Analysis of SEM Images with Artificial Intelligence Methods
[ X ]
Tarih
2022
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Osman SAĞDIÇ
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
Today, the quality of Nanotechnology and Nanoscience working with Artificial Intelligence is increasing day by day. Gains the importance of materials science effectively. Examination of SEM Images with Artificial Intelligence Methods represents a multidisciplinary field. In forming the data used in the experimental part, 22,000 SEM data are publicly available. It is known that CNR-IOM's TASC laboratory in Trieste was obtained as a result of 5 years of work of 100 scientists with the ZEISS SUPRA 40 resolution device. After examining the resolution, image size and quality one by one for the selection of the data in the prototype created for the experimental study, the feature that is considered is the image quality. In the creation of this data, after 100 image data are manually selected and arranged in nano and micro dimensions; A total of 1000 image data were created in 10 data sets. Then, artificial intelligence training was carried out using the CNN classification technique in the experimental study using the unsupervised learning method through machine learning. The approach used here enables the application of new methods and tools by adjusting to develop suitable parameters to solve specific properties of nanomaterials that can be applied to a wide variety of nanoscience use cases. Using it to create a materials science library may pave the way for future studies in the field of artificial intelligence and nanotechnology.
Today, the quality of Nanotechnology and Nanoscience working with Artificial Intelligence is increasing day by day. Gains the importance of materials science effectively. Examination of SEM Images with Artificial Intelligence Methods represents a multidisciplinary field. In forming the data used in the experimental part, 22,000 SEM data are publicly available. It is known that CNR-IOM's TASC laboratory in Trieste was obtained as a result of 5 years of work of 100 scientists with the ZEISS SUPRA 40 resolution device. After examining the resolution, image size and quality one by one for the selection of the data in the prototype created for the experimental study, the feature that is considered is the image quality. In the creation of this data, after 100 image data are manually selected and arranged in nano and micro dimensions; A total of 1000 image data were created in 10 data sets. Then, artificial intelligence training was carried out using the CNN classification technique in the experimental study using the unsupervised learning method through machine learning. The approach used here enables the application of new methods and tools by adjusting to develop suitable parameters to solve specific properties of nanomaterials that can be applied to a wide variety of nanoscience use cases. Using it to create a materials science library may pave the way for future studies in the field of artificial intelligence and nanotechnology.
Today, the quality of Nanotechnology and Nanoscience working with Artificial Intelligence is increasing day by day. Gains the importance of materials science effectively. Examination of SEM Images with Artificial Intelligence Methods represents a multidisciplinary field. In forming the data used in the experimental part, 22,000 SEM data are publicly available. It is known that CNR-IOM's TASC laboratory in Trieste was obtained as a result of 5 years of work of 100 scientists with the ZEISS SUPRA 40 resolution device. After examining the resolution, image size and quality one by one for the selection of the data in the prototype created for the experimental study, the feature that is considered is the image quality. In the creation of this data, after 100 image data are manually selected and arranged in nano and micro dimensions; A total of 1000 image data were created in 10 data sets. Then, artificial intelligence training was carried out using the CNN classification technique in the experimental study using the unsupervised learning method through machine learning. The approach used here enables the application of new methods and tools by adjusting to develop suitable parameters to solve specific properties of nanomaterials that can be applied to a wide variety of nanoscience use cases. Using it to create a materials science library may pave the way for future studies in the field of artificial intelligence and nanotechnology.
Açıklama
Anahtar Kelimeler
Engineering, Mühendislik
Kaynak
European Journal of Science and Technology
Avrupa Bilim ve Teknoloji Dergisi
Avrupa Bilim ve Teknoloji Dergisi
WoS Q Değeri
Scopus Q Değeri
Cilt
Sayı
44
