A5106455667- Online Learning and Analytics
- Neural Networks and Applications
- Indoor and Outdoor Localization Technologies
- Wireless Body Area Networks
- Network Time Synchronization Technologies
- Healthcare Technology and Patient Monitoring
- Mobile Crowdsensing and Crowdsourcing
- Human Pose and Action Recognition
- Advanced Multi-Objective Optimization Algorithms
- Data Stream Mining Techniques
- Recommender Systems and Techniques
Jiangsu University
2023-2024
Yantai University
2021
Meizu (China)
2021
Knowledge distillation (KD) is a prevalent model compression technique in deep learning, aiming to leverage knowledge from large teacher enhance the training of smaller student model. It has found success deploying compact models intelligent applications like transportation, smart health, and distributed intelligence. Current methods primarily fall into two categories: offline online distillation. Offline involve one-way process, transferring unvaried student, while enable simultaneous...
In most real-world large-scale online applications (e.g., e-commerce or finance), customer acquisition is usually a multi-step conversion process of audiences. For example, an impression->click->purchase performed audiences for platforms. However, it more difficult to acquire customers in financial advertising credit card advertising) than traditional advertising. On the one hand, audience path longer, impression->click->application->approval->activation occurs during business other positive...
With the development of mobile networks and intelligent equipment, as a new data sensing paradigm in large-scale sensor applications such industrial Internet Things, crowd (MCS) assigns tasks to workers for collection sharing, which has created bright future building strong system improving services. How design an effective worker selection mechanism maximize utility crowdsourcing is research hotspot technologies. This article studies problem least make large MCS perform more achieve certain...
Security is an important factor that cannot be neglected in the design of time synchronization algorithms since industrial wireless sensor networks are prone to attacks against physical nodes and communication links. The Sybil attack intelligent with a high destructive capacity pretending multiple identities broadcasting illegitimate messages destroy network operation. Existing secure mostly focus on distributed protocols; however, they pay less attention centralized synchronization. In this...