Robust Anomaly Detection for Time-series Data

TL;DR

This paper introduces RADTD, a robust anomaly detection method for time-series data that combines negative selection, recurrence plots, and an autoencoder to improve accuracy and robustness across various datasets and real-world scenarios.

Contribution

The paper presents a novel hybrid approach, RADTD, which automatically learns dynamical features and enhances anomaly detection robustness with low label dependency.

Findings

RADTD outperforms existing methods in benchmark datasets.

RADTD achieves high accuracy in tunneling accident detection.

Experiments confirm RADTD's robustness and effectiveness.

Abstract

Time-series anomaly detection plays a vital role in monitoring complex operation conditions. However, the detection accuracy of existing approaches is heavily influenced by pattern distribution, existence of multiple normal patterns, dynamical features representation, and parameter settings. For the purpose of improving the robustness and guaranteeing the accuracy, this research combined the strengths of negative selection, unthresholded recurrence plots, and an extreme learning machine autoencoder and then proposed robust anomaly detection for time-series data (RADTD), which can automatically learn dynamical features in time series and recognize anomalies with low label dependency and high robustness. Yahoo benchmark datasets and three tunneling engineering simulation experiments were used to evaluate the performance of RADTD. The experiments showed that in benchmark datasets RADTD possessed higher accuracy and robustness than recurrence qualification analysis and extreme learning machine autoencoder, respectively, and that RADTD accurately detected the occurrence of tunneling settlement accidents, indicating its remarkable performance in accuracy and robustness.