Feature expression of frequency transform regarding daily power demand information

Tomoya Imanishi, Rajitha Tennekoon, Hiroaki Nishi

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

1 Citation (Scopus)

Abstract

Owing to the introduction of an energy-monitoring device called the "smart meter," a large amount of power-demand information regarding private houses is being stored around the world through the development of smart grids. Such electric consumption data include a variety of features related to the structure of the customer's home, as well as their family structure and lifestyle. To capture the meaningful features from the power-demand information, a proper extraction method should be considered such as a discrete Fourier transform (DFT) or discrete cosine transform (DCT). This paper proposes the use of two frequency analysis methods, i.e., DFT and DCT, toward power-demand information. The converted power-demand information is transformed using three expression methods. A power-demand dataset was gathered from more than 100 houses in Yokohama, Japan, over a two-year period. The numbers of feature values in these three expression methods were compared by estimating the floor space of each customer's house with two support vector classification (SVC) values using both linear and RBF kernels. As a result, the proposed expression method performed better than the other two feature expression methods. The mean accuracy of this expression method is better than the other two by 20%, and the highest level of accuracy in terms of the floor-space estimation is greater than 95% when using liner SVC (L2-SVC). The accuracy shows a distribution of 50% to 100% regardless of the number of selected frequencies transformed using a DFT and DCT.

Original languageEnglish
Title of host publicationProceedings of the 11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017
PublisherAssociation for Computing Machinery, Inc
ISBN (Electronic)9781450348881
DOIs
Publication statusPublished - 2017 Jan 5
Event11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017 - Beppu, Japan
Duration: 2017 Jan 52017 Jan 7

Other

Other11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017
CountryJapan
CityBeppu
Period17/1/517/1/7

Fingerprint

Discrete cosine transforms
Discrete Fourier transforms
Smart meters
Monitoring

Keywords

  • Classification
  • Feature extraction
  • Frequency transform
  • Power demand information
  • Support vector machine

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems

Cite this

Imanishi, T., Tennekoon, R., & Nishi, H. (2017). Feature expression of frequency transform regarding daily power demand information. In Proceedings of the 11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017 [23] Association for Computing Machinery, Inc. https://doi.org/10.1145/3022227.3022249

Feature expression of frequency transform regarding daily power demand information. / Imanishi, Tomoya; Tennekoon, Rajitha; Nishi, Hiroaki.

Proceedings of the 11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017. Association for Computing Machinery, Inc, 2017. 23.

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

Imanishi, T, Tennekoon, R & Nishi, H 2017, Feature expression of frequency transform regarding daily power demand information. in Proceedings of the 11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017., 23, Association for Computing Machinery, Inc, 11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017, Beppu, Japan, 17/1/5. https://doi.org/10.1145/3022227.3022249
Imanishi T, Tennekoon R, Nishi H. Feature expression of frequency transform regarding daily power demand information. In Proceedings of the 11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017. Association for Computing Machinery, Inc. 2017. 23 https://doi.org/10.1145/3022227.3022249
Imanishi, Tomoya ; Tennekoon, Rajitha ; Nishi, Hiroaki. / Feature expression of frequency transform regarding daily power demand information. Proceedings of the 11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017. Association for Computing Machinery, Inc, 2017.
@inproceedings{e79ddf3ddd7c4e8386072f439c8d78b2,
title = "Feature expression of frequency transform regarding daily power demand information",
abstract = "Owing to the introduction of an energy-monitoring device called the {"}smart meter,{"} a large amount of power-demand information regarding private houses is being stored around the world through the development of smart grids. Such electric consumption data include a variety of features related to the structure of the customer's home, as well as their family structure and lifestyle. To capture the meaningful features from the power-demand information, a proper extraction method should be considered such as a discrete Fourier transform (DFT) or discrete cosine transform (DCT). This paper proposes the use of two frequency analysis methods, i.e., DFT and DCT, toward power-demand information. The converted power-demand information is transformed using three expression methods. A power-demand dataset was gathered from more than 100 houses in Yokohama, Japan, over a two-year period. The numbers of feature values in these three expression methods were compared by estimating the floor space of each customer's house with two support vector classification (SVC) values using both linear and RBF kernels. As a result, the proposed expression method performed better than the other two feature expression methods. The mean accuracy of this expression method is better than the other two by 20{\%}, and the highest level of accuracy in terms of the floor-space estimation is greater than 95{\%} when using liner SVC (L2-SVC). The accuracy shows a distribution of 50{\%} to 100{\%} regardless of the number of selected frequencies transformed using a DFT and DCT.",
keywords = "Classification, Feature extraction, Frequency transform, Power demand information, Support vector machine",
author = "Tomoya Imanishi and Rajitha Tennekoon and Hiroaki Nishi",
year = "2017",
month = "1",
day = "5",
doi = "10.1145/3022227.3022249",
language = "English",
booktitle = "Proceedings of the 11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - Feature expression of frequency transform regarding daily power demand information

