A5100389148- Transportation Planning and Optimization
- Traffic Prediction and Management Techniques
- Advanced Computational Techniques and Applications
- Knowledge Management and Sharing
- Traffic and Road Safety
- Traffic control and management
- Higher Education and Teaching Methods
- Advanced Steganography and Watermarking Techniques
- Civil and Geotechnical Engineering Research
- Advanced Image and Video Retrieval Techniques
- Evacuation and Crowd Dynamics
- Advanced Neural Network Applications
- Service-Oriented Architecture and Web Services
- Video Surveillance and Tracking Methods
- Human Mobility and Location-Based Analysis
- Expert finding and Q&A systems
- Digital Media Forensic Detection
- Anomaly Detection Techniques and Applications
- Education and Work Dynamics
- Sparse and Compressive Sensing Techniques
- Advanced Algorithms and Applications
- Technology and Security Systems
- Network Security and Intrusion Detection
- Image Processing Techniques and Applications
- Industrial Automation and Control Systems
State Grid Corporation of China (China)
2022-2024
Beijing University of Civil Engineering and Architecture
2009-2024
Xiamen University of Technology
2024
China Agricultural University
2024
Southwest Jiaotong University
2006-2024
Guangzhou University
2023
Changchun University of Science and Technology
2023
Wuhan University of Technology
2023
East China Normal University
2011-2023
Institute of Process Engineering
2023
Convolutional neural networks (CNNs) have facilitated impressive improvements in the semantic segmentation of very high-resolution (VHR) remote sensing images. The success depends on an effective receptive field (RF) large enough to cover entire object. Popular methods enlarge RF include dilated filters, subsampling operations, and stacking layers. Unfortunately, are inefficient or able cause grid artifacts. Moreover, although object sizes vary greatly images, size cannot reach a compromise...
Convolutional neural networks (CNNs) have attracted great attention in the semantic segmentation of very-high-resolution (VHR) images urban areas. However, large-scale variation objects areas often makes it difficult to achieve good accuracy. Atrous convolution and atrous spatial pyramid pooling composed can alleviate this problem by exploring multiscale contextual information. Unfortunately, causes gridding artifacts, where actual receptive fields are separated unit sets fail cover all...
Short term forecasting is essential and challenging in time series data analysis for traffic flow research. A novel deep learning architecture on short-term prediction was presented this work. In conventional model-driven method, a critical deviation accuracy occurred face of large fluctuations flow, while machine learning-based approaches performed well study than regression-based models. Moreover, fusion attention mechanism bidirectional long memory model (ATT-BiLSTM) proposed due to its...
Digital twin railway is a pivotal foundation for the intelligent construction and maintenance of engineering projects within extensive open spaces. Its essence integrated representation association management multi-granularity spatiotemporal data, executable analysis models, professional knowledge. These elements are characterized by prominent characteristics multi-source, heterogeneity, massive volume. However, current decentralized independent strategies often neglect dynamic coupling...
Vehicle exhaust is one of the main sources carbon emissions. The short-term traffic flow prediction plays an important role in alleviating congestion, optimizing travel structure, and reducing current advanced models are evaluated this work, especially their inadequacies. To improve accuracy ensure fine management, effective self-attention-based hybrid model proposed to predict flow. includes encoder-decoder neural network module a self-attention mechanism module. applied as feature...
Congestion and queues are crucial factors in high-passenger flow areas, affecting both traffic efficiency pedestrian comfort. Ensuring safety bottleneck areas is of utmost importance, understanding characteristics essential to improving resilience levels. In this study, a comparative experiment was conducted investigate crowd dynamics different transition types, including straight, right-angle, curve transitions. Pedestrian data were analyzed examine the impact shape on characteristics, such...
We propose a comprehensive framework to explore propagation of passenger crowdedness in public transportation systems using 74.16 million trip chains. A deep learning method HSTGCNT is adopted which firstly models normal spatio-temporal dependencies time series data, and assigns an anomaly score new data based on its prediction error. The derived discrete events are further aggregated into groups their proximity by clustering algorithm that binds shared nearest neighbors together pairwise...
A one-dimensional, vertical (1DV) grid model has been developed for the prediction of sediment transport in combined wave-current flow under sheet conditions. The uses a one-equation turbulence closure scheme to simulate mixing processes, and time-varying reference concentration as bottom boundary condition suspended layer. Comparison with recent experimental data shows that gives good predictions (within 30%) measured net rates different results also demonstrate importance "wave-related"...
Existing control schemes which distribute the roll moment by employing ratio of damping force front axle to rear using a semiactive suspension lack theoretical foundation. Given that new variable-stiffness variable-damping system configuration may require adjustment only variable damper, this study considers an ordinary magnetorheological damper itself as equivalent system. The does not need any modifications. A novel strategy is presented stiffness between and axle, regulate attitude...
The seismic source release by fault slip under the influence of mining is an important factor to induce rock burst. In this study, normal and reverse with different horizontal stress are constructed numerical simulation law stope dynamic response characteristics when panel through faults compared analyzed. Studies show that fault, level higher, so shear strength greater. When coal pillar small disturbance severe, displacement increases significantly, drops suddenly, Under load, vibration...
The aim of our study was to further develop an understanding organizational climate in knowledge sharing. We first developed a research model which three factors (friendly relation, innovation and fairness) were combined with the social cognitive theory. After developing measurement tool, we collected 142 effective questionnaires about developers from IT enterprises south China, examined revised by using confirmatory factoring analysis. found that , enterprises, relations, fairness),...
As an emerging product under the condition of informatization, utilization cloud platform in many industries has brought fundamental changes to production and business model related fields. The provides rich diverse services terminals through multi-dimensional integration different IT resources. With in-depth platform, security problems it faces are becoming more prominent. traditional network protection means have been difficult effectively adapt deal with threats new situation utilization....
Regional traffic efficiency plays a key role in the development of regional economy and its social development. How to accurately explain inherent associations mechanisms is very significant for transport investment benefits. This paper analyses road economic data Beijing-Tianjin Hebei, Yangtze River Delta Pearl city populations, identifies an yield indicator system effectively reflect development, establishes hybrid envelopment analysis model based on preferences. used compare analyze...