Feature extraction and resident number prediction method using power consumption data

Masahiro Yoshida, Tomoya Imanishi, Hiroaki Nishi

Research output: Contribution to journalArticle

Abstract

A large amount of power consumption information generated from private houses is being aggregated nowadays, particularly by the spread of smart electric meters. Applications that utilize these data are widely studied, and several services have been proposed. In order to utilize the power demand information effectively, an appropriate feature extraction and selection method is necessary. In this paper, a feature extraction method for power consumption information is proposed. Extracted features are used to predict the “number of household members (number of residents)” using typical machine learning algorithms, namely, Support Vector Machine (SVM), k-Nearest Neighborhood (k-NN), and Random Forest (RF). The number of residents represents significant information for the marketing departments of several industries such as real estate and construction industries. The proposed feature extraction method consists of two steps: feature variable generation and feature variable selection. In the feature variable generation step, we have used both fundamental statics and an ARMA model to generate 33 feature variables. In the feature variable selection step, the extracted feature variables are first ranked by applying Analysis of Variance (ANOVA). An appropriate feature variable set is selected by assessing several combinations of the 33 features, based on proposed extended algorithm of Recursive Feature Elimination (RFE). Our overall feature extraction method is evaluated based on the prediction accuracy using extracted feature variables. Compared with the accuracy using feature variables extracted by conventional methods, the accuracy is improved by 6.78%, 4.98%, and 8.11% for k-NN, SVM, and RF, respectively, and we have successfully proven validity of our proposition.

Original languageEnglish
Pages (from-to)227-236
Number of pages10
JournalIEEJ Transactions on Electronics, Information and Systems
Volume139
Issue number3
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

Feature extraction
Electric power utilization
Support vector machines
Electric measuring instruments
Smart meters
Construction industry
Analysis of variance (ANOVA)
Learning algorithms
Learning systems
Marketing
Industry

Keywords

  • Analysis of variance (ANOVA)
  • ARMA model
  • Feature extraction
  • Feature selection
  • Machine learning
  • Smart electric meter

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Feature extraction and resident number prediction method using power consumption data. / Yoshida, Masahiro; Imanishi, Tomoya; Nishi, Hiroaki.

In: IEEJ Transactions on Electronics, Information and Systems, Vol. 139, No. 3, 01.01.2019, p. 227-236.

Research output: Contribution to journalArticle

@article{56be4a41ecd74a579ca2a3758c240930,
title = "Feature extraction and resident number prediction method using power consumption data",
abstract = "A large amount of power consumption information generated from private houses is being aggregated nowadays, particularly by the spread of smart electric meters. Applications that utilize these data are widely studied, and several services have been proposed. In order to utilize the power demand information effectively, an appropriate feature extraction and selection method is necessary. In this paper, a feature extraction method for power consumption information is proposed. Extracted features are used to predict the “number of household members (number of residents)” using typical machine learning algorithms, namely, Support Vector Machine (SVM), k-Nearest Neighborhood (k-NN), and Random Forest (RF). The number of residents represents significant information for the marketing departments of several industries such as real estate and construction industries. The proposed feature extraction method consists of two steps: feature variable generation and feature variable selection. In the feature variable generation step, we have used both fundamental statics and an ARMA model to generate 33 feature variables. In the feature variable selection step, the extracted feature variables are first ranked by applying Analysis of Variance (ANOVA). An appropriate feature variable set is selected by assessing several combinations of the 33 features, based on proposed extended algorithm of Recursive Feature Elimination (RFE). Our overall feature extraction method is evaluated based on the prediction accuracy using extracted feature variables. Compared with the accuracy using feature variables extracted by conventional methods, the accuracy is improved by 6.78{\%}, 4.98{\%}, and 8.11{\%} for k-NN, SVM, and RF, respectively, and we have successfully proven validity of our proposition.",
keywords = "Analysis of variance (ANOVA), ARMA model, Feature extraction, Feature selection, Machine learning, Smart electric meter",
author = "Masahiro Yoshida and Tomoya Imanishi and Hiroaki Nishi",
year = "2019",
month = "1",
day = "1",
doi = "10.1541/ieejeiss.139.227",
language = "English",
volume = "139",
pages = "227--236",
journal = "IEEJ Transactions on Electronics, Information and Systems",
issn = "0385-4221",
publisher = "The Institute of Electrical Engineers of Japan",
number = "3",

