A5047768530- Internet Traffic Analysis and Secure E-voting
- Network Security and Intrusion Detection
- Digital and Cyber Forensics
- Fuzzy Logic and Control Systems
- Emotion and Mood Recognition
- Non-Invasive Vital Sign Monitoring
- Heart Rate Variability and Autonomic Control
- Neural Networks and Applications
- Anomaly Detection Techniques and Applications
- Face and Expression Recognition
Beijing University of Posts and Telecommunications
2024
University of Jinan
2023
Changsha University of Science and Technology
2020-2023
Abstract Traffic classification is widely used in network security and management. Early studies have mainly focused on mapping traffic to different unencrypted applications, but little research has been done of encrypted especially the underlying applications. To address above issues, this paper proposes a encryption model that combines attention mechanisms spatiotemporal features. The firstly uses long short-term memory (LSTM) method analyze continuous flows find temporal correlation...
Aiming at the problems of excessive dependence on manual work, low detection accuracy and poor real-time performance current probe flow anomaly in power system network security detection, a method for calculating information entropy random forest classificat ion is proposed. Firstly, stream data are captured aggregated to extract metadata. Secondly, by Pearson correlation coefficient maximum mutual coefficient, feature selection metadata carried out. Finally, stochastic algorithm combined...
Abstract Traffic classification has been widely used in network security and management. Previous research focused on mapping traffic to different non-encrypted applications, However, there are few researches of encryption especially the underlying application. In order solve above problems, this paper proposes a encrypted model which combines attention mechanism with spatial temporal characteristics. The first uses LSTM (Long ShortTerm Memory) analyze time series continuous flows find out...
At present, research mainly uses single modal and multimodal physiological signals to identify human psychological states, but these methods generally have the drawbacks of low evaluation accuracy, poor applicability, weak effectiveness. To address above shortcomings, this article proposes a stress assessment method based on privileged information learning paradigm framework. This SVM+ algorithm under framework predict from WESAD dataset compares its performance with other algorithms....