Effective Abnormal Activity Detection on Multivariate Time Series Healthcare Data

TL;DR

This paper introduces Rs-AD, a residual-based method for detecting anomalies in multivariate healthcare time series data, effectively capturing temporal and inter-variable dependencies to improve accuracy.

Contribution

The paper presents a novel residual-based anomaly detection approach tailored for multivariate time series in healthcare, enhancing representation learning for better detection performance.

Findings

Achieved an F1 score of 0.839 on real-world gait data

Effectively captures temporal dependencies and inter-variable relationships

Improves anomaly detection accuracy in healthcare MTS data

Abstract

Multivariate time series (MTS) data collected from multiple sensors provide the potential for accurate abnormal activity detection in smart healthcare scenarios. However, anomalies exhibit diverse patterns and become unnoticeable in MTS data. Consequently, achieving accurate anomaly detection is challenging since we have to capture both temporal dependencies of time series and inter-relationships among variables. To address this problem, we propose a Residual-based Anomaly Detection approach, Rs-AD, for effective representation learning and abnormal activity detection. We evaluate our scheme on a real-world gait dataset and the experimental results demonstrate an F1 score of 0.839.