An Evaluation of Anomaly Detection and Diagnosis in Multivariate Time Series

Astha Garg, Wenyu Zhang, Jules Samaran, Savitha Ramasamy, Chuan-Sheng Foo

IEEE Transactions on Neural Networks and Learning Systems · 2021 · 249 citations · 43 references

DOIFull text

Open access

Concepts

TL;DR

Multivariate time‑series anomaly detection has many proposed methods, yet systematic comparisons on common datasets and metrics are lacking, and detecting anomalous events is more critical than individual time‑points. The study aims to systematically evaluate unsupervised and semi‑supervised deep‑learning anomaly detection methods on cyber‑physical system data and introduce a composite F‑score metric for event‑level evaluation. The authors evaluate 10 deep‑learning models combined with 4 independent scoring functions on cyber‑physical multivariate time‑series data, using a grid search to compare variants against state‑of‑the‑art methods. Experiments show that existing metrics fail to capture event‑level performance, dynamic scoring functions outperform static ones, and a channel‑wise Univariate Fully‑Connected Auto‑Encoder with dynamic Gaussian scoring outperforms state‑of‑the‑art algorithms.

Abstract

Several techniques for multivariate time series anomaly detection have been proposed recently, but a systematic comparison on a common set of datasets and metrics is lacking. This paper presents a systematic and comprehensive evaluation of unsupervised and semi-supervised deep-learning based methods for anomaly detection and diagnosis on multivariate time series data from cyberphysical systems. Unlike previous works, we vary the model and post-processing of model errors, i.e. the scoring functions independently of each other, through a grid of 10 models and 4 scoring functions, comparing these variants to state of the art methods. In time-series anomaly detection, detecting anomalous events is more important than detecting individual anomalous time-points. Through experiments, we find that the existing evaluation metrics either do not take events into account, or cannot distinguish between a good detector and trivial detectors, such as a random or an all-positive detector. We propose a new metric to overcome these drawbacks, namely, the composite F-score ($Fc_1$), for evaluating time-series anomaly detection. Our study highlights that dynamic scoring functions work much better than static ones for multivariate time series anomaly detection, and the choice of scoring functions often matters more than the choice of the underlying model. We also find that a simple, channel-wise model - the Univariate Fully-Connected Auto-Encoder, with the dynamic Gaussian scoring function emerges as a winning candidate for both anomaly detection and diagnosis, beating state of the art algorithms.

References

43