A5037237895- Cognitive Computing and Networks
- Image Retrieval and Classification Techniques
- Complex Network Analysis Techniques
- Semantic Web and Ontologies
- Web Data Mining and Analysis
- Advanced Text Analysis Techniques
- Network Security and Intrusion Detection
- Advanced Combustion Engine Technologies
- Advanced Image and Video Retrieval Techniques
- Anomaly Detection Techniques and Applications
- Human Mobility and Location-Based Analysis
- Vehicle emissions and performance
- Advanced Computational Techniques and Applications
- Combustion and flame dynamics
- Advanced Aircraft Design and Technologies
- Information and Cyber Security
- Service-Oriented Architecture and Web Services
- Advanced Malware Detection Techniques
- Graph Theory and Algorithms
- Data-Driven Disease Surveillance
- Big Data Technologies and Applications
- Electric and Hybrid Vehicle Technologies
- Data Mining Algorithms and Applications
- Data Management and Algorithms
- Cloud Data Security Solutions
Tsinghua University
2014-2025
Beihang University
2014-2025
Beijing Tsinghua Chang Gung Hospital
2024-2025
Zhejiang International Studies University
2024-2025
University of Electronic Science and Technology of China
2024
Shanghai Polytechnic University
2022-2024
Hangzhou Institute of Applied Acoustics
2024
Southern University of Science and Technology
2024
Shenzhen Institutes of Advanced Technology
2024
Chinese Academy of Sciences
2024
Widespread adoption of cloud computing has increased the attractiveness such services to cybercriminals. Distributed denial service (DDoS) attacks targeting cloud's bandwidth, and resources render unavailable both providers, users are a common form attacks. In recent times, feature selection been identified as pre-processing phase in DDoS attack defence which can potentially increase classification accuracy reduce computational complexity by identifying important features from original...
Association Link Network (ALN) aims to establish associated relations among various resources. By extending the hyperlink network World Wide Web an association-rich network, ALN is able effectively support intelligence activities such as browsing, knowledge discovery, and publishing, etc. Since existing methods for building semantic link on resources cannot automatically organize loose resources, effective are still challenging. In this paper, a discovery algorithm of first proposed build...
Crowdsourcing is a process of acquisition, integration, and analysis big heterogeneous data generated by diversity sources in urban spaces, such as sensors, devices, vehicles, buildings, human. Especially, nowadays, no countries, communities, person are immune to emergency events. Detection about events, e.g., fires, storms, traffic jams great importance protect the security humans. Recently, social media feeds rapidly emerging novel platform for providing dissemination information that...
Recent research shows that multimedia resources in the wild are growing at a staggering rate. The rapid increase number of has brought an urgent need to develop intelligent methods organize and process them. In this paper, semantic link network model is used for organizing resources. A whole generating association relation between using proposed. definitions, modules, mechanisms proposed method. integration provides new prospect them with their semantics. tags surrounding texts measure...
With the advances of information communication technologies, it is critical to improve efficiency and accuracy emergency management systems through modern data processing techniques. Geographic system (GIS) models simulation capabilities are used exercise response recovery plans during non-disaster times. They help decision-makers understand near real-time possibilities an event. In this paper, a participatory sensing-based model for mining spatial urban events introduced. Firstly, basic...
There is an increasing interest on accelerating neural networks for real-time applications. We study the student-teacher strategy, in which a small and fast student network trained with auxiliary information learned from large accurate teacher network. propose to use conditional adversarial learn loss function transfer knowledge student. The proposed method particularly effective relatively networks. Moreover, experimental results show effect of size when modern are used as empirically...
Summary An emergency event is an unexceptional that exceeds the capacity of normal resources and organization to cope a situation poses immediate risk health, life, property, or environment. Crowdsourcing connects unobtrusive ubiquitous sensing technologies, advanced data management analytics models, novel visualization methods, create solutions improve urban environment, human life quality, city operation systems. The crowdsourcing on social media can be used detect analyze events. In this...
Webpage recommendations for hot Web events can assist people to easily follow the evolution of these events. At same time, there are different levels semantic uncertainty underlying amount Webpages a event, such as recapitulative information and detailed information. Apparently, grasp could improve satisfactoriness recommendations. However, traditional hit-rate-based or clustering-based recommendation methods have overlooked uncertainty. In this paper, we propose framework identify in terms...