- Privacy-Preserving Technologies in Data
- Mobile Crowdsensing and Crowdsourcing
- Nonlinear Dynamics and Pattern Formation
- Artificial Intelligence in Healthcare and Education
- Cryptography and Data Security
- Topic Modeling
- Stochastic Gradient Optimization Techniques
- Data Mining Algorithms and Applications
- Software System Performance and Reliability
- Ethics and Social Impacts of AI
- Catalysts for Methane Reforming
- Service-Oriented Architecture and Web Services
- Web Applications and Data Management
- Machine Learning and Data Classification
- Cloud Computing and Resource Management
- Catalytic Processes in Materials Science
- Catalysis and Oxidation Reactions
- Advanced Differential Equations and Dynamical Systems
- Chaos control and synchronization
- Advanced Computational Techniques and Applications
Fudan University
2022-2024
Shandong University
2024
Hebei University of Engineering
2022
Huazhong University of Science and Technology
2003
As a new distributed machine learning (ML) framework for privacy protection, federated (FL) enables substantial Internet of Things (IoT) devices (e.g., mobile phones, tablets, etc.) to participate in collaborative training an ML model. FL can protect the data IoT without exposing their raw data. However, diversity may degrade overall process due straggler issue. To tackle this problem, we propose gear-based asynchronous (AsyFed) architecture. It adds gear layer between clients and server as...
Federated Learning (FL) heralds a paradigm shift in the training of artificial intelligence (AI) models by fostering collaborative model while safeguarding client data privacy. In sectors where sensitivity and AI security are paramount importance, such as fintech biomedicine, maintaining utility without compromising privacy is crucial with growing application technologies. Therefore, adoption FL attracting significant attention. However, traditional methods susceptible to Deep Leakage from...
As the major financial entity in China, banks have high performance and security requirements for databases data service solutions. With progression of application services banking, types business scenarios become more diverse, it is difficult users to make optimal choices among a wide diversity database products In combination with demands industry, this study comprehensively analyzes current status applications particularly challenges localization recent years, by using literature research...
As digital transformation continues, enterprises are generating, managing, and storing vast amounts of data, while artificial intelligence technology is rapidly advancing. However, it brings challenges in information security data security. Data refers to the protection from unauthorized access, damage, theft, etc. throughout its entire life cycle. With promulgation implementation laws emphasis on privacy by organizations users, Privacy-preserving represented federated learning has a wide...
As digital transformation continues, enterprises are generating, managing, and storing vast amounts of data, while artificial intelligence technology is rapidly advancing. However, it brings challenges in information security data security. Data refers to the protection from unauthorized access, damage, theft, etc. throughout its entire life cycle. With promulgation implementation laws emphasis on privacy by organizations users, Privacy-preserving represented federated learning has a wide...
In this paper, we propose an archetypal two DOF self-excited system driven by moving belt friction, based upon the SD oscillator mounted on a belt. The friction is modeled as Coulomb to formulate mathematical model of proposed oscillator. stability equilibria are obtained show complex equilibrium bifurcations. A three-dimensional Poincaré map constructed which characterize dynamics system. Phase portraits depicted present stick-slip periodic motion, chaotic and other friction-induced...