}

TY - JOUR

T1 - Feature extraction and resident number prediction method using power consumption data

AU - Yoshida, Masahiro

AU - Imanishi, Tomoya

AU - Nishi, Hiroaki

PY - 2019/1/1

Y1 - 2019/1/1

N2 - A large amount of power consumption information generated from private houses is being aggregated nowadays, particularly by the spread of smart electric meters. Applications that utilize these data are widely studied, and several services have been proposed. In order to utilize the power demand information effectively, an appropriate feature extraction and selection method is necessary. In this paper, a feature extraction method for power consumption information is proposed. Extracted features are used to predict the “number of household members (number of residents)” using typical machine learning algorithms, namely, Support Vector Machine (SVM), k-Nearest Neighborhood (k-NN), and Random Forest (RF). The number of residents represents significant information for the marketing departments of several industries such as real estate and construction industries. The proposed feature extraction method consists of two steps: feature variable generation and feature variable selection. In the feature variable generation step, we have used both fundamental statics and an ARMA model to generate 33 feature variables. In the feature variable selection step, the extracted feature variables are first ranked by applying Analysis of Variance (ANOVA). An appropriate feature variable set is selected by assessing several combinations of the 33 features, based on proposed extended algorithm of Recursive Feature Elimination (RFE). Our overall feature extraction method is evaluated based on the prediction accuracy using extracted feature variables. Compared with the accuracy using feature variables extracted by conventional methods, the accuracy is improved by 6.78%, 4.98%, and 8.11% for k-NN, SVM, and RF, respectively, and we have successfully proven validity of our proposition.

AB - A large amount of power consumption information generated from private houses is being aggregated nowadays, particularly by the spread of smart electric meters. Applications that utilize these data are widely studied, and several services have been proposed. In order to utilize the power demand information effectively, an appropriate feature extraction and selection method is necessary. In this paper, a feature extraction method for power consumption information is proposed. Extracted features are used to predict the “number of household members (number of residents)” using typical machine learning algorithms, namely, Support Vector Machine (SVM), k-Nearest Neighborhood (k-NN), and Random Forest (RF). The number of residents represents significant information for the marketing departments of several industries such as real estate and construction industries. The proposed feature extraction method consists of two steps: feature variable generation and feature variable selection. In the feature variable generation step, we have used both fundamental statics and an ARMA model to generate 33 feature variables. In the feature variable selection step, the extracted feature variables are first ranked by applying Analysis of Variance (ANOVA). An appropriate feature variable set is selected by assessing several combinations of the 33 features, based on proposed extended algorithm of Recursive Feature Elimination (RFE). Our overall feature extraction method is evaluated based on the prediction accuracy using extracted feature variables. Compared with the accuracy using feature variables extracted by conventional methods, the accuracy is improved by 6.78%, 4.98%, and 8.11% for k-NN, SVM, and RF, respectively, and we have successfully proven validity of our proposition.

KW - Analysis of variance (ANOVA)

KW - ARMA model

KW - Feature extraction

KW - Feature selection

KW - Machine learning

KW - Smart electric meter

UR - http://www.scopus.com/inward/record.url?scp=85062404260&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062404260&partnerID=8YFLogxK

U2 - 10.1541/ieejeiss.139.227

DO - 10.1541/ieejeiss.139.227

M3 - Article

VL - 139

SP - 227

EP - 236

JO - IEEJ Transactions on Electronics, Information and Systems

JF - IEEJ Transactions on Electronics, Information and Systems

SN - 0385-4221

IS - 3

ER -