A5113118652- Reinforcement Learning in Robotics
- Simulation and Modeling Applications
- Internet Traffic Analysis and Secure E-voting
- Machine Learning and Data Classification
- Machine Learning and Algorithms
- Evacuation and Crowd Dynamics
- Media Influence and Health
- Energy Efficient Wireless Sensor Networks
- Wireless Networks and Protocols
- Autonomous Vehicle Technology and Safety
- Emotions and Moral Behavior
- Misinformation and Its Impacts
- Network Security and Intrusion Detection
- Anomaly Detection Techniques and Applications
- Advanced MIMO Systems Optimization
Xi'an Jiaotong University
2024
Peking University
2020-2022
Beijing Computing Center
2022
During the outbreak of COVID-19, information on epidemic inundated people's lives and led to negative emotions (e.g., tension, anxiety, fear) in many people. This study aims explore effect various prosocial tendencies during COVID-19 moderating severity epidemic. We these effects by conducting a text analysis content posts 387,730 Weibo users. The results show that promotes tendencies; anger motivates significantly; moderates three emotions—anger, sadness, surprise—on tendencies. These...
Learning robust driving policy for complex scenarios brings significant challenges to autonomous system due its inherent black-box properties. Recent methods learn policies from not only ego-vehicle but all the observed vehicles improve sample efficiency and scenario exposure. However, our empirical studies unveil existence of meaningless erroneous behaviors vehicles, which may result in unexpected dangerous policies. Expanding upon notion influence function, gauges effect a training on...
Pedestrian simulation is essential for verifying the safety of autonomous vehicles in simulators. The goal pedes-trian to create realistic virtual representations pedestrian. However, current simulations lack empirical knowledge about real pedestrian behavior. In this paper, we propose a reality (VR)-based method that enables real-time interaction between an individual and simulated traffic environment. Our human-in-the-loop approach incorporates VR user into simulator. can view by wearing...
As wireless networks play an increasingly important role in campus communications, identifying anomalous APs(wireless access points) is becoming important. This paper proposes unsupervised AP anomaly detection method at multiple time granularities, which does not depend on the labeling quality of training samples. In addition, proposed considers APs' behavior under different granularities and can eliminate influence improper selection granularity detection. Experimental results show that...