About this document

Transformer Models for Anomaly Detection by admiral2188 is a document available to read on EtoBox.

This paper investigates the use of Transformer-based models, specifically Time-Series Transformer (TST) and Temporal Fusion Transformer (TFT), for anomaly detection in streaming data, demonstrating their superiority over traditional LSTM Autoencoders. The study shows that TFT achieves an F1-score of 0.92 and TST an F1-score of 0.88, highlighting their efficiency and effectiveness in real-time applications. The findings suggest that Transformer models are a robust solution for large-scale anomaly detection,

Author

admiral2188

Language

EN