Incremental Anomaly Detection with Guarantee in the Internet of Medical Things
Open Access
- 9 May 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 327-339
Abstract
The Internet of Medical Things (IoMT), aided by learning-enabled components, is becoming increasingly important in health monitoring. However, the IoMT-based system must be highly reliable since it directly interacts with the patients. One critical function for facilitating reliable IoMT is anomaly detection, which involves sending alerts when a medical device’s usage pattern deviates from normal behavior. Due to the safety-critical nature of IoMT, the anomaly detectors are expected to have consistently high accuracy and low error, ideally being bounded with a guarantee. Besides, since the IoMT-based system is non-stationary, the anomaly detector and the performance guarantee should adapt to the evolving data distributions. To tackle these challenges, we propose a framework for incremental anomaly detection in IoMT with a Probably Approximately Correct (PAC)-based two-sided guarantee, guided by a human-in-the-loop design to accommodate shifts in anomaly distributions. As a result, our framework can improve detection performance and provide a tight guarantee on False Alarm Rate (FAR) and Miss Alarm Rate (MAR). We demonstrate the effectiveness of our design using synthetic data and the real-world IoMT monitoring platform VitalCore.Keywords
Funding Information
- NSF (National Science Foundation) (1915398)
- Army Research Office (W911NF-20-1-0080)
This publication has 24 references indexed in Scilit:
- A Survey on Anomaly detection in Evolving DataACM SIGKDD Explorations Newsletter, 2018
- Incremental anomaly detection using two-layer cluster-based structureInformation Sciences, 2018
- Incremental Clustering for Semi-Supervised Anomaly Detection applied on Log Data2017
- Incremental anomaly-based intrusion detection system using limited labeled data2017
- Online Incremental Learning Algorithm for anomaly detection and prediction in health care2014
- Optimizing system monitoring configurations for non-actionable alerts2012
- Direct importance estimation for covariate shift adaptationAnnals of the Institute of Statistical Mathematics, 2008
- A Comparative Study of Anomaly Detection Schemes in Network Intrusion Detection2003
- Inductive Confidence Machines for Regression2002
- Safety critical systems2002