Intelligent Identification of MoS<sub>2</sub> Nanostructures with Hyperspectral Imaging by 3D-CNN
Increasing attention has been paid to two-dimensional (2D) materials because of their superior performance and wafer-level synthesis methods. However, the large-area characterization, precision, intelligent automation, and high-efficiency detection of nanostructures for 2D materials have not yet rea...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-06-01
|
| Series: | Nanomaterials |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-4991/10/6/1161 |
| _version_ | 1827715160512397312 |
|---|---|
| author | Kai-Chun Li Ming-Yen Lu Hong Thai Nguyen Shih-Wei Feng Sofya B. Artemkina Vladimir E. Fedorov Hsiang-Chen Wang |
| author_facet | Kai-Chun Li Ming-Yen Lu Hong Thai Nguyen Shih-Wei Feng Sofya B. Artemkina Vladimir E. Fedorov Hsiang-Chen Wang |
| author_sort | Kai-Chun Li |
| collection | DOAJ |
| description | Increasing attention has been paid to two-dimensional (2D) materials because of their superior performance and wafer-level synthesis methods. However, the large-area characterization, precision, intelligent automation, and high-efficiency detection of nanostructures for 2D materials have not yet reached an industrial level. Therefore, we use big data analysis and deep learning methods to develop a set of visible-light hyperspectral imaging technologies successfully for the automatic identification of few-layers MoS<sub>2</sub>. For the classification algorithm, we propose deep neural network, one-dimensional (1D) convolutional neural network, and three-dimensional (3D) convolutional neural network (3D-CNN) models to explore the correlation between the accuracy of model recognition and the optical characteristics of few-layers MoS<sub>2</sub>. The experimental results show that the 3D-CNN has better generalization capability than other classification models, and this model is applicable to the feature input of the spatial and spectral domains. Such a difference consists in previous versions of the present study without specific substrate, and images of different dynamic ranges on a section of the sample may be administered via the automatic shutter aperture. Therefore, adjusting the imaging quality under the same color contrast conditions is unnecessary, and the process of the conventional image is not used to achieve the maximum field of view recognition range of ~1.92 mm<sup>2</sup>. The image resolution can reach ~100 nm and the detection time is 3 min per one image. |
| first_indexed | 2024-03-10T19:12:32Z |
| format | Article |
| id | doaj.art-dd63fd9ac97d42869eaa7083d4c5c5da |
| institution | Directory Open Access Journal |
| issn | 2079-4991 |
| language | English |
| last_indexed | 2024-03-10T19:12:32Z |
| publishDate | 2020-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Nanomaterials |
| spelling | doaj.art-dd63fd9ac97d42869eaa7083d4c5c5da2023-11-20T03:42:46ZengMDPI AGNanomaterials2079-49912020-06-01106116110.3390/nano10061161Intelligent Identification of MoS<sub>2</sub> Nanostructures with Hyperspectral Imaging by 3D-CNNKai-Chun Li0Ming-Yen Lu1Hong Thai Nguyen2Shih-Wei Feng3Sofya B. Artemkina4Vladimir E. Fedorov5Hsiang-Chen Wang6Department of Mechanical Engineering and Advanced Institute of Manufacturing with High Tech Innovations, National Chung Cheng University, 168, University Rd., Min Hsiung, Chia Yi 62102, TaiwanDepartment of Materials Science and Engineering, National Tsing Hua University, 101, Sec. 2, Kuang-Fu Road, Hsinchu 30013, TaiwanDepartment of Mechanical Engineering and Advanced Institute of Manufacturing with High Tech Innovations, National Chung Cheng University, 168, University Rd., Min Hsiung, Chia Yi 62102, TaiwanDepartment of Applied Physics, National University of Kaohsiung, 700 Kaohsiung University Rd., Nanzih District, Kaohsiung 81148, TaiwanNikolaev Institute of Inorganic Chemistry, Siberian Branch of Russian Academy of Sciences, 