Cargando…

Power fingerprint identification based on the improved V-I trajectory with color encoding and transferred CBAM-ResNet

In power fingerprint identification, feature information is insufficient when using a single feature to identify equipment, and small load data of specific customers, difficult to meet the refined equipment classification needs. A power fingerprint identification based on the improved voltage-curren...

Descripción completa

Detalles Bibliográficos
Autores principales: Lin, Lin, Zhang, Jie, Gao, Xu, Shi, Jiancheng, Chen, Cheng, Huang, Nantian
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9910749/
https://www.ncbi.nlm.nih.gov/pubmed/36757938
http://dx.doi.org/10.1371/journal.pone.0281482
_version_ 1784884851831209984
author Lin, Lin
Zhang, Jie
Gao, Xu
Shi, Jiancheng
Chen, Cheng
Huang, Nantian
author_facet Lin, Lin
Zhang, Jie
Gao, Xu
Shi, Jiancheng
Chen, Cheng
Huang, Nantian
author_sort Lin, Lin
collection PubMed
description In power fingerprint identification, feature information is insufficient when using a single feature to identify equipment, and small load data of specific customers, difficult to meet the refined equipment classification needs. A power fingerprint identification based on the improved voltage-current(V-I) trajectory with color encoding and transferred CBAM-ResNet34 is proposed. First, the current, instantaneous power, and trajectory momentum information are added to the original V-I trajectory image using color coding to obtain a color V-I trajectory image. Then, the ResNet34 model was pre-trained using the ImageNet dataset and a new fully-connected layer meeting the device classification goal was used to replace the fully-connected layer of ResNet34. The Convolutional Block Attention Module (CBAM) was added to each residual structure module of ResNet34. Finally, Class-Balanced (CB) loss is introduced to reweight the Softmax cross-entropy (SM-CE) loss function to solve the problem of data imbalance in V-I trajectory identification. All parameters are retrained to extract features from the color V-I trajectory images for device classification. The experimental results on the imbalanced PLAID dataset verify that the method in this paper has better classification capability in small sample imbalanced datasets. The experimental results show that the method effectively improves the identification accuracy by 4.4% and reduces the training time of the model by 14 minutes compared with the existing methods, which meets the accuracy requirements of fine-grained power fingerprint identification.
format Online
Article
Text
id pubmed-9910749
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-99107492023-02-10 Power fingerprint identification based on the improved V-I trajectory with color encoding and transferred CBAM-ResNet Lin, Lin Zhang, Jie Gao, Xu Shi, Jiancheng Chen, Cheng Huang, Nantian PLoS One Research Article In power fingerprint identification, feature information is insufficient when using a single feature to identify equipment, and small load data of specific customers, difficult to meet the refined equipment classification needs. A power fingerprint identification based on the improved voltage-current(V-I) trajectory with color encoding and transferred CBAM-ResNet34 is proposed. First, the current, instantaneous power, and trajectory momentum information are added to the original V-I trajectory image using color coding to obtain a color V-I trajectory image. Then, the ResNet34 model was pre-trained using the ImageNet dataset and a new fully-connected layer meeting the device classification goal was used to replace the fully-connected layer of ResNet34. The Convolutional Block Attention Module (CBAM) was added to each residual structure module of ResNet34. Finally, Class-Balanced (CB) loss is introduced to reweight the Softmax cross-entropy (SM-CE) loss function to solve the problem of data imbalance in V-I trajectory identification. All parameters are retrained to extract features from the color V-I trajectory images for device classification. The experimental results on the imbalanced PLAID dataset verify that the method in this paper has better classification capability in small sample imbalanced datasets. The experimental results show that the method effectively improves the identification accuracy by 4.4% and reduces the training time of the model by 14 minutes compared with the existing methods, which meets the accuracy requirements of fine-grained power fingerprint identification. Public Library of Science 2023-02-09 /pmc/articles/PMC9910749/ /pubmed/36757938 http://dx.doi.org/10.1371/journal.pone.0281482 Text en © 2023 Lin et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Lin, Lin
Zhang, Jie
Gao, Xu
Shi, Jiancheng
Chen, Cheng
Huang, Nantian
Power fingerprint identification based on the improved V-I trajectory with color encoding and transferred CBAM-ResNet
title Power fingerprint identification based on the improved V-I trajectory with color encoding and transferred CBAM-ResNet
title_full Power fingerprint identification based on the improved V-I trajectory with color encoding and transferred CBAM-ResNet
title_fullStr Power fingerprint identification based on the improved V-I trajectory with color encoding and transferred CBAM-ResNet
title_full_unstemmed Power fingerprint identification based on the improved V-I trajectory with color encoding and transferred CBAM-ResNet
title_short Power fingerprint identification based on the improved V-I trajectory with color encoding and transferred CBAM-ResNet
title_sort power fingerprint identification based on the improved v-i trajectory with color encoding and transferred cbam-resnet
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9910749/
https://www.ncbi.nlm.nih.gov/pubmed/36757938
http://dx.doi.org/10.1371/journal.pone.0281482
work_keys_str_mv AT linlin powerfingerprintidentificationbasedontheimprovedvitrajectorywithcolorencodingandtransferredcbamresnet
AT zhangjie powerfingerprintidentificationbasedontheimprovedvitrajectorywithcolorencodingandtransferredcbamresnet
AT gaoxu powerfingerprintidentificationbasedontheimprovedvitrajectorywithcolorencodingandtransferredcbamresnet
AT shijiancheng powerfingerprintidentificationbasedontheimprovedvitrajectorywithcolorencodingandtransferredcbamresnet
AT chencheng powerfingerprintidentificationbasedontheimprovedvitrajectorywithcolorencodingandtransferredcbamresnet
AT huangnantian powerfingerprintidentificationbasedontheimprovedvitrajectorywithcolorencodingandtransferredcbamresnet