A5091166192- Advanced Graph Neural Networks
- Recommender Systems and Techniques
- Privacy-Preserving Technologies in Data
- Caching and Content Delivery
- Topic Modeling
- Internet Traffic Analysis and Secure E-voting
- Network Security and Intrusion Detection
- Complex Network Analysis Techniques
- Advanced Multi-Objective Optimization Algorithms
- Rough Sets and Fuzzy Logic
- Graph Theory and Algorithms
- Advanced Malware Detection Techniques
- Text and Document Classification Technologies
- Blockchain Technology Applications and Security
- IoT and Edge/Fog Computing
- Spam and Phishing Detection
- Anomaly Detection Techniques and Applications
- Metaheuristic Optimization Algorithms Research
- Face and Expression Recognition
- Access Control and Trust
- Kidney Stones and Urolithiasis Treatments
- Robotics and Sensor-Based Localization
- Remote Sensing and LiDAR Applications
- Hydrological Forecasting Using AI
- Cryptography and Data Security
Taiyuan University of Science and Technology
2020-2025
East China Jiaotong University
2021-2024
University of South China
2023-2024
Tencent (China)
2022-2024
University of Science and Technology of China
2022
Anhui Provincial Hospital
2022
Institute of Information Engineering
2020
Chinese Academy of Sciences
2020
University of Chinese Academy of Sciences
2019
Baogang Group (China)
2014
Social trust assessment that characterizes a pairwise trustworthiness relationship can spur diversified applications. Extensive efforts have been put in exploration, but mainly focusing on applying graph convolutional network to establish social evaluation model, overlooking user feature factors related context-aware information prediction. In this article, we aim design new framework GATrust which integrates multi-aspect properties of users, including context-specific information,...
The rapid progress of artificial intelligence expands its wide applicability in Internet Things (IoT). Meanwhile, data insufficient and source privacy are key supply chain challenges facing IoT especially the healthcare industry. To address this problem IoT, article, we propose a skin cancer detection model based on federated learning integrated with deep generation model. First, employ dual generative adversarial networks to data. In addition, improve quality generated images, synchronously...
With the development of cloud computing technology (CCT), processing network traffic data becomes particularly important. However, existing intrusion detection systems (IDS) are not efficient enough in analyzing for anomaly detection. Therefore, this paper proposes a new model The can simultaneously optimize number features (NF), accuracy, recall, false alarm rate (FAR) and precision. In order to better solve model, an integrating dominance algorithm (MaOEA-ABC) with adaptive selection...
ABSTRACT In practical engineering problems, uncertainties due to prediction errors and fluctuations in equipment efficiency often lead constrained many‐objective optimization problem with interval parameters (ICMaOPs). These problems pose significant challenges for evolutionary algorithms, particularly balancing solution convergence, diversity, feasibility, uncertainty. To address these challenges, a personalized indicator‐based algorithm (PI‐ICMaOEA) specifically designed ICMaOPs is...
Edit-based approaches for Grammatical Error Correction (GEC) have attracted volume attention due to their outstanding explanations of the correction process and rapid inference. Through exploring characteristics generalized specific knowledge learning GEC, we discover that efficiently training GEC systems with satisfactory generalization capacity prefers more rather than knowledge. Current gradient-based methods systems, however, usually prioritize minimizing loss over loss. This paper...
With the rise of mobile Internet and AI, social media integrating short messages, images, videos has developed rapidly. As a guarantee for stable operation media, information security, especially graph anomaly detection (GAD), become hot issue inspired by extensive attention researchers. Most GAD methods are mainly limited to enhancing homophily or considering heterophilic connections. Nevertheless, due deceptive nature connections among anomalies, discriminative anomalies can be eliminated....
The recommender system is of great significance to alleviate information overload. rise online social networks leads a promising direction—social recommendation. By injecting the interaction influence among users, recommendation performance has been further improved. Successful as they are, we argue that most methods are still not sufficient make full use network information. Existing solutions typically either considered only local neighbors or treat neighbors' equally, even both. However,...
Recently, graph neural network (GNN) approaches have received huge interests in recommendation tasks due to their ability of learning more effective user and item representations. However, existing GNN-based models cannot support real-time where the model keeps its freshness by continuously training streaming data that users produced, leading negative impact on performance. To fully graph-enhanced large-scale scenarios, a deep system is required dynamically store as structure enable...
In online social networks, users can vote on different trust levels for each other to indicate how much they their friends. Researchers have improved ability predict relationships through a variety of methods, one which is the graph neural network (GNN) method, but also brought vulnerability GNN method into model. We propose data-poisoning attack GNN-based models based characteristics networks. used two-sample test power-law distributions discrete data avoid changes in dataset being detected...
Autism Spectrum Disorder (ASD) is one common developmental disorder with great variations in symptoms and severity, making the diagnosis of ASD a challenging task. Existing deep learning models using brain connectivity features to classify still suffer from degraded performance for multi-center data due limited feature representation ability insufficient interpretability. Given that Graph Convolutional Network (GCN) has demonstrated superiority discriminative representations networks, this...
The precise measuring of vehicle location has been a critical task in enhancing the autonomous driving terms intelligent decision making and safe transportation. Internet Vehicles ( IoV ) is an important infrastructure support driving, allowing real-time road information exchanging sharing for localizing vehicles. Global positioning System GPS widely used traditional system. unable to meet key application requirements due meter level error signal deterioration. In this article, we propose...
Summary In many‐objective optimization algorithms, it is very important to maintain significant convergence and diversity of the population. And with increasing demand in various fields, problem also becomes gradually complicated. Some existing algorithms are faced challenges such as domination resistance dimensional crisis. To solve these challenges, a algorithm based on dual criteria mixed distribution correction strategy (MaOEA‐CSMDC) proposed this paper. be specific, matching selection...