A5100775924- Complex Network Analysis Techniques
- Advanced Graph Neural Networks
- Opinion Dynamics and Social Influence
- Imbalanced Data Classification Techniques
- Text and Document Classification Technologies
- Bioinformatics and Genomic Networks
- Advanced Computing and Algorithms
- Anomaly Detection Techniques and Applications
- Network Security and Intrusion Detection
- Internet Traffic Analysis and Secure E-voting
- Software-Defined Networks and 5G
- Neural Networks Stability and Synchronization
- Advanced Authentication Protocols Security
- Advanced Clustering Algorithms Research
- Infrastructure Resilience and Vulnerability Analysis
- Network Time Synchronization Technologies
- Advanced Memory and Neural Computing
- Electricity Theft Detection Techniques
- Spam and Phishing Detection
- Opportunistic and Delay-Tolerant Networks
- Human Mobility and Location-Based Analysis
- Advanced Algorithms and Applications
- Mental Health Research Topics
- Sustainability and Ecological Systems Analysis
- Data-Driven Disease Surveillance
Shanghai Dianji University
2022-2025
Xinjiang Agricultural University
2019-2025
PLA Information Engineering University
2013-2024
System Equipment (China)
2016-2024
Northeastern University
2021-2023
Tsinghua University
2023
Health and Family Planning Commission of Sichuan Province
2022
Chengdu University of Technology
2022
Shenyang University of Technology
2022
State Key Laboratory of Synthetical Automation for Process Industries
2021
Along with the rapid evolution of mobile communication technologies, such as 5G, there has been a significant increase in telecom fraud, which severely dissipates individual fortune and social wealth. In recent years, graph mining techniques are gradually becoming mainstream solution for detecting fraud. However, imbalance problem, caused by Pareto principle, brings severe challenges to data mining. This emerging complex issue received limited attention prior research. this paper, we propose...
In recent years, the increasing prevalence of mobile social network fraud has led to significant distress and depletion personal wealth, resulting in considerable economic harm. Graph neural networks (GNNs) have emerged as a popular approach tackle this issue. However, challenge graph imbalance, which can greatly impede effectiveness GNN-based detection methods, received little attention prior research. Thus, we are going present novel cost-sensitive (CSGNN) article. Initially, reinforcement...
This paper discusses the optimal synchronisation problem of multi-agent systems with unknown system dynamics, where each agent is subject to both input saturation and external disturbances. A novel data-driven control approach developed in this based on low-gain technique, output regulation, differential game theory, adaptive dynamic programming (ADP). Unlike existing approaches problem, our method eliminates need for an initially admissible stabilising policy, proposed distributed law...
With the rapid evolution of mobile communication networks, number subscribers and their practices is increasing dramatically worldwide. However, fraudsters are also sniffing out benefits. Detecting from massive volume call detail records (CDR) in networks has become an important yet challenging topic. Fortunately, Graph neural network (GNN) brings new possibilities for telecom fraud detection. presence graph imbalance GNN oversmoothing problems makes fraudster detection unsatisfactory. To...
This paper proposes a systematic analysis method for 5G Non-Access Stratum Signalling security based on formal analysis, which has identified 10 new protocol vulnerabilities, and an improved PKI mechanism targeted at eliminating these vulnerabilities. Firstly, the system, state transition properties were abstracted from 3GPP specifications. To mimic attacker's behavior, Dolev-Yao adversary model was constructed in by empowering it with NAS signalling testing knowledge reasonable capabilities...
Telecom fraud detection is of great significance in online social networks. Yet the massive, redundant, incomplete, and uncertain network information makes it a challenging task to handle. Hence, this paper mainly uses correlation attributes by entropy function optimize data quality then solves problem telecommunication with incomplete information. First, filter out redundancy noise, we propose an attribute reduction algorithm based on max-correlation max-independence rate (MCIR) improve...
Abstract Pairwise dependencies in interdependent networks exist not only between ordinary nodes but also groups of nodes, where cooperate and form to increase their robustness risks each group can be considered a ‘supernode’. The interdependencies supernodes are universal always complete homogeneous. In this paper, we study the with heterogeneous weak interdependency strength under targeted attack, could vary different supernodes. We identify several types percolation transitions, namely...
Recently, a number of similarity-based methods have been proposed for link prediction complex networks. Among these indices, the resource-allocation-based perform very well considering amount resources in information transmission process between nodes. However, they ignore channels and their capacity two endpoints. Motivated by Cannikin Law, definition is to quantify capability any Then, based on capacity, potential (PIC) index prediction. Empirical study 15 datasets has shown that PIC we...
Many link prediction methods have been proposed for predicting the likelihood that a exists between two nodes in complex networks. Among these methods, similarity indices are receiving close attention. Most similarity-based assume contribution of links with different topological structures is same calculations. This paper proposes local weighted method, which weights strength connection each pair nodes. Based on six extended from unweighted (including Common Neighbor (CN), Adamic-Adar (AA),...
Cross-social network user identification refers to finding users with the same identity in multiple social networks, which is widely used cross-network recommendation, link prediction, personality and data mining. At present, traditional method obtain structure information from neighboring nodes through graph convolution, embed networks into low-dimensional vector space. However, as depth increases, effect of model will decrease. Therefore, order better embedding representation, a...
Blast waves with a large amount of energy, from the use explosive weapons, is major cause traumatic brain injury in armed and security forces. The monitoring blast required for defence civil applications. utilization wireless sensing technology to monitor has shown great advantages, such as easy deployment flexibility. However, due drifting embedded clock frequency, establishment common timescale among distributed sensors been challenge, which may lead network failing estimate precise...
The development of graph neural networks (GCN) makes it possible to learn structural features from evolving complex networks. Even though a wide range realistic are directed ones, few existing works investigated the properties and temporal In this paper, we address problem link prediction in propose deep learning model based on GCN self-attention mechanism, namely TSAM. proposed adopts an autoencoder architecture, which utilizes attentional layers capture feature neighborhood nodes, as well...
This paper discusses the output-feedback-based model-free optimal output tracking control problem of discrete-time systems with completely unknown system models under mild assumptions. The only information that allows utilisation is and reference output. To overcome these challenges, aims to solve a regulation for achieving control; solving an equivalent linear quadratic (LQR) constrained static optimisation problem. state reconstruction first given represent in terms input sequences. A...