Detecting Anomalies in Time Series Using Kernel Density Approaches

Detecting Anomalies in Time Series Using Kernel Density Approaches

This paper introduces a novel anomaly detection approach tailored for time series data with exclusive reliance on normal events during training. Our key innovation lies in the application of kernel-density estimation (KDE) to scrutinize reconstruction errors, providing an empirically derived probabi...

Full description

Bibliographic Details
Main Authors: Robin Frehner, Kesheng Wu, Alexander Sim, Jinoh Kim, Kurt Stockinger
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Time series anomaly detection
machine learning
neural networks
autoencoder
kernel density estimation
Online Access:https://ieeexplore.ieee.org/document/10453576/

Similar Items

Similar Items