BSSAD: Towards A Novel Bayesian State-Space Approach for Anomaly Detection in Multivariate Time Series

TL;DR

This paper introduces BSSAD, a novel Bayesian state-space approach combining neural networks and Bayesian filtering techniques for high-accuracy anomaly detection in multivariate time series data, adaptable through modular design.

Contribution

The paper presents a new hybrid Bayesian neural network framework for anomaly detection, integrating state-space models with neural networks for improved accuracy and flexibility.

Findings

Achieved F1-score > 0.95 on five datasets

Demonstrated superior performance over baseline methods

Proposed MCC metric for better accuracy assessment

Abstract

Detecting anomalies in multivariate time series(MTS) data plays an important role in many domains. The abnormal values could indicate events, medical abnormalities,cyber-attacks, or faulty devices which if left undetected could lead to significant loss of resources, capital, or human lives. In this paper, we propose a novel and innovative approach to anomaly detection called Bayesian State-Space Anomaly Detection(BSSAD). The BSSAD consists of two modules: the neural network module and the Bayesian state-space module. The design of our approach combines the strength of Bayesian state-space algorithms in predicting the next state and the effectiveness of recurrent neural networks and autoencoders in understanding the relationship between the data to achieve high accuracy in detecting anomalies. The modular design of our approach allows flexibility in implementation with the option of changing the parameters of the Bayesian state-space models or swap-ping neural network algorithms to achieve different levels of performance. In particular, we focus on using Bayesian state-space models of particle filters and ensemble Kalman filters. We conducted extensive experiments on five different datasets. The experimental results show the superior performance of our model over baselines, achieving an F1-score greater than 0.95. In addition, we also propose using a metric called MatthewCorrelation Coefficient (MCC) to obtain more comprehensive information about the accuracy of anomaly detection.