- Privacy-Preserving Technologies in Data
- Advanced Malware Detection Techniques
- Reinforcement Learning in Robotics
- Cryptography and Data Security
- Vehicular Ad Hoc Networks (VANETs)
- Adversarial Robustness in Machine Learning
- Web Application Security Vulnerabilities
- Power Line Communications and Noise
- Smart Grid Energy Management
- Wireless Sensor Networks and IoT
- Artificial Intelligence in Games
- Advanced Authentication Protocols Security
- Access Control and Trust
- Advanced NMR Techniques and Applications
- Tensor decomposition and applications
- Power Systems and Technologies
- Opportunistic and Delay-Tolerant Networks
- IPv6, Mobility, Handover, Networks, Security
- Autonomous Vehicle Technology and Safety
- Blockchain Technology Applications and Security
- Technology and Security Systems
- Semiconductor Lasers and Optical Devices
- Traffic control and management
- Parallel Computing and Optimization Techniques
- Topic Modeling
Stanford University
2023-2024
Beijing University of Posts and Telecommunications
2024
State Key Laboratory of Networking and Switching Technology
2024
Beijing Jiaotong University
2021-2022
Harbin University of Science and Technology
2019
Guangdong University of Foreign Studies
2010
Training AI agents to perform complex tasks in simulated worlds requires millions billions of steps experience. To achieve high performance, today's fastest simulators for training adopt the idea batch simulation: using a single simulation engine simultaneously step many environments parallel. We introduce framework productively authoring novel (including custom logic environment generation, time stepping, and generating agent observations rewards) that execute as high-performance,...
Inefficient signal control will not only exaggerate traffic congestion, but also increase the fuel consumption and exhaust emissions. Thus, planning is highly important in green transportation. As Connected vehicle (CV) technology has transformed today's transportation systems by connecting vehicles infrastructure through wireless communication, CV-based system seen significant studies recently. Unfortunately, existing algorithms use are developed for signal-intersection, showing low...
To solve the data silos and security dilemma faced by machine learning (ML), concept of federated (FL) was first proposed, has also attracted great attention from information community in recent years, where most concerned issue is models learning. The current centralized scheme prone to single point failure as well central server evil problem, so blockchain used replace server, but network not immune poisoning attacks participants on global model inference participants' local data. this...
The aim of this study was to investigate the mechanism for security a wireless network.The research wired equivalent privacy algorithm and statistical probability model approach adopted, in addition, new WEP encryption based on introduced.The results revealed that is insufficient, concluded time crack key amount package needed capturing.The findings may make network more safety aspect data transmission, thus it be beneficial widespread network.
The controller area network (CAN) bus for interconnection of electronic control units (ECUs) plays a highly important role in modern intelligent vehicles. To facilitate the CAN Bus accessing to vehicle or diagnosis, number mobile APPs are designed and published by automobile manufacturers support driving vehicle-based social network, some realized through in-vehicle infotainment (IVI) middleware. Blockchain technologies also mature automobiles interact service information with whole...