Mining residential household information from low-resolution smart meter data

Francesco Fusco, Michael Wurst, Ji Won Yoon

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

9 Citations (Scopus)

Abstract

The implementation of electricity smart meters has raised a number of privacy concerns, related to all sorts of information about the nature of the residents that could be inferred from readings of the power consumption. In this paper we attempt to classify households according to different classes, ranging from the presence of kids and of specific appliances to the employment status and education level of the residents. We apply a wide range of features and classification methods and measure the achievable accuracy. It is shown that, at a time resolution of 30 minutes, only a few of the investigated problems give a satisfactorily accuracy, while most of them would require a higher sampling frequency that is not practical for smart meters.

Original languageEnglish
Title of host publicationProceedings - International Conference on Pattern Recognition
Pages3545-3548
Number of pages4
Publication statusPublished - 2012 Dec 1
Externally publishedYes
Event21st International Conference on Pattern Recognition, ICPR 2012 - Tsukuba, Japan
Duration: 2012 Nov 112012 Nov 15

Other

Other21st International Conference on Pattern Recognition, ICPR 2012
CountryJapan
CityTsukuba
Period12/11/1112/11/15

Fingerprint

Smart meters
Electric power utilization
Electricity
Education
Sampling

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Fusco, F., Wurst, M., & Yoon, J. W. (2012). Mining residential household information from low-resolution smart meter data. In Proceedings - International Conference on Pattern Recognition (pp. 3545-3548). [6460930]

Mining residential household information from low-resolution smart meter data. / Fusco, Francesco; Wurst, Michael; Yoon, Ji Won.

Proceedings - International Conference on Pattern Recognition. 2012. p. 3545-3548 6460930.

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

Fusco, F, Wurst, M & Yoon, JW 2012, Mining residential household information from low-resolution smart meter data. in Proceedings - International Conference on Pattern Recognition., 6460930, pp. 3545-3548, 21st International Conference on Pattern Recognition, ICPR 2012, Tsukuba, Japan, 12/11/11.
Fusco F, Wurst M, Yoon JW. Mining residential household information from low-resolution smart meter data. In Proceedings - International Conference on Pattern Recognition. 2012. p. 3545-3548. 6460930
Fusco, Francesco ; Wurst, Michael ; Yoon, Ji Won. / Mining residential household information from low-resolution smart meter data. Proceedings - International Conference on Pattern Recognition. 2012. pp. 3545-3548
@inproceedings{ca9dd84745a54bd2980818d6a5da0926,
title = "Mining residential household information from low-resolution smart meter data",
abstract = "The implementation of electricity smart meters has raised a number of privacy concerns, related to all sorts of information about the nature of the residents that could be inferred from readings of the power consumption. In this paper we attempt to classify households according to different classes, ranging from the presence of kids and of specific appliances to the employment status and education level of the residents. We apply a wide range of features and classification methods and measure the achievable accuracy. It is shown that, at a time resolution of 30 minutes, only a few of the investigated problems give a satisfactorily accuracy, while most of them would require a higher sampling frequency that is not practical for smart meters.",
author = "Francesco Fusco and Michael Wurst and Yoon, {Ji Won}",
year = "2012",
month = "12",
day = "1",
language = "English",
isbn = "9784990644109",
pages = "3545--3548",
booktitle = "Proceedings - International Conference on Pattern Recognition",

}

TY - GEN

T1 - Mining residential household information from low-resolution smart meter data

AU - Fusco, Francesco

AU - Wurst, Michael

AU - Yoon, Ji Won

PY - 2012/12/1

Y1 - 2012/12/1

N2 - The implementation of electricity smart meters has raised a number of privacy concerns, related to all sorts of information about the nature of the residents that could be inferred from readings of the power consumption. In this paper we attempt to classify households according to different classes, ranging from the presence of kids and of specific appliances to the employment status and education level of the residents. We apply a wide range of features and classification methods and measure the achievable accuracy. It is shown that, at a time resolution of 30 minutes, only a few of the investigated problems give a satisfactorily accuracy, while most of them would require a higher sampling frequency that is not practical for smart meters.

AB - The implementation of electricity smart meters has raised a number of privacy concerns, related to all sorts of information about the nature of the residents that could be inferred from readings of the power consumption. In this paper we attempt to classify households according to different classes, ranging from the presence of kids and of specific appliances to the employment status and education level of the residents. We apply a wide range of features and classification methods and measure the achievable accuracy. It is shown that, at a time resolution of 30 minutes, only a few of the investigated problems give a satisfactorily accuracy, while most of them would require a higher sampling frequency that is not practical for smart meters.

UR - http://www.scopus.com/inward/record.url?scp=84874556828&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874556828&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84874556828

SN - 9784990644109

SP - 3545

EP - 3548

BT - Proceedings - International Conference on Pattern Recognition

ER -