A5066653432- Network Security and Intrusion Detection
- Remote Sensing and LiDAR Applications
- Computer Graphics and Visualization Techniques
- Internet Traffic Analysis and Secure E-voting
- Advanced Algorithms and Applications
- Advanced Sensor and Control Systems
- Anomaly Detection Techniques and Applications
- Advanced Vision and Imaging
Anhui University of Science and Technology
2025
Zhongyuan University of Technology
2023
This study addresses the prevalent challenges of inefficiency and suboptimal quality in indoor 3D scene generation rendering by proposing a parameter-tuning strategy for Gaussian Splatting (3DGS). Through systematic quantitative analysis various performance indicators under differing resolution conditions, threshold settings average magnitude spatial position gradients, adjustments to scaling learning rate, optimal parameter configuration 3DGS model, specifically tailored modeling scenarios,...
In this paper, support vector machine (SVM) is used to predict hourly building cooling load of commercial building. The prediction model based on SVM has been presented, and applied a in China. simulation results show that the method can achieve better accuracy generalization than traditional back-propagation (BP) neural network model, it effective for prediction.
Anomaly detection for network attacks has always been a very important part of intrusion detection. The current research focus is anomaly based on deep learning, which two main problems. One the lack large amount labeled data in model training, and other difficult to detect unknown or variant attacks. To solve above problems, an unsupervised constructed this paper. automatic encoder used learn normal traffic characteristics abnormal traffic. Meanwhile, time correlation features hierarchical...
In view of the privacy leakage problem location based services (LBS), academic community has proposed various protection mechanism(LPPM), and effect LPPM needs a means to measure. At present, measurement mechanisms mainly focus on metric or query privacy, for specific LPPM, which is not universal. this paper, generic framework proposed, in which, mobile user, adversary are formalized, performance criterion used as metric, considers degree service utility. This both meanwhile, it can be...
Network attack identification and analysis has been a difficult problem in cyberspace security research, at present, the research on network based deep learning models achieved remarkable results. However, most of only use temporal correlation traffic data to analyze, detect warn data, do not make full thus ignoring topological information generated by space. To address above problems, this paper is attempt graph convolutional neural networks solve analysis, designs model networks, which...