A Statistical-Based Light-Weight Anomaly Detection Framework for Wireless Body Area Networks

Abstract

Abstract In healthcare scenario, the major challenge in anomaly detection for remote patient monitoring is to classify true medical conditions and false alarms. This paper proposes a light-weight anomaly detection (LWAD) framework for detecting anomalies in remote patient monitoring based on wireless body area networks. The proposed framework uses distance correlation for finding correlated (both linear and non-linear) physiological parameters. It also uses a statistical-based improvised dynamic sliding window algorithm for efficient short-range prediction of physiological parameters. Finally, the proposed LWAD framework detects anomalies using anomaly detection framework based on robust statistical techniques. The validation of LWAD framework is performed using three real time datasets with various statistical measures. The proposed LWAD framework outperforms existing methods.