630090 Novosibirsk, RussiaNikolaev Institute of Inorganic Chemistry, Siberian Branch of Russian Academy of Sciences, 630090 Novosibirsk, RussiaDepartment of Mechanical Engineering and Advanced Institute of Manufacturing with High Tech Innovations, National Chung Cheng University, 168, University Rd., Min Hsiung, Chia Yi 62102, TaiwanIncreasing attention has been paid to two-dimensional (2D) materials because of their superior performance and wafer-level synthesis methods. However, the large-area characterization, precision, intelligent automation, and high-efficiency detection of nanostructures for 2D materials have not yet reached an industrial level. Therefore, we use big data analysis and deep learning methods to develop a set of visible-light hyperspectral imaging technologies successfully for the automatic identification of few-layers MoS<sub>2</sub>. For the classification algorithm, we propose deep neural network, one-dimensional (1D) convolutional neural network, and three-dimensional (3D) convolutional neural network (3D-CNN) models to explore the correlation between the accuracy of model recognition and the optical characteristics of few-layers MoS<sub>2</sub>. The experimental results show that the 3D-CNN has better generalization capability than other classification models, and this model is applicable to the feature input of the spatial and spectral domains. Such a difference consists in previous versions of the present study without specific substrate, and images of different dynamic ranges on a section of the sample may be administered via the automatic shutter aperture. Therefore, adjusting the imaging quality under the same color contrast conditions is unnecessary, and the process of the conventional image is not used to achieve the maximum field of view recognition range of ~1.92 mm<sup>2</sup>. The image resolution can reach ~100 nm and the detection time is 3 min per one image.https://www.mdpi.com/2079-4991/10/6/1161hyperspectral imagerydeep learning3D-CNNMoS<sub>2</sub>automated optical inspection |
| spellingShingle | Kai-Chun Li Ming-Yen Lu Hong Thai Nguyen Shih-Wei Feng Sofya B. Artemkina Vladimir E. Fedorov Hsiang-Chen Wang Intelligent Identification of MoS<sub>2</sub> Nanostructures with Hyperspectral Imaging by 3D-CNN Nanomaterials hyperspectral imagery deep learning 3D-CNN MoS<sub>2</sub> automated optical inspection |
| title | Intelligent Identification of MoS<sub>2</sub> Nanostructures with Hyperspectral Imaging by 3D-CNN |
| title_full | Intelligent Identification of MoS<sub>2</sub> Nanostructures with Hyperspectral Imaging by 3D-CNN |
| title_fullStr | Intelligent Identification of MoS<sub>2</sub> Nanostructures with Hyperspectral Imaging by 3D-CNN |
| title_full_unstemmed | Intelligent Identification of MoS<sub>2</sub> Nanostructures with Hyperspectral Imaging by 3D-CNN |
| title_short | Intelligent Identification of MoS<sub>2</sub> Nanostructures with Hyperspectral Imaging by 3D-CNN |
| title_sort | intelligent identification of mos sub 2 sub nanostructures with hyperspectral imaging by 3d cnn |
| topic | hyperspectral imagery deep learning 3D-CNN MoS<sub>2</sub> automated optical inspection |
| url | https://www.mdpi.com/2079-4991/10/6/1161 |
| work_keys_str_mv | AT kaichunli intelligentidentificationofmossub2subnanostructureswithhyperspectralimagingby3dcnn AT mingyenlu intelligentidentificationofmossub2subnanostructureswithhyperspectralimagingby3dcnn AT hongthainguyen intelligentidentificationofmossub2subnanostructureswithhyperspectralimagingby3dcnn AT shihweifeng intelligentidentificationofmossub2subnanostructureswithhyperspectralimagingby3dcnn AT sofyabartemkina intelligentidentificationofmossub2subnanostructureswithhyperspectralimagingby3dcnn AT vladimirefedorov intelligentidentificationofmossub2subnanostructureswithhyperspectralimagingby3dcnn AT hsiangchenwang intelligentidentificationofmossub2subnanostructureswithhyperspectralimagingby3dcnn |