A5061525374- Privacy-Preserving Technologies in Data
- Stochastic Gradient Optimization Techniques
- Birth, Development, and Health
- Mobile Crowdsensing and Crowdsourcing
- IoT and Edge/Fog Computing
- Pregnancy and preeclampsia studies
- Advanced Sensor and Energy Harvesting Materials
- Machine Learning and Data Classification
- Fire Detection and Safety Systems
- Advanced Memory and Neural Computing
- Recommender Systems and Techniques
- Traffic Prediction and Management Techniques
- Tactile and Sensory Interactions
- Gestational Diabetes Research and Management
- Blockchain Technology Applications and Security
- Caching and Content Delivery
- Lightning and Electromagnetic Phenomena
- Service-Oriented Architecture and Web Services
- Hypothalamic control of reproductive hormones
- Hormonal and reproductive studies
- Plant Surface Properties and Treatments
- Brain Tumor Detection and Classification
- Transportation Planning and Optimization
- Plant Stress Responses and Tolerance
- Text and Document Classification Technologies
Institute of Computing Technology
2022-2025
Chinese Academy of Sciences
2016-2025
Nanjing Medical University
2024
University of Chinese Academy of Sciences
2022-2024
Huazhong University of Science and Technology
2024
Institute of Information Engineering
2024
Tsinghua University
2024
Wuhan University of Science and Technology
2023-2024
Tianjin Fire Research Institute
2023-2024
Ningbo Institute of Industrial Technology
2024
The growing interest in intelligent services and privacy protection for mobile devices has given rise to the widespread application of federated learning Multi-access Edge Computing (MEC). Diverse user behaviors call personalized with heterogeneous Machine Learning (ML) models on different devices. Federated Multi-task (FMTL) is proposed train related but ML devices, whereas previous works suffer from excessive communication overhead during training neglect model heterogeneity among MEC....
Federated learning (FL) is a privacy-preserving machine paradigm in which the server periodically aggregates local model parameters from cli ents without assembling their private data. Constrained communication and personalization requirements pose severe challenges to FL. distillation (FD) proposed simultaneously address above two problems, exchanges knowledge between clients, supporting heterogeneous models while significantly reducing overhead. However, most existing FD methods require...
Federated learning (FL) aims to learn joint knowledge from a large scale of decentralized devices with labeled data in privacy-preserving manner. However, noisy labels are ubiquitous reality since high-quality require expensive human efforts, which cause severe performance degradation. Although lot methods proposed directly deal labels, these either excessive computation overhead or violate the privacy protection principle FL. To this end, we focus on issue FL purpose alleviating degradation...
Edge Intelligence (EI) allows Artificial (AI) applications to run at the edge, where data analysis and decision-making can be performed in real-time close sources. To protect privacy unify silos distributed among end devices EI, Federated Learning (FL) is proposed for collaborative training of shared AI models across multiple without compromising privacy. However, prevailing FL approaches cannot guarantee model generalization adaptation on heterogeneous clients. Recently, Personalized (PFL)...
Federated Learning (FL) facilitates collaborative model training across decentralized clients, and achieves successes in privacy-sensitive applications such as medical analysis health care. However, data collected annotated by different clients can contain varying degrees of label noise, which decreases the overall convergence leads to performance degradation. We propose a novel end-to-end dual optimization framework, DualOptim, firstly divides into clean noisy groups via analyzing...
Abstract Objective To establish the population pharmacokinetics (PPK) of magnesium sulfate (MgSO 4 )in women with preeclampsia (PE), and to determine key covariates having an effect in Chinese PE. Methods Pregnant PE prescribed MgSO4 were enrolled this prospective study from April 2021 2023. On initial day administration, patients administered a loading dose 5 g conjunction 10 as maintenance dose. second day, only was maternal blood samples taken at 0, 4, 5, 12 h after day’s The software...
The origin of life on Earth is believed to be from the ocean, which offers abundant resources in its depths. However, deep-sea operations are limited due lack underwater robots and rigid grippers with sensitive force sensors. Therefore, it crucial for pressure sensors integrated mechanical hands manipulation. Here, a flexible stress sensor presented that can function effectively under high water deep ocean. Inspired by biological structures found abyssal zone, our designed an internal...
Recently, federated learning (FL) has achieved wide successes for diverse privacy-sensitive applications without sacrificing the sensitive private information of clients. However, data quality client datasets can not be guaranteed since corresponding annotations different clients often contain complex label noise varying degrees, which inevitably causes performance degradation. Intuitively, degradation is dominated by with higher rates their trained models more misinformation from data, thus...
Objective Type 2 diabetes mellitus (T2DM) is an endocrine-related disease with increasing incidence worldwide. Male sexual dysfunction common in diabetic patients. Therefore, we designed a Mendelian randomization (MR) study to investigate the association of type and 3 glycemic traits testosterone levels. Methods Uncorrelated single nucleotide polymorphisms (SNPs) associated T2DM (N = 228), fasting insulin 38), glucose 71), HbA1c 75) at genome-wide significance were selected as instrument...
To study the fire behavior of UHVDC (ultra-high-voltage direct current) converter transformers and effectiveness CAFs (compressed air foams) in suppressing fires, a full-scale model 220 kV transformer was constructed. The mainly considered oil pool fires spill that form after explosions, causing casing to completely fall out. hot tests were conducted on physical transformer. suppression characteristics CAF system for studied. temperature changes various locations analyzed under different...
To alleviate the pressure on ground base station (BS) from intensive video requests, unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) has become a promising and flexible solution. The UAV carries MEC server to provide caching transcoding services for adaptive bitrate streaming, which can reduce duplicate transmissions of BS content acquisition latency users, while improving flexibility delivery. However, considering uncertainty user requests popularity distribution,...
genotype and the CT+TT were significantly associated with an increased risk of
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI
Edge Intelligence (EI) enables Artificial (AI) applications to run at the edge, where data analysis and decision-making can be performed in real-time close sources. To protect privacy unify silos distributed among end devices EI, Federated Learning (FL) is proposed for collaborative training shared AI models across multiple without compromising security. However, prevailing FL approaches cannot guarantee model generalization adaptation on heterogeneous clients. Recently, Personalized (PFL)...
Robustness to label noise within data is a significant challenge in federated learning (FL).From the data-centric perspective, quality of distributed datasets can not be guaranteed since annotations different clients contain complicated varying degrees, which causes performance degradation.There have been some early attempts tackle noisy labels FL.However, there exists lack benchmark studies on comprehensively evaluating their practical under unified experimental settings.To this end, we...