A5100385211- Rock Mechanics and Modeling
- Fatigue and fracture mechanics
- Video Surveillance and Tracking Methods
- Geotechnical Engineering and Underground Structures
- Face recognition and analysis
- Numerical methods in engineering
- Image and Signal Denoising Methods
- Advanced Image Processing Techniques
- Advanced Graph Neural Networks
- Landslides and related hazards
- Image Processing Techniques and Applications
- Ferroptosis and cancer prognosis
- Atmospheric aerosols and clouds
- Computer Graphics and Visualization Techniques
- Advanced Neural Network Applications
- Advanced Sensor and Control Systems
- Recommender Systems and Techniques
- Radiomics and Machine Learning in Medical Imaging
- Atmospheric chemistry and aerosols
- Human Pose and Action Recognition
- Advanced Algorithms and Applications
- Seismic Imaging and Inversion Techniques
- 3D Surveying and Cultural Heritage
- Evaluation and Optimization Models
- Ship Hydrodynamics and Maneuverability
Lanzhou University
2012-2025
Beijing Zhongke Science and Technology (China)
2025
Zhengzhou University
2023-2025
First Teaching Hospital of Tianjin University of Traditional Chinese Medicine
2025
Zunyi Medical University
2022-2025
Tianjin University of Traditional Chinese Medicine
2025
Tianjin University of Technology
2024
China Iron and Steel Research Institute Group
2024
University of Science and Technology of China
2021-2024
Sichuan University
2023-2024
In point cloud analysis, point-based methods have rapidly developed in recent years. These recently focused on concise MLP structures, such as Point-NeXt, which demonstrated competitiveness with Convolutional and Transformer structures. However, standard MLPs are limited their ability to extract local features effectively. To address this limitation, we propose a Vector-oriented Point Set Abstraction that can aggregate neighboring through higher-dimensional vectors. facilitate network...
Abstract The prefabricated building construction (PBC) project is sensitive to uncertainties due the highly required coordination and interdependency among installation activities, which may cause progress delay. Hence, it necessary monitor evaluate schedule in terms of duration take proactive control actions avoid actual This study focuses on intelligent monitoring evaluation for PBC by combining computer vision‐based (CVB) technology, a weighted kernel density estimation (WKDE) method,...
Current Scene text image super-resolution approaches primarily focus on extracting robust features, acquiring information, and complex training strategies to generate images. However, the upsampling module, which is crucial in process of converting low-resolution images high-resolution ones, has received little attention existing works. To address this issue, we propose Pixel Adapter Module (PAM) based graph pixel distortion caused by upsampling. The PAM effectively captures local structural...
Abstract Particle size distributions (PSDs) are highly important in numerical models of cloud microphysical schemes. However, PSDs have large uncertainties due to complex ice particle habits and formation processes. The influential factors were investigated based on aircraft measurements cold stratiform orographic clouds August 16 29, 2020, over the Qilian Mountains (QM), northeastern Tibetan Plateau. results revealed that displayed multiple vertically layered structures, number...
To study and understand group collaborations involving multiple handheld devices large interactive displays, researchers frequently analyse video recordings of interaction studies to interpret people's interactions with each other and/or devices. Advances in ubicomp technologies allow record spatial information through sensors addition material. However, the volume data high number coding parameters involved such an analysis makes this a time-consuming labour-intensive process. We designed...
In the High Speed Internet (HSI) service of Fiber-To-The-Home (FTTH) networks, there are increasingly various applications, such as browsing, video streaming, large downloads and online games. They competing for fixed bandwidth on a best-effort basis, finally resulting in network congestion poor quality experience (QoE). Users want to improve certain applications. However, today's controller (e.g. Broadband Remote Access Server, BRAS) lacks mechanisms meet users' desire enhance QoE specific...
Chest X-ray image is an important clinical diagnostic reference to lung diseases that a serious threat human health. At present, with the rapid development of computer vision and deep learning technology, many scholars have carried out fruitful research on how build valid model for chest images recognition diseases. While some efforts are still expected improve performance enhance interpretability results. In this paper, we construct multi-scale adaptive residual neural network (MARnet)...
Graph convolutional networks (GCN) is widely used to handle irregular data since it updates node features by using the structure information of graph. With help iterated GCN, high-order can be obtained further enhance representation nodes. However, how apply GCN structured (such as pictures) has not been deeply studied. In this paper, we explore application graph attention (GAT) in image feature extraction. First all, propose a novel generation algorithm convert images into graphs through...
Recently, manual observations sequence has been gradually replaced by automatic observation sequence. The difference between and is somewhat inevitable. This challenges the homogeneity continuity of historical weather data, influences atmospheric researches applications. Therefore, based on understanding influence caused two sequences, how to modify data become a problem. In this paper, model, which modifies wind speed suquence sequence, established using wavelet neural network (WNN)....
Neonatal repetitive noxious stimuli (RNS) has been shown to cause long-term harmful effects on nociceptive processing, learning, and memory which persist until adulthood. Plasticity-related gene 1 (PRG-1) regulates synaptic plasticity functional reorganization in the brain during neuronal development. In this study, neonatal RNS rats were established by needle pricks all four feet model pain exposure infants. caused thermal hyperalgesia, mechanical allodynia, impairments manifested young...
Fall detection of the elderly is a major public health problem. Thus it has generated wide range applied research and prompted development telemedicine systems to enable early diagnosis fall conditions. This paper proposed model that uses tri-axial acceleration sensor devices detect an accidental transmit information designed servers through wireless transmission devices. The algorithm we core this which can be used directly in field. combines Sum Vector Magnitude (SVM) Activity Signal Area...