Advanced search
2 files | 2.90 MB

Comprehensive feature selection for appliance classification in NILM

Nasrin Sadeghianpourhamami (UGent) , Joeri Ruyssinck (UGent) , Dirk Deschrijver (UGent) , Tom Dhaene (UGent) and Chris Develder (UGent)
(2017) ENERGY AND BUILDINGS. 151. p.98-106
Author
Organization
Abstract
Since the inception of non-intrusive appliance load monitoring (NILM), extensive research has focused on identifying an effective set of features that allows to form a unique appliance signature to discriminate various loads. Although an abundance of features are reported in literature, most works use only a limited subset of them. A systematic comparison and combination of the available features in terms of their effectiveness is still missing. This paper, as its first contribution, offers a concise and updated review of the features reported in literature for the purpose of load identification. As a second contribution, a systematic feature elimination process is proposed to identify the most effective feature set. The analysis is validated on a large benchmark dataset and shows that the proposed feature elimination process improves the appliance classification accuracy for all the appliances in the dataset compared to using all the features or randomly chosen subsets of features. (C) 2017 Elsevier B.V. All rights reserved.
Keywords
IBCN, MAJOR END-USES, RESIDENTIAL BUILDINGS, DISAGGREGATION, IDENTIFICATION, LOADS, CONSUMPTION, ELECTRICITY, RECOGNITION, SIGNATURES, SYSTEMS

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.92 MB
  • 6966 i.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 979.68 KB

Citation

Please use this url to cite or link to this publication:

Chicago
Sadeghianpourhamami, Nasrin, Joeri Ruyssinck, Dirk Deschrijver, Tom Dhaene, and Chris Develder. 2017. “Comprehensive Feature Selection for Appliance Classification in NILM.” Energy and Buildings 151: 98–106.
APA
Sadeghianpourhamami, N., Ruyssinck, J., Deschrijver, D., Dhaene, T., & Develder, C. (2017). Comprehensive feature selection for appliance classification in NILM. ENERGY AND BUILDINGS, 151, 98–106.
Vancouver
1.
Sadeghianpourhamami N, Ruyssinck J, Deschrijver D, Dhaene T, Develder C. Comprehensive feature selection for appliance classification in NILM. ENERGY AND BUILDINGS. 2017;151:98–106.
MLA
Sadeghianpourhamami, Nasrin, Joeri Ruyssinck, Dirk Deschrijver, et al. “Comprehensive Feature Selection for Appliance Classification in NILM.” ENERGY AND BUILDINGS 151 (2017): 98–106. Print.
@article{8533445,
  abstract     = {Since the inception of non-intrusive appliance load monitoring (NILM), extensive research has focused on identifying an effective set of features that allows to form a unique appliance signature to discriminate various loads. Although an abundance of features are reported in literature, most works use only a limited subset of them. A systematic comparison and combination of the available features in terms of their effectiveness is still missing. This paper, as its first contribution, offers a concise and updated review of the features reported in literature for the purpose of load identification. As a second contribution, a systematic feature elimination process is proposed to identify the most effective feature set. The analysis is validated on a large benchmark dataset and shows that the proposed feature elimination process improves the appliance classification accuracy for all the appliances in the dataset compared to using all the features or randomly chosen subsets of features. (C) 2017 Elsevier B.V. All rights reserved.},
  author       = {Sadeghianpourhamami, Nasrin and Ruyssinck, Joeri and Deschrijver, Dirk and Dhaene, Tom and Develder, Chris},
  issn         = {0378-7788},
  journal      = {ENERGY AND BUILDINGS},
  language     = {eng},
  pages        = {98--106},
  title        = {Comprehensive feature selection for appliance classification in NILM},
  url          = {http://dx.doi.org/10.1016/j.enbuild.2017.06.042},
  volume       = {151},
  year         = {2017},
}

Altmetric
View in Altmetric
Web of Science
Times cited: