UoCAD: An Unsupervised Online Contextual Anomaly Detection Approach for Multivariate Time Series from Smart Homes

Aafan Toor, Jia-Chun Lin, Ming-Chang Lee, Ernst Gran

2024

Abstract

In the context of time series data, a contextual anomaly is considered an event or action that causes a deviation in the data values from the norm. This deviation may appear normal if we do not consider the timestamp associated with it. Detecting contextual anomalies in real-world time series data poses a challenge because it often requires domain knowledge and an understanding of the surrounding context. In this paper, we propose UoCAD, an online contextual anomaly detection approach for multivariate time series data. UoCAD employs a sliding window method to (re)train a Bi-LSTM model in an online manner. UoCAD uses the model to predict the upcoming value for each variable/feature and calculates the model’s prediction error value for each feature. To adapt to minor pattern changes, UoCAD employs a double-check approach without immediately triggering an anomaly notification. Two criteria, individual and majority, are explored for anomaly detection. The individual criterion identifies an anomaly if any feature is detected as anomalous, while the majority criterion triggers an anomaly when more than half of the features are identified as anomalous. We evaluate UoCAD using an air quality dataset containing a contextual anomaly. The results show UoCAD’s effectiveness in detecting the contextual anomaly across different sliding window sizes but with varying false positives and detection time consumption.

Paper Citation

in Harvard Style

Toor A., Lin J., Lee M. and Gran E. (2024). UoCAD: An Unsupervised Online Contextual Anomaly Detection Approach for Multivariate Time Series from Smart Homes. In Proceedings of the 9th International Conference on Internet of Things, Big Data and Security - Volume 1: IoTBDS; ISBN 978-989-758-699-6, SciTePress, pages 86-96. DOI: 10.5220/0012692100003705

in Bibtex Style

@conference{iotbds24,
author={Aafan Toor and Jia-Chun Lin and Ming-Chang Lee and Ernst Gran},
title={UoCAD: An Unsupervised Online Contextual Anomaly Detection Approach for Multivariate Time Series from Smart Homes},
booktitle={Proceedings of the 9th International Conference on Internet of Things, Big Data and Security - Volume 1: IoTBDS},
year={2024},
pages={86-96},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012692100003705},
isbn={978-989-758-699-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 9th International Conference on Internet of Things, Big Data and Security - Volume 1: IoTBDS
TI - UoCAD: An Unsupervised Online Contextual Anomaly Detection Approach for Multivariate Time Series from Smart Homes
SN - 978-989-758-699-6
AU - Toor A.
AU - Lin J.
AU - Lee M.
AU - Gran E.
PY - 2024
SP - 86
EP - 96
DO - 10.5220/0012692100003705
PB - SciTePress