Xu Liu

ORCID: 0009-0006-3139-530X
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Traffic Prediction and Management Techniques
  • Craniofacial Disorders and Treatments
  • Data Management and Algorithms
  • Geophysical Methods and Applications
  • Human Mobility and Location-Based Analysis
  • Time Series Analysis and Forecasting
  • Underwater Acoustics Research
  • Orthodontics and Dentofacial Orthopedics
  • Underwater Vehicles and Communication Systems
  • Cleft Lip and Palate Research

Nanjing University of Aeronautics and Astronautics
2024

Qingdao University
2012

Structured Abstract Objectives To differentiate a symmetric face from an asymmetric by analyzing three‐dimensional (3 D ) facial image and plotting the asymmetry index ( AI on symmetry diagram. Setting Sample Population Sixty healthy C hinese adults (30 men 30 women, mean age: 27.7 + 4.9 years old) without any craniofacial deformity were recruited voluntary basis medical center. Material Methods A 3 of each participant was captured GENEX 3D FACE CAM system. Sixteen landmarks, as defined...

10.1111/ocr.12010 article EN other-oa Orthodontics and Craniofacial Research 2012-12-04

Road traffic forecasting plays a critical role in smart city initiatives and has experienced significant advancements thanks to the power of deep learning capturing non-linear patterns data. However, promising results achieved on current public datasets may not be applicable practical scenarios due limitations within these datasets. First, limited sizes them reflect real-world scale networks. Second, temporal coverage is typically short, posing hurdles studying long-term acquiring sufficient...

10.48550/arxiv.2306.08259 preprint EN other-oa arXiv (Cornell University) 2023-01-01

Road traffic forecasting is crucial in real-world intelligent transportation scenarios like dispatching and path planning city management personal traveling. Spatio-temporal graph neural networks (STGNNs) stand out as the mainstream solution this task. Nevertheless, quadratic complexity of remarkable dynamic spatial modeling-based STGNNs has become bottleneck over large-scale data. From data perspective, we present a novel Transformer framework called PatchSTG to efficiently dynamically...

10.48550/arxiv.2412.09972 preprint EN arXiv (Cornell University) 2024-12-13
Coming Soon ...