Anomaly detection for an elderly personwatching system using multiple power consumption models

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.

Original languageEnglish
Title of host publicationICPRAM 2017 - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods
EditorsAna Fred, Maria De De Marsico, Gabriella Sanniti di Baja
PublisherSciTePress
Pages669-675
Number of pages7
ISBN (Electronic)9789897582226
Publication statusPublished - Jan 1 2017
Event6th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2017 - Porto, Portugal
Duration: Feb 24 2017Feb 26 2017

Publication series

NameICPRAM 2017 - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods
Volume2017-January

Conference

Conference6th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2017
CountryPortugal
CityPorto
Period2/24/172/26/17

Fingerprint

Electric power utilization
Smart meters
Sleep

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Cite this

Hori, M., Harada, T., & Taniguchi, R-I. (2017). Anomaly detection for an elderly personwatching system using multiple power consumption models. In A. Fred, M. D. De Marsico, & G. S. di Baja (Eds.), ICPRAM 2017 - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods (pp. 669-675). (ICPRAM 2017 - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods; Vol. 2017-January). SciTePress.

Anomaly detection for an elderly personwatching system using multiple power consumption models. / Hori, Maiya; Harada, Tatsuro; Taniguchi, Rin-Ichiro.

ICPRAM 2017 - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods. ed. / Ana Fred; Maria De De Marsico; Gabriella Sanniti di Baja. SciTePress, 2017. p. 669-675 (ICPRAM 2017 - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods; Vol. 2017-January).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hori, M, Harada, T & Taniguchi, R-I 2017, Anomaly detection for an elderly personwatching system using multiple power consumption models. in A Fred, MD De Marsico & GS di Baja (eds), ICPRAM 2017 - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods. ICPRAM 2017 - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods, vol. 2017-January, SciTePress, pp. 669-675, 6th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2017, Porto, Portugal, 2/24/17.
Hori M, Harada T, Taniguchi R-I. Anomaly detection for an elderly personwatching system using multiple power consumption models. In Fred A, De Marsico MD, di Baja GS, editors, ICPRAM 2017 - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods. SciTePress. 2017. p. 669-675. (ICPRAM 2017 - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods).
Hori, Maiya ; Harada, Tatsuro ; Taniguchi, Rin-Ichiro. / Anomaly detection for an elderly personwatching system using multiple power consumption models. ICPRAM 2017 - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods. editor / Ana Fred ; Maria De De Marsico ; Gabriella Sanniti di Baja. SciTePress, 2017. pp. 669-675 (ICPRAM 2017 - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods).
@inproceedings{cbeaee3e7c5c45e9a3d6375be6fbaeb5,
title = "Anomaly detection for an elderly personwatching system using multiple power consumption models",
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.",
author = "Maiya Hori and Tatsuro Harada and Rin-Ichiro Taniguchi",
year = "2017",
month = "1",
day = "1",
language = "English",
series = "ICPRAM 2017 - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods",
publisher = "SciTePress",
pages = "669--675",
editor = "Ana Fred and {De Marsico}, {Maria De} and {di Baja}, {Gabriella Sanniti}",
booktitle = "ICPRAM 2017 - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods",

}

TY - GEN

T1 - Anomaly detection for an elderly personwatching system using multiple power consumption models

AU - Hori, Maiya

AU - Harada, Tatsuro

AU - Taniguchi, Rin-Ichiro

PY - 2017/1/1

Y1 - 2017/1/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85049440493&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049440493&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85049440493

T3 - ICPRAM 2017 - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods

SP - 669

EP - 675

BT - ICPRAM 2017 - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods

A2 - Fred, Ana

A2 - De Marsico, Maria De

A2 - di Baja, Gabriella Sanniti

PB - SciTePress

ER -