Safety Monitoring by a Graph-Regularized Semi-Supervised Nonnegative Matrix Factorization With Applications to a Vision-Based Marking Process
This paper proposes a brand-new method to perform safety monitoring using images for steel coil marking industrial processes. The new safety monitoring method is developed with the aid of a new graph-regularized semi-supervised nonnegative matrix factorization (GSNMF) algorithm. Compared with the ex...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9118902/ |
id |
doaj-1e90029429ef40c88492ea9112c49aef |
---|---|
record_format |
Article |
spelling |
doaj-1e90029429ef40c88492ea9112c49aef2021-03-30T02:46:44ZengIEEEIEEE Access2169-35362020-01-01811227811228610.1109/ACCESS.2020.30028029118902Safety Monitoring by a Graph-Regularized Semi-Supervised Nonnegative Matrix Factorization With Applications to a Vision-Based Marking ProcessSong Fan0https://orcid.org/0000-0003-3131-6238Qilong Jia1https://orcid.org/0000-0002-3256-8202Wan Sheng Cheng2https://orcid.org/0000-0003-2895-5290College of Information Science and Engineering, Northeastern University, Shenyang, ChinaCollege of Information Science and Engineering, Northeastern University, Shenyang, ChinaSchool of Electronic and Information Engineering, University of Science and Technology Liaoning, Anshan, ChinaThis paper proposes a brand-new method to perform safety monitoring using images for steel coil marking industrial processes. The new safety monitoring method is developed with the aid of a new graph-regularized semi-supervised nonnegative matrix factorization (GSNMF) algorithm. Compared with the existing nonnegative matrix factorization (NMF)-like algorithms, GSNMF is developed in an all-new manner so that it not only can take advantage of images with known labels and images with unknown labels to train a model for monitoring purpose, but also can take advantage of graph theory to improve the monitoring performance. Because any two different samples are connected by an edge in a graph, thus graph theory is beneficial for GSNMF to measure the similarity between any two different samples and to assign the same labels for the samples with close connections between them. As a result, GSNMF is more capable of analyzing the samples with a complicated distribution than the existing NMF-like algorithms, theoretically. Finally, an experiment on a steel coil marking process is adopted to evaluate the superiorities of our proposed method over the existing methods.https://ieeexplore.ieee.org/document/9118902/Fault detectionnonnegative matrix factorizationsemi-supervised learningmarking process |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Song Fan Qilong Jia Wan Sheng Cheng |
spellingShingle |
Song Fan Qilong Jia Wan Sheng Cheng Safety Monitoring by a Graph-Regularized Semi-Supervised Nonnegative Matrix Factorization With Applications to a Vision-Based Marking Process IEEE Access Fault detection nonnegative matrix factorization semi-supervised learning marking process |
author_facet |
Song Fan Qilong Jia Wan Sheng Cheng |
author_sort |
Song Fan |
title |
Safety Monitoring by a Graph-Regularized Semi-Supervised Nonnegative Matrix Factorization With Applications to a Vision-Based Marking Process |
title_short |
Safety Monitoring by a Graph-Regularized Semi-Supervised Nonnegative Matrix Factorization With Applications to a Vision-Based Marking Process |
title_full |
Safety Monitoring by a Graph-Regularized Semi-Supervised Nonnegative Matrix Factorization With Applications to a Vision-Based Marking Process |
title_fullStr |
Safety Monitoring by a Graph-Regularized Semi-Supervised Nonnegative Matrix Factorization With Applications to a Vision-Based Marking Process |
title_full_unstemmed |
Safety Monitoring by a Graph-Regularized Semi-Supervised Nonnegative Matrix Factorization With Applications to a Vision-Based Marking Process |
title_sort |
safety monitoring by a graph-regularized semi-supervised nonnegative matrix factorization with applications to a vision-based marking process |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
This paper proposes a brand-new method to perform safety monitoring using images for steel coil marking industrial processes. The new safety monitoring method is developed with the aid of a new graph-regularized semi-supervised nonnegative matrix factorization (GSNMF) algorithm. Compared with the existing nonnegative matrix factorization (NMF)-like algorithms, GSNMF is developed in an all-new manner so that it not only can take advantage of images with known labels and images with unknown labels to train a model for monitoring purpose, but also can take advantage of graph theory to improve the monitoring performance. Because any two different samples are connected by an edge in a graph, thus graph theory is beneficial for GSNMF to measure the similarity between any two different samples and to assign the same labels for the samples with close connections between them. As a result, GSNMF is more capable of analyzing the samples with a complicated distribution than the existing NMF-like algorithms, theoretically. Finally, an experiment on a steel coil marking process is adopted to evaluate the superiorities of our proposed method over the existing methods. |
topic |
Fault detection nonnegative matrix factorization semi-supervised learning marking process |
url |
https://ieeexplore.ieee.org/document/9118902/ |
work_keys_str_mv |
AT songfan safetymonitoringbyagraphregularizedsemisupervisednonnegativematrixfactorizationwithapplicationstoavisionbasedmarkingprocess AT qilongjia safetymonitoringbyagraphregularizedsemisupervisednonnegativematrixfactorizationwithapplicationstoavisionbasedmarkingprocess AT wanshengcheng safetymonitoringbyagraphregularizedsemisupervisednonnegativematrixfactorizationwithapplicationstoavisionbasedmarkingprocess |
_version_ |
1724184603097300992 |