A5084108774- Optical measurement and interference techniques
- Industrial Vision Systems and Defect Detection
- Natural Language Processing Techniques
- Nanoplatforms for cancer theranostics
- 3D Surveying and Cultural Heritage
- Nanoparticle-Based Drug Delivery
- Geophysical Methods and Applications
- Traffic Prediction and Management Techniques
- Image and Object Detection Techniques
- Manufacturing Process and Optimization
- Advanced Control Systems Optimization
- Advanced Measurement and Metrology Techniques
- Robotic Path Planning Algorithms
- Autonomous Vehicle Technology and Safety
- Advanced Vision and Imaging
- Advanced Optical Sensing Technologies
- Blockchain Technology Applications and Security
- Advanced Text Analysis Techniques
- Smart Grid Security and Resilience
- Simulation and Modeling Applications
- Immune cells in cancer
- Software-Defined Networks and 5G
- Dam Engineering and Safety
- Probabilistic and Robust Engineering Design
- Video Surveillance and Tracking Methods
Hunan University
2024
Ruian People's Hospital
2024
Yuncheng University
2024
Wenzhou Medical University
2024
Huazhong University of Science and Technology
2023
Hefei University of Technology
2023
First Affiliated Hospital of Anhui Medical University
2023
Anhui Medical University
2023
Institute of Electrical Engineering
2011
Nanjing University
2006
Abstract The frequency and amplitude characteristics derived from the Ground Penetrating Radar (GPR) data have been widely applied to object recognition in karst areas, but still meet some limitations. Here we present a new method using wavelet energy spectral analysis. First analyze GPR signals of typical samples areas obtain their spectra, which consist eigenvectors on different scales bands. Then is achieved by comparing characteristic spectra with those studied object. Both analysis...
This paper considers the problem of safe mission planning dynamic systems operating under uncertain environments. Much prior work on achieving robust and control requires solving second-order cone programs (SOCP). Unfortunately, existing general purpose SOCP methods are often infeasible for real-time robotic tasks due to high memory computational requirements imposed by optimization methods. The key contribution this is a fast memory-efficient algorithm that would enable on-board robots in...
Abstract The geometric dimensions and tolerances of blades, which are critical parts turbomachinery with complex features, must be strictly controlled to ensure the efficiency safety engine. Optical-based inspection systems for blades increasingly receiving attention because their high flexibility. However, as a key issue in blade inspection, matching part coordinate system machine directly determines measurement accuracy automation. surface is has no obvious accurate rapid thus remains...
High dynamic range 3D measurement technology, utilizing multiple exposures, is pivotal in industrial metrology. However, selecting the optimal exposure sequence to balance efficiency and quality remains challenging. This study reinterprets this challenge as a Markov decision problem presents an innovative selection method rooted deep reinforcement learning. Our approach’s foundation image prediction network (EIPN), designed predict images under specific thereby simulating virtual...
Pre-trained language models (PLMs) have significantly advanced natural processing (NLP), establishing the "pre-training + fine-tuning" paradigm as a cornerstone approach in field. However, vast size and computational demands of Transformer-based PLMs present challenges, particularly regarding storage efficiency speed. This paper addresses these limitations by proposing novel lightweight PLM optimized for accurately understanding domain-specific computer terminology. Our...
Pretrained language models (PLMs) have significantly advanced natural processing (NLP), establishing the "pretraining + fine-tuning" paradigm as a cornerstone approach in field. However, vast size and computational demands of transformer-based PLMs present challenges, particularly regarding storage efficiency speed. This paper addresses these limitations by proposing novel lightweight PLM optimized for accurately understanding domain-specific computer terminology. Our method involves...
Effective delivery of therapeutic agents for solid tumour treatment is impeded by multiple obstacles, which causes impaired penetration to deep avascular tissue that exists in a hypoxic immune cold environment.
Limited by the imaging dynamic range of camera, phenomenon over-exposure and over-dark often occurs in 3D measurement strong reflective sheet metal parts, resulting incomplete result. One existing methods such as multiple exposure can measure most visible area under a single viewpoint, but with too small or large incidence angle still cannot be measured. To solve this problem, paper, method viewpoint planning for parts reflection is proposed. The introduces surface model into to achieve...
We propose a Doppler velocity-based cluster and velocity estimation algorithm based on the characteristics of FMCW LiDAR which achieves highly accurate, single-scan, real-time motion state detection estimation. prove continuity same object. Based this principle, we achieve distinction between moving objects stationary background via region growing clustering algorithm. The obtained will be used to estimate by least-squares method. Then using estimated clustering. To ensure processing, set...