A5100409855- Advanced MIMO Systems Optimization
- Advanced Graph Neural Networks
- Millimeter-Wave Propagation and Modeling
- Advanced Steganography and Watermarking Techniques
- Digital Media Forensic Detection
- Advanced Wireless Communication Technologies
- Wireless Communication Security Techniques
- Smart Grid Energy Management
- Power Systems and Technologies
- Smart Grid and Power Systems
- Adversarial Robustness in Machine Learning
- Electronic Packaging and Soldering Technologies
- Geochemistry and Geologic Mapping
- Energy Harvesting in Wireless Networks
- Cooperative Communication and Network Coding
- Chaos-based Image/Signal Encryption
- Quantum Computing Algorithms and Architecture
- Generative Adversarial Networks and Image Synthesis
- Face recognition and analysis
- AI in cancer detection
- Power System Optimization and Stability
- Blind Source Separation Techniques
- Optimal Power Flow Distribution
- Geological and Geochemical Analysis
- Network Security and Intrusion Detection
Central South University
2015-2025
Nankai University
2025
Affiliated Hospital of Jiangsu University
2025
Jiangsu University
2025
Chinese Center For Disease Control and Prevention
2021-2024
State Grid Hebei Electric Power Company
2023
State Grid Corporation of China (China)
2018-2023
Quantum Technology Sciences (United States)
2023
Beijing University of Posts and Telecommunications
2023
China Aerodynamics Research and Development Center
2022
In recent years, with the rapid enhancement of computing power, deep learning methods have been widely applied in wireless networks and achieved impressive performance. To effectively exploit information graph-structured data as well contextual information, graph neural (GNNs) introduced to address a series optimization problems networks. this overview, we first illustrate construction method communication for various simply introduce progress several classical paradigms GNNs. Then,...
Millimeter-wave (mmWave) frequency bands, which offer abundant underutilized spectral resources, have been explored and exploited in the past several years to meet requirements of emerging wireless services highlighted by high data rates, ultrareliability, ultralow delivery latency. Yet, unique characteristics mmWave, e.g., continuous wide bandwidth, large path, penetration losses, along with hardware constraints, call for innovative technologies mmWave communication. Recently, an extensive...
Driven by the explosive growth of Internet Things (IoT) devices with stringent requirements on latency and reliability, ultra-reliability low communication (uRLLC) has become one three key scenarios for 5th generation (5G) 6G systems. In this paper, we focus beamforming design problem downlink multiuser uRLLC system. Since strict demand reliability latency, in general, short packet transmission is a favorable way systems, which indicates classical Shannon's capacity formula no longer...
The KNN (K-nearest neighbors) algorithm is one of Top-10 data mining algorithms and widely used in various fields artificial intelligence. This leads to that quantum have developed achieved certain speed improvements, denoted as Q-KNN. However, these Q-KNN methods must face two key problems follows. first they are mainly focused on neighbor selection without paying attention the influence K value algorithm. second only process quantized, not quantized. To solve problems, this paper designs a...
The non-orthogonal multiple access (NOMA) technique or more generally the principle is a crucial component for next generation cellular system. For two-user downlink NOMA, constellations of near and far users are superposed transmission, maximum likelihood (ML) successive interference cancellation (SIC) receiver used reception. In this paper, we aim to further enhance linklevel performance NOMA with ML receiver. A method constellation rotation proposed where respectively rotated before...
Femtocells are considered as promising technologies for the next generation wireless networks to improve system capacity and enhance indoor coverage. The dense deployment of femtocells brings a lot challenges in terms interference management energy consumption. To alleviate co-channel interference, we investigate based on hierarchically joint user scheduling power control downlink femtocell considering impact cost. Then, formulate this problem Stackelberg game with one leader multiple...
Electroencephalography (EEG) is widely used for analyzing brain activity; however, the nonlinear and nature of EEG signals presents significant challenges traditional analysis methods. Machine has shown great promise in addressing these limitations. This study proposes a novel approach using Radial Function (RBF) neural networks optimized by Particle Swarm Optimization (PSO) to reconstruct dynamics extract age-related characteristics. recordings were collected from 142 participants spanning...
Unauthorised face recognition (FR) systems have posed significant threats to digital identity and privacy protection. To alleviate the risk of compromised identities, recent makeup transfer-based attack methods embed adversarial signals in order confuse unauthorised FR systems. However, their major weakness is that they set up a fixed image unrelated both protected reference images as confusion identity, which turn has negative impact on success rate visual quality transferred photos. In...
Knowledge graph (KG) fact prediction aims to complete a KG by determining the truthfulness of predicted triples. Reinforcement learning (RL)-based approaches have been widely used for prediction. However, existing largely suffer from unreliable calculations on rule confidences owing limited number obtained reasoning paths, thereby resulting in decisions Hence, we propose new RL-based approach named EvoPath this study. features reward mechanism based entity heterogeneity, facilitating an...
Nasopharyngeal Carcinoma (NPC) is one of the most common malignant tumors in China. However, cancer's region subtle, variability and irregular. In traditional diagnostic way, clinicians' diagnosis relies on manual delineations which are time consuming require rich prior experience. Recently, deep learning architecture U-Net Dual Path Network (DPN) apply well biomedical segmentation nature scene respectively. cannot extract abundance texture information from data DPN utilize shallow layer...
As more and cloud services are exposed to DDoS attacks, attack detect has become a new challenging task because large packet traces captured on fast links could not be easily handled single server with limited computing memory resources. In this paper, we propose Hadoop based model identify abnormal packets compute the statistics according number of packets. The novelties that:(1) by harnessing HBASE, an improved bloom filter mapping mechanism named TCP2HC/UDP2HC implemented, (2)with...
Graph neural networks (GNNs) have attracted much attention because of their excellent performance on tasks such as node classification. However, there is inadequate understanding how and why GNNs work, especially for representation learning. This paper aims to provide a theoretical framework understand GNNs, specifically, spectral graph convolutional networks, from signal denoising perspectives. Our shows that are implicitly solving problems: convolutions work features, while attentions edge...
Recommendation has become especially crucial during the COVID-19 pandemic as a significant number of people rely on online shopping from home. Existing recommendation algorithms, designed to address issues like cold start and data sparsity, often overlook time constraints users. Specifically, users expect receive recommendations for products interest in shortest possible time. To this challenge, we propose novel collaborative filtering algorithm that leverages advantages quantum computing...