Recent experiments showed application of statistical methods to detect shift in in-home activities routine. These methods considered each type of house activity at initial time normally distributed, with distribution segmented into several regions of different degree of abnormality, with accuracy beyond 90%.
Hoque et all, focused on reducing false alarms in clustering-based anomaly detection on in-home activities with rule-based approach.
Source: E. Hoque, R. F. Dickerson, S. M. Preum, M. Hanson, A. Barth and J. A. Stankovic, “Holmes: A Comprehensive Anomaly Detection System for Daily In-home Activities,” 2015 International Conference on Distributed Computing in Sensor Systems, Fortaleza, pp. 40-51, 2015.
https://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&ved=2ahUKEwi4ybqDwPncAhVELo8KHeOABAAQFjAAegQIAxAC&url=https%3A%2F%2Fwinser.ece.vt.edu%2Fwp-content%2Fuploads%2F2018%2F04%2FDOI_ver.pdf&usg=AOvVaw3iYuPDrUyYIWJK_0MEFEKq
- Badges
- Science topic
- Similar topics
- Education
- Higher Education
- Conferences