Predictability of machine learning framework in cross-section data
Today, the use of artificial intelligence in electron optics, as in many other fields, has begun to increase. In this scope, we present a machine learning framework to predict experimental cross-section data. Our framework includes 8 deep learning models and 13 different machine learning algorithms...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
De Gruyter
2023-07-01
|
| Series: | Open Physics |
| Subjects: | |
| Online Access: | https://doi.org/10.1515/phys-2022-0261 |
| _version_ | 1797773501157867520 |
|---|---|
| author | Isik Nimet Eskicioglu Omer Can |
| author_facet | Isik Nimet Eskicioglu Omer Can |
| author_sort | Isik Nimet |
| collection | DOAJ |
| description | Today, the use of artificial intelligence in electron optics, as in many other fields, has begun to increase. In this scope, we present a machine learning framework to predict experimental cross-section data. Our framework includes 8 deep learning models and 13 different machine learning algorithms that learn the fundamental structure of the data. This article aims to develop a machine learning framework to accurately predict double-differential cross-section values. This approach combines multiple models such as convolutional neural networks, machine learning algorithms, and autoencoders to create a more robust prediction system. The data for training the models are obtained from experimental data for different atomic and molecular targets. We developed a methodology for learning tasks, mainly using rigorous prediction error limits. Prediction results show that the machine learning framework can predict the scattering angle and energy of scattering electrons with high accuracy, with an R-squared score of up to 99% and a mean squared error of <0.7. This performance result demonstrates that the proposed machine learning framework can be used to predict electron scattering events, which could be useful for applications such as medical physics. |
| first_indexed | 2024-03-12T22:07:27Z |
| format | Article |
| id | doaj.art-c92bacaa1cd94b48bb4c811041711746 |
| institution | Directory Open Access Journal |
| issn | 2391-5471 |
| language | English |
| last_indexed | 2024-03-12T22:07:27Z |
| publishDate | 2023-07-01 |
| publisher | De Gruyter |
| record_format | Article |
| series | Open Physics |
| spelling | doaj.art-c92bacaa1cd94b48bb4c8110417117462023-07-24T11:19:28ZengDe GruyterOpen Physics2391-54712023-07-012112596710.1515/phys-2022-0261Predictability of machine learning framework in cross-section dataIsik Nimet0Eskicioglu Omer Can1Mathematics, and Science Education Department, Burdur Mehmet Akif Ersoy University, Burdur, TurkeySoftware Engineering Department, Burdur Mehmet Akif Ersoy University, Burdur, TurkeyToday, the use of artificial intelligence in electron optics, as in many other fields, has begun to increase. In this scope, we present a machine learning framework to predict experimental cross-section data. Our framework includes 8 deep learning models and 13 different machine learning algorithms that learn the fundamental structure of the data. This article aims to develop a machine learning framework to accurately predict double-differential cross-section values. This approach combines multiple models such as convolutional neural networks, machine learning algorithms, and autoencoders to create a more robust prediction system. The data for training the models are obtained from experimental data for different atomic and molecular targets. We developed a methodology for learning tasks, mainly using rigorous prediction error limits. Prediction results show that the machine learning framework can predict the scattering angle and energy of scattering electrons with high accuracy, with an R-squared score of up to 99% and a mean squared error of <0.7. This performance result demonstrates that the proposed machine learning framework can be used to predict electron scattering events, which could be useful for applications such as medical physics.https://doi.org/10.1515/phys-2022-0261differential cross sectionmachine learning algorithmregression algorithmsautoencodersdeep learning algorithm |
| spellingShingle | Isik Nimet Eskicioglu Omer Can Predictability of machine learning framework in cross-section data Open Physics differential cross section machine learning algorithm regression algorithms autoencoders deep learning algorithm |
| title | Predictability of machine learning framework in cross-section data |
| title_full | Predictability of machine learning framework in cross-section data |
| title_fullStr | Predictability of machine learning framework in cross-section data |
| title_full_unstemmed | Predictability of machine learning framework in cross-section data |
| title_short | Predictability of machine learning framework in cross-section data |
| title_sort | predictability of machine learning framework in cross section data |
| topic | differential cross section machine learning algorithm regression algorithms autoencoders deep learning algorithm |
| url | https://doi.org/10.1515/phys-2022-0261 |
| work_keys_str_mv | AT isiknimet predictabilityofmachinelearningframeworkincrosssectiondata AT eskiciogluomercan predictabilityofmachinelearningframeworkincrosssectiondata |