AU - Imanishi, Tomoya

AU - Tennekoon, Rajitha

AU - Nishi, Hiroaki

PY - 2017/1/5

Y1 - 2017/1/5

N2 - Owing to the introduction of an energy-monitoring device called the "smart meter," a large amount of power-demand information regarding private houses is being stored around the world through the development of smart grids. Such electric consumption data include a variety of features related to the structure of the customer's home, as well as their family structure and lifestyle. To capture the meaningful features from the power-demand information, a proper extraction method should be considered such as a discrete Fourier transform (DFT) or discrete cosine transform (DCT). This paper proposes the use of two frequency analysis methods, i.e., DFT and DCT, toward power-demand information. The converted power-demand information is transformed using three expression methods. A power-demand dataset was gathered from more than 100 houses in Yokohama, Japan, over a two-year period. The numbers of feature values in these three expression methods were compared by estimating the floor space of each customer's house with two support vector classification (SVC) values using both linear and RBF kernels. As a result, the proposed expression method performed better than the other two feature expression methods. The mean accuracy of this expression method is better than the other two by 20%, and the highest level of accuracy in terms of the floor-space estimation is greater than 95% when using liner SVC (L2-SVC). The accuracy shows a distribution of 50% to 100% regardless of the number of selected frequencies transformed using a DFT and DCT.

AB - Owing to the introduction of an energy-monitoring device called the "smart meter," a large amount of power-demand information regarding private houses is being stored around the world through the development of smart grids. Such electric consumption data include a variety of features related to the structure of the customer's home, as well as their family structure and lifestyle. To capture the meaningful features from the power-demand information, a proper extraction method should be considered such as a discrete Fourier transform (DFT) or discrete cosine transform (DCT). This paper proposes the use of two frequency analysis methods, i.e., DFT and DCT, toward power-demand information. The converted power-demand information is transformed using three expression methods. A power-demand dataset was gathered from more than 100 houses in Yokohama, Japan, over a two-year period. The numbers of feature values in these three expression methods were compared by estimating the floor space of each customer's house with two support vector classification (SVC) values using both linear and RBF kernels. As a result, the proposed expression method performed better than the other two feature expression methods. The mean accuracy of this expression method is better than the other two by 20%, and the highest level of accuracy in terms of the floor-space estimation is greater than 95% when using liner SVC (L2-SVC). The accuracy shows a distribution of 50% to 100% regardless of the number of selected frequencies transformed using a DFT and DCT.

KW - Classification

KW - Feature extraction

KW - Frequency transform

KW - Power demand information

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=85015206254&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015206254&partnerID=8YFLogxK

U2 - 10.1145/3022227.3022249

DO - 10.1145/3022227.3022249

M3 - Conference contribution

AN - SCOPUS:85015206254

BT - Proceedings of the 11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017

PB - Association for Computing Machinery, Inc

ER -