Soldering Data Classification with a Deep Clustering Approach: Case Study of an Academic-Industrial Cooperation
Modern industries still commonly use traditional methods to visually inspect products, even though automation has many advantages over the skills of human labour. The automation of redundant tasks is one of the greatest successes of Artificial Intelligence (AI). It employs human annotation and finds...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-07-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/12/14/6927 |
_version_ | 1797407686135906304 |
---|---|
author | Kinga Bettina Faragó Joul Skaf Szabolcs Forgács Bence Hevesi András Lőrincz |
author_facet | Kinga Bettina Faragó Joul Skaf Szabolcs Forgács Bence Hevesi András Lőrincz |
author_sort | Kinga Bettina Faragó |
collection | DOAJ |
description | Modern industries still commonly use traditional methods to visually inspect products, even though automation has many advantages over the skills of human labour. The automation of redundant tasks is one of the greatest successes of Artificial Intelligence (AI). It employs human annotation and finds possible relationships between features within a particular dataset. However, until recently, this has always been the responsibility of AI specialists with a specific type of knowledge that is not available to the industrial domain experts. We documented the joint research of AI and domain experts as a case study on processing a soldering-related industrial dataset. Our image classification approach relies on the latent space representations of neural networks already trained on other databases. We perform dimensionality reduction of the representations of the new data and cluster the outputs in the lower dimension. This method requires little to no knowledge of the underlying architecture of neural networks by the domain experts, meaning it is easily manageable by them, supporting generalization to other use cases that can be investigated in future work. We also suggest a misclassification detecting method. We were able to achieve near-perfect test accuracy with minimal annotation work. |
first_indexed | 2024-03-09T03:45:07Z |
format | Article |
id | doaj.art-25f7d87eba4840dbaedfe285bfbdd201 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-09T03:45:07Z |
publishDate | 2022-07-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-25f7d87eba4840dbaedfe285bfbdd2012023-12-03T14:35:16ZengMDPI AGApplied Sciences2076-34172022-07-011214692710.3390/app12146927Soldering Data Classification with a Deep Clustering Approach: Case Study of an Academic-Industrial CooperationKinga Bettina Faragó0Joul Skaf1Szabolcs Forgács2Bence Hevesi3András Lőrincz4Department of Artificial Intelligence, Faculty of Informatics, ELTE Eötvös Loránd University, Pázmány Péter Sétány 1/A, 1117 Budapest, HungaryDepartment of Artificial Intelligence, Faculty of Informatics, ELTE Eötvös Loránd University, Pázmány Péter Sétány 1/A, 1117 Budapest, HungaryRobert Bosch Ltd., Gyömrői út 104, 1103 Budapest, HungaryRobert Bosch Ltd., Gyömrői út 104, 1103 Budapest, HungaryDepartment of Artificial Intelligence, Faculty of Informatics, ELTE Eötvös Loránd University, Pázmány Péter Sétány 1/A, 1117 Budapest, HungaryModern industries still commonly use traditional methods to visually inspect products, even though automation has many advantages over the skills of human labour. The automation of redundant tasks is one of the greatest successes of Artificial Intelligence (AI). It employs human annotation and finds possible relationships between features within a particular dataset. However, until recently, this has always been the responsibility of AI specialists with a specific type of knowledge that is not available to the industrial domain experts. We documented the joint research of AI and domain experts as a case study on processing a soldering-related industrial dataset. Our image classification approach relies on the latent space representations of neural networks already trained on other databases. We perform dimensionality reduction of the representations of the new data and cluster the outputs in the lower dimension. This method requires little to no knowledge of the underlying architecture of neural networks by the domain experts, meaning it is easily manageable by them, supporting generalization to other use cases that can be investigated in future work. We also suggest a misclassification detecting method. We were able to achieve near-perfect test accuracy with minimal annotation work.https://www.mdpi.com/2076-3417/12/14/6927visual inspectionindustrial datapre-trained modelsimage classificationdeep clustering |
spellingShingle | Kinga Bettina Faragó Joul Skaf Szabolcs Forgács Bence Hevesi András Lőrincz Soldering Data Classification with a Deep Clustering Approach: Case Study of an Academic-Industrial Cooperation Applied Sciences visual inspection industrial data pre-trained models image classification deep clustering |
title | Soldering Data Classification with a Deep Clustering Approach: Case Study of an Academic-Industrial Cooperation |
title_full | Soldering Data Classification with a Deep Clustering Approach: Case Study of an Academic-Industrial Cooperation |
title_fullStr | Soldering Data Classification with a Deep Clustering Approach: Case Study of an Academic-Industrial Cooperation |
title_full_unstemmed | Soldering Data Classification with a Deep Clustering Approach: Case Study of an Academic-Industrial Cooperation |
title_short | Soldering Data Classification with a Deep Clustering Approach: Case Study of an Academic-Industrial Cooperation |
title_sort | soldering data classification with a deep clustering approach case study of an academic industrial cooperation |
topic | visual inspection industrial data pre-trained models image classification deep clustering |
url | https://www.mdpi.com/2076-3417/12/14/6927 |
work_keys_str_mv | AT kingabettinafarago solderingdataclassificationwithadeepclusteringapproachcasestudyofanacademicindustrialcooperation AT joulskaf solderingdataclassificationwithadeepclusteringapproachcasestudyofanacademicindustrialcooperation AT szabolcsforgacs solderingdataclassificationwithadeepclusteringapproachcasestudyofanacademicindustrialcooperation AT bencehevesi solderingdataclassificationwithadeepclusteringapproachcasestudyofanacademicindustrialcooperation AT andraslorincz solderingdataclassificationwithadeepclusteringapproachcasestudyofanacademicindustrialcooperation |