Online and Robust Anomaly Detection using Recurrent Neural Network
In many real-world applications, data is dynamic and noisy. In such a situation, anomaly detection should be performed with an online and robust model against noise. In recent years, recurrent neural networks have been used on data sequences and have achieved good performance in this field. The exis...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | fas |
| Published: |
Semnan University
2023-10-01
|
| Series: | مجله مدل سازی در مهندسی |
| Subjects: | |
| Online Access: | https://modelling.semnan.ac.ir/article_7765_6b6aa42ac324e31de9da39ed54bf3b60.pdf |
| Summary: | In many real-world applications, data is dynamic and noisy. In such a situation, anomaly detection should be performed with an online and robust model against noise. In recent years, recurrent neural networks have been used on data sequences and have achieved good performance in this field. The existing methods do not have sufficient robustness against noise. This paper presents a method for anomaly detection in dynamic graph data using recurrent neural networks that are robust against noise and have sufficient adaptivity to changes in the data pattern. The proposed robust recurrent neural network extracts and introduces anomalies for the purpose of noise management. At the same time, it learns the original patterns in an online manner and is adapted to the changes. To evaluate the proposed method, some experiments are presented that measure its ability in anomaly detection in addition to the learning and adaptation ability in comparison with the existing methods. The results have confirmed the superiority of the proposed method. |
|---|---|
| ISSN: | 2008-4854 2783-2538 |