Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Detecting Anomalies in Time Series Using Kernel Density Approaches

Journal Article · · IEEE Access
 [1];  [2];  [2];  [3];  [1]
  1. Zurich University of Applied Sciences, Winterthur (Switzerland)
  2. Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
  3. Texas A & M University, Commerce, TX (United States)
+ Show Author Affiliations
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 probability distribution for normal events post-reconstruction. This non-parametric density estimation technique offers a nuanced understanding of anomaly detection, differentiating it from prevalent threshold-based mechanisms in existing methodologies. In post-training, events are encoded, decoded, and evaluated against the estimated density, providing a comprehensive notion of normality. In addition, we propose a data augmentation strategy involving variational autoencoder-generated events and a smoothing step for enhanced model robustness. The significance of our autoencoder-based approach is evident in its capacity to learn normal representation without prior anomaly knowledge. Through the KDE step on reconstruction errors, our method addresses the versatility of anomalies, departing from assumptions tied to larger reconstruction errors for anomalous events. Our proposed likelihood measure then distinguishes normal from anomalous events, providing a concise yet comprehensive anomaly detection solution. The extensive experimental results support the feasibility of our proposed method, yielding significantly improved classification performance by nearly 10% on the UCR benchmark data.
Research Organization:
Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
Sponsoring Organization:
National Energy Research Scientific Computing Center (NERSC); USDOE; USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)
Grant/Contract Number:
AC02-05CH11231
OSTI ID:
2316100
Alternate ID(s):
OSTI ID: 2319263
OSTI ID: 2587233
Journal Information:
IEEE Access, Journal Name: IEEE Access Journal Issue: 99 Vol. 12; ISSN 2169-3536
Publisher:
Institute of Electrical and Electronics Engineers (IEEE)Copyright Statement
Country of Publication:
United States
Language:
English

References (35)

Flow-based intrusion detection on software-defined networks: a multivariate time series anomaly detection approach journal March 2023
Early lameness detection in dairy cattle based on wearable gait analysis using semi-supervised LSTM-Autoencoder journal October 2023
Smoothing and Differentiation of Data by Simplified Least Squares Procedures. journal July 1964
On optimal and data-based histograms journal January 1979
Deep Learning for Anomaly Detection in Time-Series Data: Review, Analysis, and Guidelines journal January 2021
Activities Recognition, Anomaly Detection and Next Activity Prediction Based on Neural Networks in Smart Homes journal January 2022
Unsupervised Anomaly Detection in Time Series Using LSTM-Based Autoencoders conference December 2019
TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks conference December 2020
Botnet Detection Using Recurrent Variational Autoencoder conference December 2020
Malware classification with LSTM and GRU language models and a character-level CNN conference March 2017
MERLIN: Parameter-Free Discovery of Arbitrary Length Anomalies in Massive Time Series Archives conference November 2020
Data augmentation for improving deep learning in image classification problem conference May 2018
LSTM and GRU Neural Network Performance Comparison Study: Taking Yelp Review Dataset as an Example conference June 2020
Anomaly Detection for IoT Time-Series Data: A Survey journal July 2020
A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-Based Variational Autoencoder journal July 2018
Unsupervised Online Anomaly Detection on Multivariate Sensing Time Series Data for Smart Manufacturing conference November 2019
Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progress journal January 2021
Detecting Regions of Maximal Divergence for Spatio-Temporal Anomaly Detection journal May 2019
Anomaly Detection Based on Convolutional Recurrent Autoencoder for IoT Time Series journal January 2022
AER: Auto-Encoder with Regression for Time Series Anomaly Detection conference December 2022
Anomaly Detection Using Autoencoders with Nonlinear Dimensionality Reduction conference January 2014
Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications conference January 2018
Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding
  • Hundman, Kyle; Constantinou, Valentino; Laporte, Christopher
  • Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining https://doi.org/10.1145/3219819.3219845
conference July 2018
Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network conference July 2019
Deep Learning for Anomaly Detection: A Review journal March 2022
A Review on Outlier/Anomaly Detection in Time Series Data journal April 2021
A survey on Image Data Augmentation for Deep Learning journal July 2019
Big Data architecture for intelligent maintenance: a focus on query processing and machine learning algorithms journal August 2020
On Estimation of a Probability Density Function and Mode journal September 1962
An empirical survey of data augmentation for time series classification with neural networks journal July 2021
TranAD journal February 2022
Anomaly detection in time series journal May 2022
Is It Worth It? Comparing Six Deep and Classical Methods for Unsupervised Anomaly Detection in Time Series journal January 2023
A Comparative Study of Time Series Anomaly Detection Models for Industrial Control Systems journal January 2023
Auto-Encoding Variational Bayes preprint January 2013

Similar Records

Online-compatible unsupervised nonresonant anomaly detection
Journal Article · Mon Mar 07 19:00:00 EST 2022 · Physical Review. D. · OSTI ID:1894630

Related Subjects