A5055189079- Complex Network Analysis Techniques
- Opinion Dynamics and Social Influence
- Mental Health Research Topics
- Functional Brain Connectivity Studies
- Complex Systems and Time Series Analysis
- Computational Drug Discovery Methods
- Advanced Thermodynamics and Statistical Mechanics
- Advanced Graph Neural Networks
- Neural dynamics and brain function
- Catalysis for Biomass Conversion
- Bioinformatics and Genomic Networks
- Catalysis and Hydrodesulfurization Studies
- IoT and Edge/Fog Computing
- Speech Recognition and Synthesis
- Topic Modeling
- Human Mobility and Location-Based Analysis
- Speech and Audio Processing
- COVID-19 diagnosis using AI
- Graph theory and applications
- Face recognition and analysis
- Supercapacitor Materials and Fabrication
- Video Surveillance and Tracking Methods
- Soil Carbon and Nitrogen Dynamics
- Recommender Systems and Techniques
- Time Series Analysis and Forecasting
Shanghai University
2019-2024
Xi’an Jiaotong-Liverpool University
2023-2024
Yunnan Normal University
2024
Shanghai University of Engineering Science
2019-2023
Institute of Soil and Water Conservation
2023
State Key Laboratory of Soil Erosion and Dryland Farming on the Loess Plateau
2022-2023
Agriculture and Forestry University
2022
University of York
2016-2018
Jiangnan University
2017-2018
Fujian Institute of Oceanography
2016-2018
Federated learning (FL) is a privacy-preserving technique for training vast amount of decentralized data and making inferences on mobile devices. As typical language modeling problem, keyboard prediction aims at suggesting probable next word or phrase facilitating the human-machine interaction in virtual smartphone laptop. Mobile with FL hopes to satisfy growing demand that high-level privacy be preserved artificial intelligence applications even distributed models training. However, there...
Current computer-aided diagnosis system with deep learning method plays an important role in the field of medical imaging. The collaborative diseases by multiple institutions has become a popular trend. However, large scale annotations put heavy burdens on experts. Furthermore, centralized defects privacy protection and model generalization. To meet these challenges, we propose two federated active methods for multicenter diseases: Labeling Efficient Federated Active Learning (LEFAL)...
Fog computing is a promising solution to enable delay-sensitive applications in the Internet of Things (IoT). In this article, based on simultaneous wireless information and power transfer (SWIPT) technology, we investigate joint offloading tasks energy (JOTE) fog-enabled IoT networks. Specifically, task node allowed offload multiple neighboring helper nodes time-division access (TDMA) manner. When there are no queues nodes, decision for each independent. We first find strategy minimize...
Trajectory data contains rich spatial and temporal information. Turning trajectories into graphs then analyzing them efficiently in an AI-empowered way is a representative branch of trajectory analysis IoV ITS environments, which great significance. This research attempts to project onto road networks predict traffic conditions. Extracting accurate spatio-temporal dependencies the key improving analysis. However, two problems exist current study. The first one focus on network structure...
The particular environmental characteristics of deep water such as its immense scale and high pressure systems, presents technological problems that have prevented research to broaden our knowledge deep-sea fish. Here, we described the mitogenome sequence a fish, Cetonurus globiceps. genome is 17,137 bp in length, with standard set 22 transfer RNA genes (tRNAs), two ribosomal genes, 13 protein-coding typical non-coding control regions. Additionally, 70bp tRNAThr-tRNAPro intergenic spacer...
Abstract Soil microorganisms are involved in the litter decomposition process and closely related to nutrient cycling ecosystems, especially carbon (C) nitrogen (N) cycling. For grassland most biomass is invested root system. Therefore, determine influence of on soil different species, an in‐situ experiment was conducted with two species (gramineous forage: Bothriochloa ischaemum leguminous Lespedeza davurica ) over three times (90, 270 450 days). Total organic (TOC) total (TN) roots...
In the past few years, development of complex networks has stimulated great interest in study principles and mechanisms underlying Internet things (IoT). Complex have led to significant advances such an active research field been proposed tackle associated challenges. From a systematic perspective, pursue new ways represent, characterize, analyze connections interactions between huge volume sensors, actuators, processors. The theoretical framework computational tools for derive approaches...
This article explores the thermodynamic characterization of networks using heat bath analogy when energy states are occupied under different spin statistics, specified by a partition function. Using and matrix for Hamiltonian operator, we consider cases where according to Maxwell–Boltzmann, Bose–Einstein Fermi–Dirac statistics. We derive expressions variables, such as entropy, system with particles occupying given normalized Laplacian eigenvalues. The chemical potential determines number at...
Identity authentication is of great importance in the digital age where ID information commonly used finance, insurance, transportation and other fields. Challenges identity lie verification card provided by user extraction from user’s card. To meet challenge, an framework proposed, which can extract verify personal through face image recognition. The realized proposed model called Inception-ResNet Face Embedding (IRFE). IRFE uses structure to ensure a good feature aiming at accurate...
The structure of networks can be efficiently represented using motifs, which are those subgraphs that recur most frequently. One route to understanding the motif a network is study distribution statistical mechanics. In this article, we address use motifs as primitives cluster expansion from physics. By mapping clusters in gas model, derive partition function for network, and allows us calculate global thermodynamic quantities, such energy entropy. We present analytical expressions number...