A5100688676- Soft Robotics and Applications
- Remote-Sensing Image Classification
- Advanced Neural Network Applications
- Distributed and Parallel Computing Systems
- Service-Oriented Architecture and Web Services
- Banking stability, regulation, efficiency
- Advanced Image and Video Retrieval Techniques
- Data Quality and Management
- Domain Adaptation and Few-Shot Learning
- Cloud Computing and Resource Management
- Neuroscience and Neural Engineering
- Fault Detection and Control Systems
- Cancer Cells and Metastasis
- Surgical Simulation and Training
- Web Data Mining and Analysis
- Intraoperative Neuromonitoring and Anesthetic Effects
- Advanced Decision-Making Techniques
- Occupational Health and Safety Research
- Video Surveillance and Tracking Methods
- Scientific Computing and Data Management
- BIM and Construction Integration
- Salivary Gland Tumors Diagnosis and Treatment
- Machine Fault Diagnosis Techniques
- Wireless Sensor Networks and IoT
- Technology and Security Systems
Aerospace Information Research Institute
2022-2024
Chinese Academy of Sciences
2020-2024
Beijing University of Civil Engineering and Architecture
2024
Beijing Shijitan Hospital
2023-2024
Capital Medical University
2024
Wenzhou University of Technology
2024
Fuyang Second People's Hospital
2024
Anhui Medical University
2024
Wenzhou University
2024
Nankai University
2019-2023
Robot-assisted technology is often used to perform endovascular catheterization surgeries, which generally depend on the flexible operability and accurate force feedback of a robotic system. In this paper, an system (ECRS) was developed improve collaborative operation haptic feedback. A couple operating handles were designed maximize use natural operations surgeons master side, ergonomic device. magnetically controlled structure proposed based hydrogel solid magnetorheological (MR) fluid...
In the field of remote sensing technology, semantic segmentation images carries substantial importance. The creation high-quality models for this task calls an extensive collection image data. However, manual annotation these can be both time-consuming and labor-intensive. This has catalyzed advent semi-supervised methodologies. Yet, complexities inherent within foreground categories present challenges in preserving prediction consistency. Moreover, possess more complex features, different...
We examine the impact of economic policy uncertainty (EPU) on bank liquidity hoarding. create a comprehensive measure hoarding that takes into account asset-, liability-, and off-balance sheet activities. Using over one million bank-quarter observations, we find in response to EPU, banks hoard overall through all three components. This behavior is more pronounced for with less liquidity, peer-bank spillover effects, EPU exposure. Additional analyses interest rate spreads several products...
Application of Virtual Reality in Task Training the Construction Manufacturing Industry Regina Barkokebas, Chelsea Ritter, Val Sirbu, Xinming Li and Mohamed Al-Hussein Pages 796-803 (2019 Proceedings 36th ISARC, Banff, Canada, ISBN 978-952-69524-0-6, ISSN 2413-5844) Abstract: Automation construction manufacturing is becoming increasingly common due to drive for higher productivity increased quality. One important consideration implementation automation training maintenance equipment. This...
Remarkable progress based on deep neural networks has been achieved the semantic segmentation in remote sensing images. However, pixel-level labeling is expensive for Semi-supervised becomes an alternative approach to reduce cost of annotation, and it crucial utilize efficiently a large number unlabeled data. Nevertheless inevitably, there unbalanced class distribution between labeled data scene. Existing semi-supervised methods train images isolation from only learn reliable pixel...
As an important component of Internet Things (IoT), wireless sensor-actuator networks can significantly improve the practicality and flexibility smart building systems. In systems, services, stored as rules, are achieved by rule analyzing executing. However, irrational contents rules conflicts among may bring confusion maloperation in system. To verify correctness we propose a lightweight verification resolution framework which mainly include: 1) system for content anomaly detection conflict...
Chemoresistance is one of the main reasons for poor prognosis pancreatic cancer. The effects mesothelin (MSLN) on chemoresistance in cancer are still unclear. We aim to investigate potential roles MSLN and its relationship with proliferation, epithelial-mesenchymal transition (EMT) stemness cells. Human cell lines ASPC-1 Mia PaCa-2 high low expression MSLN, respectively, were selected. knockout (KO) overexpression (OE) generated. phenotypes, EMT-related markers, clone formation, tumor sphere...
Few-shot remote sensing image classification entails identifying images using a limited set of labeled data within scenes, holding significant theoretical and practical implications. However, owing to the intricacy variety images, traditional methods usually struggle extract effective features learn robust classifiers. To address this issue, an end-to-end metric learning framework named Attention-based Contrastive Learning Network is introduced in paper. Specifically, Feature Optimization...
In recent years, more concerns are shed on the lightweight detection model in remote sensing (RS), but it is difficult to reach a competitive performance relative deep model. Knowledge distillation has been verified as promising method, which can promote of without extra parameters. While there two key issues distillation, one sample selection, other knowledge selection. Since varying object size and complex features RS, existing methods based fixed threshold incapable selecting optimal...
Cloud computing can be widely applied to various IT systems resolve data backup of current systems, as well management, system monitoring and so on for it does in large scale handling distributed management. Firstly, the architecture information based cloud is discussed concept hierarchical model proposed application architecture. Secondly, construction methods infrastructure are basis computing, framework cloudlets relationship Last but not least, resource management mechanism described....
Cloud detection relying on deep convolutional neural networks obtains remarkable accuracy gains at the expense of high computation and storage costs, which are difficult to deploy resource-constrained devices, such as intelligent satellites. Recently, knowledge distillation (KD) has been a promising solution for compact model. However, most existing KD methods only transfer feature relationship pairwise pixel fails cope with thin clouds cloud-like objects in complex scenes. Furthermore,...
Abstract Background In the past quite a long time, intraoperative cholangiography(IOC)was necessary during laparoscopic cholecystectomy (LC). Now magnetic resonance cholangiopancreatography (MRCP) is main method for diagnosing common bile duct stones (CBDS). Whether MRCP can replace IOC as routine examination before LC still inconclusive. The aim of this study was to analyze clinical data patients undergoing cholecystolithiasis, and explore necessity feasibility preoperative in with...
Collaborative trajectory prediction can comprehensively forecast the future motion of objects through multi-view complementary information. However, it encounters two main challenges in multi-drone collaboration settings. The expansive aerial observations make difficult to generate precise Bird's Eye View (BEV) representations. Besides, excessive interactions not meet real-time requirements within constrained drone-based communication bandwidth. To address these problems, we propose a novel...
Assisting in the identification of ergonomic risks for workers: a large vision-language model approach Chao Fan, Qipei Mei, Xinming Li Pages 1010-1017 (2024 Proceedings 41st ISARC, Lille, France, ISBN 978-0-6458322-1-1, ISSN 2413-5844) Abstract: In construction industry, due to workers frequently engaging highly physically demanding tasks and using various tools, are often exposed safety hazards. Various observation-based traditional or computer vision-based artificial intelligence methods...