Anomaly Detection for an Elderly Person Watching System using Multiple Power Consumption Models

Maiya Hori, Tatsuro Harada, Rin-ichiro Taniguchi

2017

Abstract

We propose an anomaly detection method for watching elderly people using only the power data acquired by a smart meter. In a conventional system that uses only power data, a warning is issued if the power consumption does not increase after the wake-up time or when the amount of power does not change for a long time. These methods need to set the wake-up time and power threshold for each user. Furthermore, wrong warnings are issued while residents are out of the home. In our method, multiple common power consumption models are created for each household for each short time zone, and a watching system is constructed by regarding the gaps between these models and newly observed data as anomaly values. This can be automatically applied to various situations such as “during sleep,” “during home activity” and “time zone for frequently going out in the daytime.”

References

  1. Cabinet Office, Government of Japan (2016). Annual report on the aging society. http://www8.cao.go.jp/kourei/whitepaper/w2016/zenbun/28pdf index.html.
  2. Dasarathy, B. V. (1990). Nearest Neighbor: Pattern Classification Techniques. IEEE Computer Society.
  3. Doi, M., Inoue, H., Aoki, Y., and Oshiro, O. (2006). Video surveillance system for elderly person living alone by person tracking and fall detection. IEEJ Transactions on Sensors and Micromachines, 126(8):457-463.
  4. kondo, S. (2011). Safety confirmation system for elderly single-person household with sensor systems. IEEJ Transactions on Electronics, Information and Systems, 131(7):1293-1297.
  5. Nakano, Y. and Ueno, T. (2014). Sensor data classification for indoor situations using the multifunctional outlet. IEEJ Transactions on Electronics, Information and Systems, 134(7):949-955.
  6. Nakano, Y. and Ueno, T. (2016). Watching system for aged single person based on electricity use. IEEJ Transactions on Electronics, Information and Systems, 136(6):767-774.
  7. Ota, K., Otsu, M., Ota, Y., and Kajiwara, A. (2011). Elderly-care motion monitoring sensor using ultrawideband radio. IEEJ Transactions on Electronics, Information and Systems, 131(9):1547-1552.
Download


Paper Citation


in Harvard Style

Hori M., Harada T. and Taniguchi R. (2017). Anomaly Detection for an Elderly Person Watching System using Multiple Power Consumption Models . In Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-222-6, pages 669-675. DOI: 10.5220/0006247006690675


in Bibtex Style

@conference{icpram17,
author={Maiya Hori and Tatsuro Harada and Rin-ichiro Taniguchi},
title={Anomaly Detection for an Elderly Person Watching System using Multiple Power Consumption Models},
booktitle={Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2017},
pages={669-675},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006247006690675},
isbn={978-989-758-222-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Anomaly Detection for an Elderly Person Watching System using Multiple Power Consumption Models
SN - 978-989-758-222-6
AU - Hori M.
AU - Harada T.
AU - Taniguchi R.
PY - 2017
SP - 669
EP - 675
DO - 10.5220/0006247006690675