| Autor: |
L.H. Nguyen, Thi Hien Nguyen, Kieu-Ha Phung, K.D. Tran, T.T.N. Le, Thu-Huong Truong, Kim Phuc Tran, Huu Du Nguyen |
| Rok vydání: |
2019 |
| Předmět: |
|
| Zdroj: |
2019 6th NAFOSTED Conference on Information and Computer Science (NICS). |
| DOI: |
10.1109/nics48868.2019.9023851 |
| Popis: |
Anomaly detection is the identification of observations that deviates from the data set's normal behavioral patterns. It is an important problem that has been researched within diverse research areas and application domains such as intrusion detection, fraud detection, fault detection, and event detection in sensor networks. Among the anomaly detection methods, control charts have been considered important and critical. In this paper, we present a new method for anomaly detection based on one-sided Synthetic control charts monitoring the ratio of two normal variables in which both the steady-state and the zero-state average run length (ARL) are investigated. The numerical results show that our proposed control charts outperform the two-sided Synthetic control chart in detecting process shifts. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
