A5101893742- Sensor Technology and Measurement Systems
- Caching and Content Delivery
- Machine Learning and Data Classification
- Blockchain Technology Applications and Security
- Imbalanced Data Classification Techniques
- Manufacturing Process and Optimization
- Age of Information Optimization
- Network Security and Intrusion Detection
- Advanced Malware Detection Techniques
- Advanced Measurement and Detection Methods
- Higher Education and Teaching Methods
- Vehicular Ad Hoc Networks (VANETs)
- Recommender Systems and Techniques
- Advanced Sensor Technologies Research
- Opportunistic and Delay-Tolerant Networks
- Advanced Computational Techniques and Applications
- Geological Modeling and Analysis
- Privacy-Preserving Technologies in Data
- Advanced Steganography and Watermarking Techniques
- EFL/ESL Teaching and Learning
- Smart Grid Security and Resilience
- Gaze Tracking and Assistive Technology
- Transport Systems and Technology
- Peer-to-Peer Network Technologies
- Educational Technology and Assessment
Guangxi Normal University
2020-2024
North China University of Science and Technology
2011-2020
Tianjin Research Institute of Electric Science (China)
2020
Hebei University
2011
Zhejiang University
2003
Most Intrusion Detection System(IDS) used in Supervisory Control and Data Acquisition (SCADA) systems now are focused on the cyber field but ignored process states physical of plants. Attacks aiming at protocol traffics can be detected attacks processes difficult to such as Man In The Middle (MITM) Replay attacks. We propose a scheme both way detect above Validation is malicious behaviors prevent components from being damaged which caused by MITM, Replay, Zero-day Nonparallel hyperplane...
With the proliferation of Internet, particularly rise social media, digital images have gradually become an important part life, and trading platforms emerged for buying selling images. However, traditional image service providers may disclose users' private information profit. Additionally, many disregard fairness a transaction issue copyright protection after is sold. This neglect harms interests users affects their enthusiasm trading. A secure way to safely transact needed. We proposed...
To achieve the tamper-proof, reliability and traceability of transactions in a trustless environment, blockchain requires each peer node to store whole global ledger. However, as keep increasing over time, storage cost increases. In addition, many schemes have been proposed boost rapid which will even lead grow explosively. The problem is becoming one challenge since overhead increase rapidly. Reducing participant very urgent worthy. this paper, we present GCBlock: grouping overlay network...
Currently, most studies on content caching strategies for vehicular networks rely the Zipf distribution model of popularity. This approach, however, often fails to accommodate time-varying nature popularity and traffic. Although some have begun considering popularity, they overlook implications vehicle traffic, which significantly influences allocation policies could potentially reduce edge server rental costs service providers. Addressing this gap, our study takes both traffic data into...
Graph neural networks based on message-passing mechanisms have achieved advanced results in graph classification tasks. However, their generalization performance degrades when noisy labels are present the training data. Most existing labeling approaches focus visual domain or node tasks and analyze impact of only from a utility perspective. Unlike work, this paper, we measure effects noise data privacy model perspectives. We find that degrade model's enhance ability membership inference...
This paper studies the control of defective rate in electronic industry chain, designs a small sample binomial distribution sampling detection scheme to verify supplier 's statement and optimize cost. Based on rate, linear programming dynamic / decision tree model are used multi-stage production process, including parts inspection, finished product inspection unqualified treatment, so as maximize profit enterprise. A phased optimization strategy is proposed for complex multi-process...
Abstract Truck scale is an important weighing instrument. The truck parking cheating method one of the scales and can lead to large economic losses enterprise. A new detection based on voltage waveform analysis brought out in this paper. According output signal transducer, if turning point number different with axles, exists. Based principle, system designed. instrument using 8031 as MCU be transmitted control computer. Experimental data show that on-time detects method.
Knowledge graph (KG) as auxiliary information can solve the cold-start and data sparsity problems of recommender systems.However, most existing KG-based recommendation methods focus on how to effectively encode items with that users have interacted into entities propagate them explicitly, but neglect relation-level context-level modeling collaborative signals.Therefore, it is inevitable incorporate some unrelated while utilizing a propagation strategy, which may weaken part performance.To...
Abstract In this paper, the feasibility of fault diagnosis method based on vibration signal in GIS is studied through experiments correlation between discharge and propagation characteristics GIS. The concept pulse interval frequency put forward. According to experimental data, it concluded that there a strong signal. At same time, has regular when passing basin insulator, cavity T-shaped structure. above two points strongly support test can be used for