for hyperspectral image (HSI) classification in recent years, where composite kernel (CK) and (SSK) are the most representative methods. Unlike CK, SSK measures similarity of two clusters space to capture hidden manifold HSI, which proven be powerful handle well-known sample selection bias problem. However, cluster feature is always handled by a spatial filter treats as collection individually independent pixels. This neither...
The ability to associate touch with sight is essential for tasks that require physically interacting objects in the world. We propose a dataset paired visual and tactile data called Touch Go, which human collectors probe natural environments using sensors, while simultaneously recording egocentric video. In contrast previous efforts, have largely been confined lab settings or simulated environments, our spans large number of "in wild" scenes. To demonstrate dataset's effectiveness, we...
Carbon Nanotubes (CNTs) reinforced Polymer-Matrix Composites (PMCs) is widely used as insulation materials in thermal protection system of aerospace propulsion. However, CNTs are prone to oxidation and have high conductivities, which makes it difficult improve the ablation resistance that contain CNTs. SiO2 was encapsulated onto surface (CNTs@SiO2), were then added Ethylene Propylene Diene Monomer (EPDM) rubber prepare materials. Thermogravimetric analysis test evaluate ablation....
Geospatial semantic segmentation on remote sensing images suffers from large intra-class variance in both fore-ground and background classes. First, foreground objects are tiny the represented by only a few pixels, which leads to undermines discrimination between classes (issue firstly considered this work). Second, class contains complex context, results false alarms due variance. To alleviate these two issues, we construct sparse complete latent structure via prototypes. In particular,...
Designing dielectric absorber materials with wideband absorption, wide-angle performance, and lightweight characteristics remains a significant challenge. Inspired by the porous structure of volcanic rock, this study employed simple one-step hydrothermal method bubble assistance to synthesize micro/mesoporous Ni2P−Cu3P binary nanophosphides, which were then enhanced CNTs create three-dimensional mesh structure. The nanocomposite not only facilitates formation rich heterogeneous interfaces on...
Fault detection can provide constructive guidance for the predictive maintenance of rolling element bearings. For detecting different faults, permutation entropy (PE) has served as an effective tool due to its ability measure dynamic complexity fault signals. Unfortunately, existing PE-based methods only consider one-fold oscillatory pattern, which limits feature extraction ability. To address above issue, this paper proposed multiresolution (MRPE) match patterns by multiple wavelets. Based...
In this paper, aiming at robot target recognition and path planning, an algorithm of based on clustering analysis, which eliminates the traditional boundary extraction algorithm, decreases CPU time, improves real-time performance, is proposed, a related hardware software module design are implemented, including claw grab mechanism, drive control unit, visual Mecanum four-wheeled mobile platform, universal driver, app, etc. The can realize automatic operation manual by training calibration...
The objective of this work is to optimize the performance a constant flow parallel mechanical displacement micropump, which has pump chambers and incorporates passive check valves. critical task minimize pressure pulse caused by regurgitation, negatively impacts rate, during reciprocating motion when left right pumps interchange their role aspiration transfusion. Previous works attempt solve issue via design In work, novel concept overlap time proposed, solved from aspect control theory...
é«å 谱红å¤ä¼ æå¨é«ç²¾åº¦å¨è½¨å è°±å®æ æ¯çº¢å¤é¥æå®éåæ¼ååºç¨çéè¦åæãæ¬æé对大æ°çº¢å¤æ¢æµä»ªAIRSï¼Atmospheric Infrared Sounderï¼çè§æµæ°æ®ï¼åæä¼ æå¨çæå ¥ç³äº®æ¸©ä¸å¤§æ°éè¿çå è°±ä¸çå¸æ¶çº¿ç¹å¾ï¼åºäºNODDåå ç»çº¿å»é¤çå è°±å½ä¸åå¤çï¼èåå¤ç§å è°±å¹é ç®æ³æ建é线æ§ä»£ä»·å½æ°ï¼æåºäºä¸ç§æ éå°è¡¨å®æµæ°æ®æ¯æçé«å æå¨å æ¹æ³ãä¸JPLå®æ¹å®æ...