A5041606758- Traffic Prediction and Management Techniques
- Traffic control and management
- Hydrological Forecasting Using AI
- Anomaly Detection Techniques and Applications
- Transportation Planning and Optimization
- Geoscience and Mining Technology
- Network Security and Intrusion Detection
- Human Mobility and Location-Based Analysis
- Water Quality Monitoring Technologies
- Grouting, Rheology, and Soil Mechanics
- Age of Information Optimization
- Advanced Decision-Making Techniques
- melanin and skin pigmentation
- IoT and Edge/Fog Computing
- Geomechanics and Mining Engineering
- Artificial Immune Systems Applications
- Neural Networks and Applications
- Data Stream Mining Techniques
- Image Enhancement Techniques
- Medical Imaging and Analysis
- Scoliosis diagnosis and treatment
- Context-Aware Activity Recognition Systems
- Advanced Image Fusion Techniques
- Stock Market Forecasting Methods
- Geotechnical Engineering and Analysis
Hebei University of Engineering
2023-2025
Jiangnan University
2020-2023
Nanjing University of Science and Technology
2022
Guangzhou Metro Group (China)
2019
Central South University
2010
Xiangya Hospital Central South University
2010
Spatial–temporal graph modeling plays an important role in the fields of transportation, meteorology, and social networks. Traffic flow prediction is a classic spatial–temporal task. Existing methods usually do not take into account asynchronous correlation traffic data. In addition, due to complexity variability data, long-term forecasting highly challenging. order solve above problems, this article proposes new deep learning-based dilation convolution network (ADGCN) model graphs. We mine...
Data missing problems often occur on the Internet-of-Things domains. This article proposes a type-aware interpolation framework (IMA) for data loss in city-wide environmental monitoring systems that contain many scattered stations. To interpolate as accurately possible, IMA considers three aspects of information, i.e., spatiotemporal, all attributes one measurement, and values accordingly develop methods to estimate data. First, we an improved multiviewer method, which uses spatiotemporal...
Abstract In Guangzhou Metro line 21 tunnel construction process, weathered granite shows diversification in strength, deformation characteristics and permeability characteristics. The rock mass coefficient is the core parameter necessary construction, definition of its value directly affects accuracy calculation design anti-drainage structure negative effect evaluation groundwater environment. With on-site indoor tests, theoretical calculations, microstructure observations mineral analysis,...
Wireless Sensor Network (WSN) has already been deployed widely in industrial, agriculture and many other fields. Meaningful information extracted from the data collected by WSNs can assist people making control decisions. Anomaly detection of sensor is critical to ensure quality reliability WSNs. In recent years, distance-based anomaly methods have attracted attention experts. Though these achieve a good effect, exploitation spatio-temporal correlation not sufficient. Therefore, we propose...
Objective To set up and validate three-dimensional finite element model (FEM) of Lenke 1 BN idiopathic scoliosis based on CT images, for building ideal digitization platform further biomechanical study. Methods An 18-year-old female patient was selected as volunteer current transverse scanning in supine position done from T1 to caudal end 1mm layer interval. All images were imported into Mimics 10.01 form qualified AIS geometric after geometry clean, including all thoraco-lumbar-sacral...
In order to decrease the negative influence of water inflow on tunnel construction, risk should be evaluated and predicted. Based method experts' evaluation, combined with practical project, an assessment system into mountain was set up, in which 9 evaluation indicators were proposed from geological factors, hydrologic conditions engineering three aspects, every index weight counted AHP. With BP neural network as tool, integrated prediction model for established. The results Guangzhou Metro...
Deep graph convolution networks (GCNs) have recently shown excellent performance in traffic prediction tasks. However, they face some challenges. First, few existing models consider the influence of auxiliary information, i.e., weather and holidays, which may result a poor grasp spatial-temporal dynamics data. Second, both construction dynamic adjacent matrix regular operations quadratic computation complexity, restricts scalability GCN-based models. To address such challenges, this work...
Abstract In order to figure out the negative effect on groundwater environment caused by weathered granite tunnel construction with mining method, influence factors were considered comprehensively establish evaluation index system and classification standard for environment. The fuzzy comprehensive analytic hierarchy process used quantify indexes determine weight of indexes. evaluate method was developed based GIS applied a section Guangzhou Metro line 21. research results show that:...