A5111069554- Anomaly Detection Techniques and Applications
- Network Security and Intrusion Detection
- Machine Learning and Data Classification
- Software Reliability and Analysis Research
- Software Testing and Debugging Techniques
- Statistical and numerical algorithms
- Engineering and Test Systems
- Time Series Analysis and Forecasting
Beihang University
2023-2025
In the field of ensemble learning, bagging and stacking are two widely used strategies. Bagging enhances model robustness through repeated sampling weighted averaging homogeneous classifiers, while improves classification performance by integrating multiple models using meta-learning strategies, taking advantage diversity heterogeneous classifiers. However, fixed weight distribution strategy in traditional methods often has limitations when handling complex or imbalanced datasets. This paper...
Continuous integration (CI), a crucial technology for accelerating software delivery, employs prioritization methods to optimize testing efficiency. Reinforcement-learning-based techniques of test cases can dynamically adjust the strategy based on feedback. However, existing reinforcement learning models either use feature information from individual or complete all as input. The model’s input is fixed and does not vary characteristics case set. This leads inability handle various ranking...
In the field of ensemble learning, bagging and stacking are two widely used strategies. Bagging enhances model robustness through repeated sampling weighted averaging homogeneous classifiers, while improves classification performance by integrating multiple models using meta-learning strategies, taking advantage diversity heterogeneous classifiers. However, fixed weight distribution strategy in traditional methods often has limitations when handling complex or imbalanced datasets. This paper...
QAR (Quick Access Recorder) data contains numerous quality flaws such as anomalies and missing data. It will cause significant problems for subsequent mining, model training, analysis if it is not detected. To address these issues, this paper investigates QAR-specific anomaly detection (AD) algorithms before presenting a three-stage AD algorithm based on spatial-temporal correlation, which includes single parameter AD, correlation analysis, multi AD. The SST (Singular Spectrum...