Moon: A Modality Conversion-Based Efficient Multivariate Time Series Anomaly Detection

doi:10.1109/TKDE.2025.3622154

Moon: A Modality Conversion-Based Efficient Multivariate Time Series Anomaly Detection

2025-12-09

0

PRE

AI

DOI：10.1109/TKDE.2025.3622154

Original

Original request for help

Save

Abstract

En 中文

Multivariate time series (MTS) anomaly detection identifies abnormal patterns where each timestamp contains multiple variables. Existing MTS anomaly detection methods fall into three categories: reconstruction-based, prediction-based, and classifier-based methods. However, these methods face three key challenges: (1) Unsupervised learning methods, such as reconstruction-based and prediction-based methods, rely on error thresholds, which can lead to inaccuracies; (2) Semi-supervised methods mainly model normal dataand often underuse anomaly labels, limiting detection of subtle anomalies; (3) Supervised learning methods, such as classifier-based approaches, often fail to capture local relationships, incur high computational costs, and are constrained by the scarcity of labeled data. To address these limitations, we propose <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Moon, a supervised modality conversion-based multivariate time series anomaly detection framework. <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Moon enhances the efficiency and accuracy of anomaly detection while providing detailed anomaly analysis reports. First, <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Moon introduces a novel multivariate Markov Transition Field (MV-MTF) technique to convert numeric time series data into image representations, capturing relationships across variables and timestamps. Since numeric data retains unique patterns that cannot be fully captured by image conversion alone, <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Moon employs a Multimodal-CNN to integrate numeric and image data through a feature fusion model with parameter sharing, enhancing training efficiency. Finally, a SHAP-based anomaly explainer identifies key variables contributing to anomalies, improving interpretability. Extensive experiments on six real-world MTS datasets demonstrate that <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Moon outperforms six state-of-the-art methods by up to 93% in efficiency, 4% in accuracy and, 10.8% in interpretation performance.

Keywords:

Anomaly detection

interpretable system

multivariate time series

Moon: A Modality Conversion-Based Efficient Multivariate Time Series Anomaly Detection

Abstract

Journal

Organization