期刊
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY
卷 12, 期 2, 页码 -出版社
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3439870
关键词
Anomaly detection; Bayesian optimization; smart homes
资金
- National Science Foundation [DGE-0900781]
- National Institutes of Health [R01NR016732]
This study improves traditional anomaly detection methods by introducing Isudra, which utilizes Bayesian optimization for indirectly supervised anomaly detection. Results show that Isudra outperforms both supervised and unsupervised algorithms in detecting health-related anomalies. Isudra enhances anomaly detection accuracy and precision by selecting optimal time scales, features, and algorithms through Bayesian optimization.
Anomaly detection techniques can extract a wealth of information about unusual events. Unfortunately, these methods yield an abundance of findings that are not of interest, obscuring relevant anomalies. In this work, we improve upon traditional anomaly detection methods by introducing Isudra, an Indirectly Supervised Detector of Relevant Anomalies from time series data. Isudra employs Bayesian optimization to select time scales, features, base detector algorithms, and algorithm hyperparameters that increase true positive and decrease false positive detection. This optimization is driven by a small amount of example anomalies, driving an indirectly supervised approach to anomaly detection. Additionally, we enhance the approach by introducing a warm-start method that reduces optimization time between similar problems. We validate the feasibility of Isudra to detect clinically relevant behavior anomalies from over 2M sensor readings collected in five smart homes, reflecting 26 health events. Results indicate that indirectly supervised anomaly detection outperforms both supervised and unsupervised algorithms at detecting instances of health-related anomalies such as falls, nocturia, depression, and weakness.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据