A5101594116- 3D Shape Modeling and Analysis
- Topology Optimization in Engineering
- Reservoir Engineering and Simulation Methods
- Graph Theory and Algorithms
- Advanced Neural Network Applications
- Distributed Control Multi-Agent Systems
- Hydraulic Fracturing and Reservoir Analysis
- Advanced Graph Neural Networks
- Advanced Memory and Neural Computing
- Brain Tumor Detection and Classification
- Caching and Content Delivery
- Advanced Graph Theory Research
- Robotics and Sensor-Based Localization
- Adaptive Control of Nonlinear Systems
- Structural Health Monitoring Techniques
- Pharmacological Effects of Natural Compounds
- IoT and Edge/Fog Computing
- Robotic Path Planning Algorithms
- Poxvirus research and outbreaks
- Cognitive Computing and Networks
- Remote Sensing and LiDAR Applications
- Cryptography and Data Security
- Acne and Rosacea Treatments and Effects
- Advanced Computing and Algorithms
- Evacuation and Crowd Dynamics
Central South University
2018-2025
Sun Yat-sen University
2025
Institute of High Performance Computing
2022-2024
Agency for Science, Technology and Research
2022-2024
Xiangya Hospital Central South University
2018-2024
Northwestern University
2023-2024
Xiamen University
2024
Zhangjiakou Academy of Agricultural Sciences
2024
Swinburne University of Technology
2017-2024
Hunan University
2020-2023
Time-varying formation tracking (TVFT) control problems for a team of unmanned aerial vehicles (UAVs) with switching and directed interaction topologies are investigated, where the follower UAVs realize given time-varying while leader UAV. A TVFT protocol is firstly constructed utilizing local neighboring information, information UAV only available to partial followers neighborhood can be switching. An algorithm composed four steps provided design protocol. It proved that swarm system using...
Mobile robot path planning is a key technology and challenge in automation field. For long time, particle swarm optimization has been used planning, while the well-known shortcomings such as local minimum, premature low efficiency have prevented its extensive application. In this article, an improved localized algorithm proposed to address these problems. Firstly, improvements inertia weights, acceleration factors, localization prevent falling into minimum value increase convergence speed of...
As Large Language Models (LLMs) have achieved significant success in handling multi-modal tasks such as text, images, videos, and sounds, particularly showcasing emergent capabilities natural language tasks, they hold great potential for network operations that similarly involve vast amounts of text data, fault log files. This paper focuses on the development LLMs, detailing their fundamental principles application scenarios across different domains. It highlights remarkable LLMs diagnosis,...
For a limited set of impact conditions, drop impacting onto pool can entrap an air bubble as large its own size. The subsequent rise and rupture this plays important role in aerosol formation gas transport at the air-sea interface. is formed when crater closes up near surface known to occur only for drops that are prolate impact. Herein we use experiments numerical simulations show concentrated vortex ring, produced neck between pool, controls deformations pinchoff. However, it not strongest...
Time-series forecasting is an important problem across a wide range of domains. Designing accurate and prompt algorithms non-trivial task, as temporal data that arise in real applications often involve both non-linear dynamics linear dependencies, always have some mixtures sequential periodic patterns, such daily, weekly repetitions, so on. At this point, however, most recent deep models use Recurrent Neural Networks (RNNs) to capture these which hard parallelize not fast enough for...
Graph neural networks (GNNs), which extend conventional deep learning technologies to process graph-structured data, have shown its powerful graph representation ability. Existing typical GNNs utilize neighborhood message passing mechanism based on that updates target vertex representations by aggregating feature messages from neighboring source vertices. To accelerate the computations of GNNs, some customized accelerators, follow aggregation computation pattern for each vertex, been...
Welding defect detection in a radiographic image is an important topic the field of industrial non‐destructive testing. To improve accuracy welding segmentation, local enhancement approach proposed. In this algorithm, requirement contrast considered when extracting weld seam and segmenting defect. The whole conducted by three procedures: enhancement, extraction, segmentation. Firstly, method for determining Localised Pixel Inhomogeneity Factor (LPIF) Then, based on results LPIF, Otsu applied...
Abstract Challenge 3 of the 2022 NIST additive manufacturing benchmark (AM Bench) experiments asked modelers to submit predictions for solid cooling rate, liquid time above melt, and melt pool geometry single multiple track laser powder bed fusion process using moving lasers. An in-house developed A dditive M anufacturing C omputational F luid D ynamics code (AM-CFD) combined with a cylindrical heat source is implemented accurately predict these experiments. Heuristic calibration proposed...
Rosacea patients show facial hypersensitivity to stimulus factors (such as heat and capsaicin); however, the underlying mechanism of this hyperresponsiveness remains poorly defined. Here, we capsaicin stimulation in mice induces exacerbated rosacea-like dermatitis but has no apparent effect on normal skin. Nociceptor ablation substantially reduces dermatitis. Subsequently, find that γδ T cells express Ramp1, receptor neuropeptide CGRP, are close contact with these nociceptors significantly...