Pixel-wise classification in graphene-detection with tree-based machine learning algorithms
Mechanical exfoliation of graphene and its identification by optical inspection is one of the milestones in condensed matter physics that sparked the field of two-dimensional materials. Finding regions of interest from the entire sample space and identification of layer number is a routine task pote...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2022-01-01
|
| Series: | Machine Learning: Science and Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2632-2153/aca744 |
| _version_ | 1811158103908941824 |
|---|---|
| author | Woon Hyung Cho Jiseon Shin Young Duck Kim George J Jung |
| author_facet | Woon Hyung Cho Jiseon Shin Young Duck Kim George J Jung |
| author_sort | Woon Hyung Cho |
| collection | DOAJ |
| description | Mechanical exfoliation of graphene and its identification by optical inspection is one of the milestones in condensed matter physics that sparked the field of two-dimensional materials. Finding regions of interest from the entire sample space and identification of layer number is a routine task potentially amenable to automatization. We propose supervised pixel-wise classification methods showing a high performance even with a small number of training image datasets that require short computational time without GPU. We introduce four different tree-based machine learning (ML) algorithms—decision tree, random forest, extreme gradient boost, and light gradient boosting machine. We train them with five optical microscopy images of graphene, and evaluate their performances with multiple metrics and indices. We also discuss combinatorial ML models between the three single classifiers and assess their performances in identification and reliability. The code developed in this paper is open to the public and will be released at https://github.com/gjung-group/Graphene_segmentation . |
| first_indexed | 2024-04-10T05:18:42Z |
| format | Article |
| id | doaj.art-efe6b6a4d072474f80ab7cd6e3e8e035 |
| institution | Directory Open Access Journal |
| issn | 2632-2153 |
| language | English |
| last_indexed | 2024-04-10T05:18:42Z |
| publishDate | 2022-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Machine Learning: Science and Technology |
| spelling | doaj.art-efe6b6a4d072474f80ab7cd6e3e8e0352023-03-08T15:03:26ZengIOP PublishingMachine Learning: Science and Technology2632-21532022-01-013404502910.1088/2632-2153/aca744Pixel-wise classification in graphene-detection with tree-based machine learning algorithmsWoon Hyung Cho0https://orcid.org/0000-0003-2629-8370Jiseon Shin1https://orcid.org/0000-0002-1756-0536Young Duck Kim2https://orcid.org/0000-0003-2593-9826George J Jung3https://orcid.org/0000-0003-2523-0905Department of Physics, University of Seoul , Seoul 02504, Republic of Korea; Department of Smart Cities, University of Seoul , Seoul 02504, Republic of KoreaDepartment of Physics, University of Seoul , Seoul 02504, Republic of KoreaDepartment of Physics, Department of Information Display, KHU-KIST Department of Converging Science and Technology, Kyung Hee University , Seoul, 02447, Republic of KoreaDepartment of Physics, University of Seoul , Seoul 02504, Republic of Korea; Department of Smart Cities, University of Seoul , Seoul 02504, Republic of KoreaMechanical exfoliation of graphene and its identification by optical inspection is one of the milestones in condensed matter physics that sparked the field of two-dimensional materials. Finding regions of interest from the entire sample space and identification of layer number is a routine task potentially amenable to automatization. We propose supervised pixel-wise classification methods showing a high performance even with a small number of training image datasets that require short computational time without GPU. We introduce four different tree-based machine learning (ML) algorithms—decision tree, random forest, extreme gradient boost, and light gradient boosting machine. We train them with five optical microscopy images of graphene, and evaluate their performances with multiple metrics and indices. We also discuss combinatorial ML models between the three single classifiers and assess their performances in identification and reliability. The code developed in this paper is open to the public and will be released at https://github.com/gjung-group/Graphene_segmentation .https://doi.org/10.1088/2632-2153/aca744tree-based machine learninggraphene detectionpixel-wisewithout GPUsegmentation |
| spellingShingle | Woon Hyung Cho Jiseon Shin Young Duck Kim George J Jung Pixel-wise classification in graphene-detection with tree-based machine learning algorithms Machine Learning: Science and Technology tree-based machine learning graphene detection pixel-wise without GPU segmentation |
| title | Pixel-wise classification in graphene-detection with tree-based machine learning algorithms |
| title_full | Pixel-wise classification in graphene-detection with tree-based machine learning algorithms |
| title_fullStr | Pixel-wise classification in graphene-detection with tree-based machine learning algorithms |
| title_full_unstemmed | Pixel-wise classification in graphene-detection with tree-based machine learning algorithms |
| title_short | Pixel-wise classification in graphene-detection with tree-based machine learning algorithms |
| title_sort | pixel wise classification in graphene detection with tree based machine learning algorithms |
| topic | tree-based machine learning graphene detection pixel-wise without GPU segmentation |
| url | https://doi.org/10.1088/2632-2153/aca744 |
| work_keys_str_mv | AT woonhyungcho pixelwiseclassificationingraphenedetectionwithtreebasedmachinelearningalgorithms AT jiseonshin pixelwiseclassificationingraphenedetectionwithtreebasedmachinelearningalgorithms AT youngduckkim pixelwiseclassificationingraphenedetectionwithtreebasedmachinelearningalgorithms AT georgejjung pixelwiseclassificationingraphenedetectionwithtreebasedmachinelearningalgorithms |