TY - JOUR
T1 - Automatic feature extraction in large fusion databases by using deep learning approach
AU - Farias, Gonzalo
AU - Dormido-Canto, Sebastián
AU - Vega, Jesús
AU - Rattá, Giuseppe
AU - Vargas, Héctor
AU - Hermosilla, Gabriel
AU - Alfaro, Luis
AU - Valencia, Agustín
N1 - Funding Information:
This work was partially supported by Chilean Ministry of Education under the Project FONDECYT 11121590 and FONDECYT 1161584. This work was partially funded by the Spanish Ministry of Economy and Competitiveness under the Projects Nos. ENE2015-64914-C3-1-R and ENE2015-64914-C3-2-R.
Publisher Copyright:
© 2016 Elsevier B.V.
PY - 2016/11/15
Y1 - 2016/11/15
N2 - Feature extraction is one of the most important machine learning issues. Finding suitable attributes of datasets can enormously reduce the dimensionality of the input space, and from a computational point of view can help all of the following steps of pattern recognition problems, such as classification or information retrieval. However, the feature extraction step is usually performed manually. Moreover, depending on the type of data, we can face a wide range of methods to extract features. In this sense, the process to select appropriate techniques normally takes a long time. This work describes the use of recent advances in deep learning approach in order to find a good feature representation automatically. The implementation of a special neural network called sparse autoencoder and its application to two classification problems of the TJ-II fusion database is shown in detail. Results have shown that it is possible to get robust classifiers with a high successful rate, in spite of the fact that the feature space is reduced to less than 0.02% from the original one.
AB - Feature extraction is one of the most important machine learning issues. Finding suitable attributes of datasets can enormously reduce the dimensionality of the input space, and from a computational point of view can help all of the following steps of pattern recognition problems, such as classification or information retrieval. However, the feature extraction step is usually performed manually. Moreover, depending on the type of data, we can face a wide range of methods to extract features. In this sense, the process to select appropriate techniques normally takes a long time. This work describes the use of recent advances in deep learning approach in order to find a good feature representation automatically. The implementation of a special neural network called sparse autoencoder and its application to two classification problems of the TJ-II fusion database is shown in detail. Results have shown that it is possible to get robust classifiers with a high successful rate, in spite of the fact that the feature space is reduced to less than 0.02% from the original one.
KW - Autoencoder
KW - Future extraction
KW - Machine learning
KW - Thomson scattering
UR - http://www.scopus.com/inward/record.url?scp=84977653795&partnerID=8YFLogxK
U2 - 10.1016/j.fusengdes.2016.06.016
DO - 10.1016/j.fusengdes.2016.06.016
M3 - Article
AN - SCOPUS:84977653795
VL - 112
SP - 979
EP - 983
JO - Fusion Engineering and Design
JF - Fusion Engineering and Design
SN - 0920-3796
ER -