Unsupervised Anomaly Detection Approach for Time-Series in Multi-Domains Using Deep Reconstruction Error

Unsupervised Anomaly Detection Approach for Time-Series in Multi-Domains Using Deep Reconstruction Error

Automatic anomaly detection for time-series is critical in a variety of real-world domains such as fraud detection, fault diagnosis, and patient monitoring. Current anomaly detection methods detect the remarkably low proportion of the actual abnormalities correctly. Furthermore, most of the datasets...

Full description

Bibliographic Details
Main Authors: Tsatsral Amarbayasgalan, Van Huy Pham, Nipon Theera-Umpon, Keun Ho Ryu
Format: Article
Language:English
Published: MDPI AG 2020-07-01
Series:Symmetry
Subjects:
anomaly detection
density-based clustering
deep autoencoder
reconstruction error
unsupervised technique
Online Access:https://www.mdpi.com/2073-8994/12/8/1251

Internet

https://www.mdpi.com/2073-8994/12/8/1251

Similar Items