A5100330618- Evacuation and Crowd Dynamics
- Speech Recognition and Synthesis
- Advanced Computational Techniques and Applications
- Traffic Prediction and Management Techniques
- Energy Efficient Wireless Sensor Networks
- Traffic control and management
- Transportation Planning and Optimization
- Speech and Audio Processing
- Service-Oriented Architecture and Web Services
- Music and Audio Processing
- Mobile Ad Hoc Networks
- Combustion and flame dynamics
- Traffic and Road Safety
- Advanced Combustion Engine Technologies
- Hydrocarbon exploration and reservoir analysis
- Simulation and Modeling Applications
- Cooperative Communication and Network Coding
- Business Process Modeling and Analysis
- Natural Language Processing Techniques
- Advanced Sensor and Control Systems
- Geological and Geophysical Studies
- Air Quality Monitoring and Forecasting
- Advanced MIMO Systems Optimization
- Computational Fluid Dynamics and Aerodynamics
- Geographic Information Systems Studies
Tsinghua University
2016-2025
China Institute of Water Resources and Hydropower Research
2007-2025
Beijing University of Posts and Telecommunications
2008-2025
State Grid Corporation of China (China)
2020-2025
Tianjin University
2013-2025
Ningbo University
2025
Minzu University of China
2025
Dali University
2025
Langley Research Center
2023-2024
National Earthquake Response Support Service
2023-2024
The use of satellite imagery for surface deformation monitoring has been steadily increasing. However, the study extracting slopes from data requires further advancement. This limitation not only poses challenges subsequent studies but also restricts potential deeper exploration and utilization data. LT-1 satellite, China’s largest L-band synthetic aperture radar offers a new perspective monitoring. In this study, we extracted in Chongqing its surrounding areas China based on generated by...
In cognitive radio networks, spectrum sensing is a crucial component in the discovery of opportunities for secondary systems (or unlicensed systems). The performance characterized by both accuracy and efficiency. Currently, significant research effort has been made on improving accuracy. Several exemplary techniques include energy detectors, feature cooperative sensing. these schemes, either one or multiple users (SUs) perform single same channel during each period. This strategy...
In neural network based speaker verification, embedding is expected to be discriminative between speakers while the intra-speaker distance should remain small.A variety of loss functions have been proposed achieve this goal.In paper, we investigate large margin softmax with different configurations in verification.Ring and minimum hyperspherical energy criterion are introduced further improve performance.Results on VoxCeleb show that our best system outperforms baseline approach by 15% EER,...
Forecasting and preventing urban noise pollution are major challenges in environmental management. Most existing efforts, including experiment-based models, statistical mapping, however, have limited capacity to explain the association between growth corresponding change. Therefore, these conventional methods can hardly forecast at a given outlook of development layout. This paper, for first time, introduces land use regression method, which has been applied simulating air quality decade,...
E-commerce, driven by computer and internet technology, has experienced a significant growth in almost all fields during the past two decades. E-commerce significantly changed rules of business. Numerous research institutions enterprises have made e-commerce more intelligent convenient. Here, we propose novel prototype next-generation platform with an architecture framework theoretical models. Each subject, including individual, enterprise, administrative department, his/her personalized...
Automatic identification system (AIS) is an important part of perfecting terrestrial networks, radar systems and satellite constellations. It has been widely used in vessel traffic service to improve navigational safety. Following the explosion AIS data, issues data storing, processing, analysis arise as emerging research topics recent years. Vessel trajectory compression eliminate redundant information, preserve key features, simplify information for further mining, thus correspondingly...
We report on the energy exchange between femtosecond laser filaments in air. A traveling plasma grating formed at intersection of is proposed to explain transfer. In this moving mediated mechanism transfers from lower frequency pulse its higher partner, while a traditional Kerr nonlinearity grating, transfer occurs opposite manner. Based mechanism, we demonstrate an ratio as high 50% for pulses with several millijoules.
Several solutions have been proposed for improving the Quality of Service (QoS) in wireless cellular networks, such as Call Admission Control (CAC) and handover strategies. However, none them considers usage different interfaces conditions. In this work, we propose a Fuzzy-Based Multi-Interface System (FBMIS), where each node is equipped with two interfaces: traditional network interface Mobile Ad hoc Networks (MANET)interface. The FBMIS system able to switch from ad-hoc mode vice versa. We...
Speaker embeddings achieve promising results on many speaker verification tasks.Phonetic information, as an important component of speech, is rarely considered in the extraction embeddings.In this paper, we introduce phonetic information to embedding based x-vector architecture.Two methods using vectors and multi-task learning are proposed.On Fisher dataset, our best system outperforms original approach by 20% EER, 15%, 15% minDCF08 minDCF10, respectively.Experiments conducted NIST SRE10...
Due to the frequent occurrence of multi-hazard disasters worldwide in recent years, effective scenario analysis is imperative for disaster rescue and emergency management. The response procedure different single hazards were investigated formulated before. However, investigations rarely systematically address entire development process multi-hazards, including coupling mechanisms, evolution dynamics, assessment response. To this end, paper presents our methodology that integrates...