Back to Search Start Over

Recovery of Ionospheric Signals Using Fully Convolutional DenseNet and Its Challenges.

Authors :
Mendoza, Merlin M.
Chang, Yu-Chi
Dmitriev, Alexei V.
Lin, Chia-Hsien
Tsai, Lung-Chih
Li, Yung-Hui
Hsieh, Mon-Chai
Hsu, Hao-Wei
Huang, Guan-Han
Lin, Yu-Ciang
Tsogtbaatar, Enkhtuya
Source :
Sensors (14248220); Oct2021, Vol. 21 Issue 19, p6482, 1p
Publication Year :
2021

Abstract

The technique of active ionospheric sounding by ionosondes requires sophisticated methods for the recovery of experimental data on ionograms. In this work, we applied an advanced algorithm of deep learning for the identification and classification of signals from different ionospheric layers. We collected a dataset of 6131 manually labeled ionograms acquired from low-latitude ionosondes in Taiwan. In the ionograms, we distinguished 11 different classes of the signals according to their ionospheric layers. We developed an artificial neural network, FC-DenseNet24, based on the FC-DenseNet convolutional neural network. We also developed a double-filtering algorithm to reduce incorrectly classified signals. That made it possible to successfully recover the sporadic E layer and the F2 layer from highly noise-contaminated ionograms whose mean signal-to-noise ratio was low, SNR = 1.43. The Intersection over Union (IoU) of the recovery of these two signal classes was greater than 0.6, which was higher than the previous models reported. We also identified three factors that can lower the recovery accuracy: (1) smaller statistics of samples; (2) mixing and overlapping of different signals; (3) the compact shape of signals. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
14248220
Volume :
21
Issue :
19
Database :
Complementary Index
Journal :
Sensors (14248220)
Publication Type :
Academic Journal
Accession number :
153039001
Full Text :
https://doi.org/10.3390/s21196482