A5101416812- Multi-Criteria Decision Making
- Blockchain Technology Applications and Security
- Privacy-Preserving Technologies in Data
- Internet Traffic Analysis and Secure E-voting
- IoT and Edge/Fog Computing
- Network Security and Intrusion Detection
- Reinforcement Learning in Robotics
- Cloud Computing and Resource Management
- Traffic Prediction and Management Techniques
- Human Mobility and Location-Based Analysis
- Human Pose and Action Recognition
- Face recognition and analysis
- Cryptography and Data Security
- Digital Media Forensic Detection
- Advanced Steganography and Watermarking Techniques
- Risk and Safety Analysis
- Smart Grid Security and Resilience
- Industrial Vision Systems and Defect Detection
- Infrastructure Maintenance and Monitoring
- Optimization and Mathematical Programming
- Advanced Sensor and Control Systems
- Aluminum Alloy Microstructure Properties
- Fire Detection and Safety Systems
- Mobile Crowdsensing and Crowdsourcing
- High-Voltage Power Transmission Systems
Qilu University of Technology
2019-2025
Shandong Academy of Sciences
2019-2025
Shandong University
2022-2025
Sun Yat-sen University
2024
Nanjing University of Posts and Telecommunications
2022
Shandong University of Finance and Economics
2013-2022
National Supercomputing Center in Wuxi
2019-2022
Beijing Academy of Agricultural and Forestry Sciences
2017-2018
National Engineering Research Center for Information Technology in Agriculture
2017-2018
Jiangxi University of Science and Technology
2016
Message-passing Graph Neural Networks (GNNs) are often criticized for their limited expressiveness, issues like over-smoothing and over-squashing, challenges in capturing long-range dependencies, while Transformers (GTs) considered superior due to global attention mechanisms. Literature frequently suggests that GTs outperform GNNs, particularly graph-level tasks such as graph classification regression. In this study, we explore the untapped potential of GNNs through an enhanced framework,...
The rapid advancement of the Internet Things (IoT) and mobile devices has made location-based services (LBSs) increasingly prevalent, significantly improving daily convenience work efficiency. However, this widespread usage raised growing concerns about privacy security, particularly during data outsourcing to cloud servers, where users’ location information related are susceptible breaches by malicious actors or attackers. Traditional privacy-preserving spatial keyword schemes often employ...
With the widespread application of collaborative learning (CL) technology in mobile-crowdsourcing-related scenarios, special attention should be paid to privacy disclosure problem therein. Many pioneer noise-perturbation-based methods, particularly differentially private ones, provide only homogeneous protection, which is insufficient for heterogeneous protection requirements many practical CL cases. In this article, we propose a privacy-aware mechanism that uses appropriate Gaussian noises...
As a critical mission of intelligent transportation systems, urban flow prediction (UFP) benefits in many city services including trip planning, congestion control, and public safety. Despite the achievements previous studies, limited efforts have been observed on simultaneous investigation heterogeneity both space time aspects. That is, regional correlations would be variable at different timestamps. In this paper, we propose spatio-temporal learning framework with mask contrast...
Distributed classification learning (DCL) is a promising solution to establish Internet of Things-based smart applications, especially due its strong ability in dealing with large-scale and high-concurrency data. However, the performance DCL may be seriously affected by label flipping attack (LFA). Regarding LFA-resilient problem, most existing works are built more centralized settings. The work addressing secure issue makes an assumption that rates symmetric available for scheme design. In...
By violating semantic constraints that the control process impose, attack leads Industry Control Systems (ICS) into an undesirable state or critical state. The spread of has caused huge economic losses and casualties to infrastructure. Therefore, detecting is referred urgent task. However, few existing techniques can achieve satisfactory effects in ICS, due high requirements complete state-based behavior features description, joint detection on multivariate type variables, validity field...
Predicting the sentiment polarity of aspect terms in sentences is goal Aspect-Based Sentiment Analysis(ABSA) task. Graph Convolutional Network(GCN) used majority ABSA task due to its ability effectively capture dependencies among words or entities within sentences. However, it may not work as expected when some have no obvious syntactic structure. To alleviate this issue, we propose a Context-guided and Syntactic Augmented Dual Network(CSADGCN) model for Specifically, context-guided...
Abstract The complex q-rung orthopair fuzzy (CQ-ROF) set can describe the uncertain information. In this manuscript, we develop Yager operational laws based on CQ-ROF information and t-norm t-conorm. Furthermore, in aggregating values, power, averaging, geometric aggregation operators have played a very essential critical role environment of set. Inspired from discussed operators, propose power averaging (CQ-ROFPYA), ordered (CQ-ROFPYOA), (CQ-ROFPYG), (CQ-ROFPYOG) operators. These are...
This paper explores a novel task ""Dexterous Grasp as You Say"" (DexGYS), enabling robots to perform dexterous grasping based on human commands expressed in natural language. However, the development of this field is hindered by lack datasets with guidance; thus, we propose language-guided grasp dataset, named DexGYSNet, offering high-quality annotations along flexible and fine-grained language guidance. Our dataset construction cost-efficient, carefully-design hand-object interaction...