Multifeature Fusion-Based Earthquake Event Classification Using Transfer Learning

Gwantae Kim; Bonhwa Ku; Hanseok Ko

doi:10.1109/LGRS.2020.2993302

Multifeature Fusion-Based Earthquake Event Classification Using Transfer Learning

Gwantae Kim, Bonhwa Ku, Hanseok Ko^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

21 Citations (Scopus)

Abstract

This letter proposes a multifeature fusion model using deep convolution neural networks and transfer learning approach for earthquake event classification. There are several feature representations for seismic analysis, such as the time domain, the frequency domain, and the time-frequency domain. To successfully classify various earthquake events, we propose a novel model that combines these features hierarchically. In addition, we apply a transfer learning to mitigate overfitting problem of deep learning model while achieving high classification performance. To evaluate our approach, we conduct experiments with the Korean peninsula earthquake database from 2016 to 2018 and a large earthquake database on the Circum-Pacific belt in 2019. The experimental results show that the proposed method outperforms over the compared state-of-the-art methods.

Original language	English
Article number	9098918
Pages (from-to)	974-978
Number of pages	5
Journal	IEEE Geoscience and Remote Sensing Letters
Volume	18
Issue number	6
DOIs	https://doi.org/10.1109/LGRS.2020.2993302
Publication status	Published - 2021 Jun

Bibliographical note

Funding Information:
Manuscript received November 26, 2019; revised March 9, 2020; accepted May 4, 2020. Date of publication May 22, 2020; date of current version May 21, 2021. This work was supported by Meteorological/Earthquake See-At Technology Development Research under Grant KMI2018-09610. (Corresponding author: Hanseok Ko.) The authors are with the School of Electrical Engineering, Korea University, Seoul 02841, South Korea (e-mail: [email protected]; [email protected]; [email protected]).

Publisher Copyright:
© 2004-2012 IEEE.

Keywords

Convolution neural network (CNN)
deep learning
earthquake event classification
multifeature fusion
transfer learning

ASJC Scopus subject areas

Geotechnical Engineering and Engineering Geology
Electrical and Electronic Engineering

Access to Document

10.1109/LGRS.2020.2993302

Cite this

@article{e632c884f3224d0688bbe8c6388b25be,

title = "Multifeature Fusion-Based Earthquake Event Classification Using Transfer Learning",

abstract = "This letter proposes a multifeature fusion model using deep convolution neural networks and transfer learning approach for earthquake event classification. There are several feature representations for seismic analysis, such as the time domain, the frequency domain, and the time-frequency domain. To successfully classify various earthquake events, we propose a novel model that combines these features hierarchically. In addition, we apply a transfer learning to mitigate overfitting problem of deep learning model while achieving high classification performance. To evaluate our approach, we conduct experiments with the Korean peninsula earthquake database from 2016 to 2018 and a large earthquake database on the Circum-Pacific belt in 2019. The experimental results show that the proposed method outperforms over the compared state-of-the-art methods. ",

keywords = "Convolution neural network (CNN), deep learning, earthquake event classification, multifeature fusion, transfer learning",

author = "Gwantae Kim and Bonhwa Ku and Hanseok Ko",

note = "Funding Information: Manuscript received November 26, 2019; revised March 9, 2020; accepted May 4, 2020. Date of publication May 22, 2020; date of current version May 21, 2021. This work was supported by Meteorological/Earthquake See-At Technology Development Research under Grant KMI2018-09610. (Corresponding author: Hanseok Ko.) The authors are with the School of Electrical Engineering, Korea University, Seoul 02841, South Korea (e-mail: [email protected]; [email protected]; [email protected]). Publisher Copyright: {\textcopyright} 2004-2012 IEEE.",

year = "2021",

month = jun,

doi = "10.1109/LGRS.2020.2993302",

language = "English",

volume = "18",

pages = "974--978",

journal = "IEEE Geoscience and Remote Sensing Letters",

issn = "1545-598X",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "6",

}

TY - JOUR

T1 - Multifeature Fusion-Based Earthquake Event Classification Using Transfer Learning

AU - Kim, Gwantae

AU - Ku, Bonhwa

AU - Ko, Hanseok

N1 - Funding Information: Manuscript received November 26, 2019; revised March 9, 2020; accepted May 4, 2020. Date of publication May 22, 2020; date of current version May 21, 2021. This work was supported by Meteorological/Earthquake See-At Technology Development Research under Grant KMI2018-09610. (Corresponding author: Hanseok Ko.) The authors are with the School of Electrical Engineering, Korea University, Seoul 02841, South Korea (e-mail: [email protected]; [email protected]; [email protected]). Publisher Copyright: © 2004-2012 IEEE.

PY - 2021/6

Y1 - 2021/6

N2 - This letter proposes a multifeature fusion model using deep convolution neural networks and transfer learning approach for earthquake event classification. There are several feature representations for seismic analysis, such as the time domain, the frequency domain, and the time-frequency domain. To successfully classify various earthquake events, we propose a novel model that combines these features hierarchically. In addition, we apply a transfer learning to mitigate overfitting problem of deep learning model while achieving high classification performance. To evaluate our approach, we conduct experiments with the Korean peninsula earthquake database from 2016 to 2018 and a large earthquake database on the Circum-Pacific belt in 2019. The experimental results show that the proposed method outperforms over the compared state-of-the-art methods.

AB - This letter proposes a multifeature fusion model using deep convolution neural networks and transfer learning approach for earthquake event classification. There are several feature representations for seismic analysis, such as the time domain, the frequency domain, and the time-frequency domain. To successfully classify various earthquake events, we propose a novel model that combines these features hierarchically. In addition, we apply a transfer learning to mitigate overfitting problem of deep learning model while achieving high classification performance. To evaluate our approach, we conduct experiments with the Korean peninsula earthquake database from 2016 to 2018 and a large earthquake database on the Circum-Pacific belt in 2019. The experimental results show that the proposed method outperforms over the compared state-of-the-art methods.

KW - Convolution neural network (CNN)

KW - deep learning

KW - earthquake event classification

KW - multifeature fusion

KW - transfer learning

UR - https://www.scopus.com/pages/publications/85106719438

U2 - 10.1109/LGRS.2020.2993302

DO - 10.1109/LGRS.2020.2993302

M3 - Article

AN - SCOPUS:85106719438

SN - 1545-598X

VL - 18

SP - 974

EP - 978

JO - IEEE Geoscience and Remote Sensing Letters

JF - IEEE Geoscience and Remote Sensing Letters

IS - 6

M1 - 9098918

ER -

Multifeature Fusion-Based Earthquake Event Classification Using Transfer Learning

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this