A5018788219- IoT and Edge/Fog Computing
- Cloud Computing and Resource Management
- Image and Video Quality Assessment
- Machine Learning and Data Classification
- Reinforcement Learning in Robotics
- Advanced Neural Network Applications
- Occupational Health and Safety Research
- Medical Image Segmentation Techniques
- Mobile Crowdsensing and Crowdsourcing
- Distributed and Parallel Computing Systems
- Human-Automation Interaction and Safety
- Privacy-Preserving Technologies in Data
- Risk and Safety Analysis
Huawei Technologies (China)
2022
Huawei Technologies (France)
2022
East China Normal University
2021
Shanghai University of Engineering Science
2021
Federated reinforcement learning aims to promote training efficiency or improve policy quality through information interaction with privacy protection. Existing federated methods rarely utilize the structure of algorithms while are limiting specific scenarios algorithms. We propose a general framework FRS, which employs reward shaping as shared among different clients tasks each client's speed and quality. The is implicitly learned by average state value all protect task real trajectory...
Virtual machine (VM) scheduling is one of the critical tasks in cloud computing. Many works have attempted to incorporate learning, especially reinforcement empower VM procedures. Although improved results are shown several demo simulators, performances real-world scenarios still underexploited. In this paper, we design a practical platform, i.e., VMAgent, assist researchers developing their methods on problem. VMAgent consists three components: simulator, scheduler, and visualizer. The...
Based on task analysis and multi-resource theory, this paper analyzes, classifies decomposes the tasks of urban rail transit dispatchers, establishes a workload model dispatchers based time occupancy. In addition, considering individual difference resource demand conflict between channels, supply parameter psychological interference load are introduced to modify model. Then, is validated by subjective measurement physiological measurement. The results show that established in good agreement...
With the rapid development of cloud computing, virtual machine scheduling has become one most important but challenging issues for computing community, especially practical heterogeneous request sequences. By analyzing impact heterogeneity on some popular heuristic schedulers, it can be found that existing algorithms not handle properly and efficiently. In this paper, a plug-and-play intensifier, called Resource Assigner (ReAssigner), is proposed to enhance efficiency any given scheduler...
The lack of high-quality expert labeled data is a common shortfall for medical image segmentation, which promotes semi-supervised learning scheme to an active research topic. pseudo-labeling technique has been demonstrated be powerful module in segmentation framework leveraging unlabeled data. However, simple generated pseudo labels are inevitably noisy and limited by the introduced confirmation biases, reason that prediction errors these would enhance misleading network. In this paper, we...