Applying Deep Learning for Improving Image Classification in Nuclear Fusion Devices
Deep learning has become one of the most promising approaches in recent years. One of the main applications of deep learning is the automatic feature extraction with auto-encoders (AEs). Feature extraction, one of the most important stages in machine learning, that can reduce drastically the dimensi...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2018-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8537905/ |
| _version_ | 1818874770628804608 |
|---|---|
| author | Gonzalo Farias Ernesto Fabregas Sebastian Dormido-Canto Jesus Vega Sebastian Vergara Sebastian Dormido Bencomo Ignacio Pastor Alvaro Olmedo |
| author_facet | Gonzalo Farias Ernesto Fabregas Sebastian Dormido-Canto Jesus Vega Sebastian Vergara Sebastian Dormido Bencomo Ignacio Pastor Alvaro Olmedo |
| author_sort | Gonzalo Farias |
| collection | DOAJ |
| description | Deep learning has become one of the most promising approaches in recent years. One of the main applications of deep learning is the automatic feature extraction with auto-encoders (AEs). Feature extraction, one of the most important stages in machine learning, that can reduce drastically the dimensionality of the problem, making easier any subsequent process such as classification. The main contribution of this research is to evaluate the use of AEs for automatic feature extraction in massive thermonuclear fusion databases. In order to show the performance of AEs in a practical way, the problem of image classification of the TJ-II Thomson Scattering diagnostic has been selected. The classification has been performed by the algorithm of support vector machines and conformal predictors. The results show that the use of AEs produces the predictions faster, with more reliable models, and with higher success rates in comparison to the performance without using the deep learning approach. |
| first_indexed | 2024-12-19T13:15:53Z |
| format | Article |
| id | doaj.art-9f5802444ce54d75989d71d35a924152 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-19T13:15:53Z |
| publishDate | 2018-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-9f5802444ce54d75989d71d35a9241522022-12-21T20:19:49ZengIEEEIEEE Access2169-35362018-01-016723457235610.1109/ACCESS.2018.28818328537905Applying Deep Learning for Improving Image Classification in Nuclear Fusion DevicesGonzalo Farias0https://orcid.org/0000-0003-2186-4126Ernesto Fabregas1https://orcid.org/0000-0003-4478-6626Sebastian Dormido-Canto2Jesus Vega3Sebastian Vergara4Sebastian Dormido Bencomo5Ignacio Pastor6Alvaro Olmedo7Escuela de Ingeniería Eléctrica, Pontificia Universidad Católica de Valparaíso, Avenida Brasil 2147, Valparaíso, ChileDepartamento de Informática y Automática, Universidad Nacional de Educación a Distancia, Madrid, SpainDepartamento de Informática y Automática, Universidad Nacional de Educación a Distancia, Madrid, SpainLaboratorio Nacional de Fusión, CIEMAT, Madrid, SpainEscuela de Ingeniería Eléctrica, Pontificia Universidad Católica de Valparaíso, Avenida Brasil 2147, Valparaíso, ChileDepartamento de Informática y Automática, Universidad Nacional de Educación a Distancia, Madrid, SpainLaboratorio Nacional de Fusión, CIEMAT, Madrid, SpainDepartamento de Informática y Automática, Universidad Nacional de Educación a Distancia, Madrid, SpainDeep learning has become one of the most promising approaches in recent years. One of the main applications of deep learning is the automatic feature extraction with auto-encoders (AEs). Feature extraction, one of the most important stages in machine learning, that can reduce drastically the dimensionality of the problem, making easier any subsequent process such as classification. The main contribution of this research is to evaluate the use of AEs for automatic feature extraction in massive thermonuclear fusion databases. In order to show the performance of AEs in a practical way, the problem of image classification of the TJ-II Thomson Scattering diagnostic has been selected. The classification has been performed by the algorithm of support vector machines and conformal predictors. The results show that the use of AEs produces the predictions faster, with more reliable models, and with higher success rates in comparison to the performance without using the deep learning approach.https://ieeexplore.ieee.org/document/8537905/Images classificationauto-encoderfuture extractionnuclear fusion |
| spellingShingle | Gonzalo Farias Ernesto Fabregas Sebastian Dormido-Canto Jesus Vega Sebastian Vergara Sebastian Dormido Bencomo Ignacio Pastor Alvaro Olmedo Applying Deep Learning for Improving Image Classification in Nuclear Fusion Devices IEEE Access Images classification auto-encoder future extraction nuclear fusion |
| title | Applying Deep Learning for Improving Image Classification in Nuclear Fusion Devices |
| title_full | Applying Deep Learning for Improving Image Classification in Nuclear Fusion Devices |
| title_fullStr | Applying Deep Learning for Improving Image Classification in Nuclear Fusion Devices |
| title_full_unstemmed | Applying Deep Learning for Improving Image Classification in Nuclear Fusion Devices |
| title_short | Applying Deep Learning for Improving Image Classification in Nuclear Fusion Devices |
| title_sort | applying deep learning for improving image classification in nuclear fusion devices |
| topic | Images classification auto-encoder future extraction nuclear fusion |
| url | https://ieeexplore.ieee.org/document/8537905/ |
| work_keys_str_mv | AT gonzalofarias applyingdeeplearningforimprovingimageclassificationinnuclearfusiondevices AT ernestofabregas applyingdeeplearningforimprovingimageclassificationinnuclearfusiondevices AT sebastiandormidocanto applyingdeeplearningforimprovingimageclassificationinnuclearfusiondevices AT jesusvega applyingdeeplearningforimprovingimageclassificationinnuclearfusiondevices AT sebastianvergara applyingdeeplearningforimprovingimageclassificationinnuclearfusiondevices AT sebastiandormidobencomo applyingdeeplearningforimprovingimageclassificationinnuclearfusiondevices AT ignaciopastor applyingdeeplearningforimprovingimageclassificationinnuclearfusiondevices AT alvaroolmedo applyingdeeplearningforimprovingimageclassificationinnuclearfusiondevices |