Feedback Network with Curriculum Learning for Earthquake Event Classification

Jeongki Min; Bonwha Ku; Hanseok Ko

doi:10.1109/LGRS.2021.3097041

Feedback Network with Curriculum Learning for Earthquake Event Classification

Jeongki Min, Bonwha Ku, Hanseok Ko

School of Electrical Engineering

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

1 Citation (Scopus)

Abstract

In this letter, we propose an earthquake event classification model utilizing a feedback network and curriculum learning (CL). In particular, we propose the CL method with a feature concatenation using gated convolution so that CL can be effectively performed in consideration of the feedback structure. We show that the proposed model is effective through comparison experiments with the existing model using the earthquake dataset for Korean Peninsula and the Stanford earthquake dataset.

Original language	English
Journal	IEEE Geoscience and Remote Sensing Letters
Volume	19
DOIs	https://doi.org/10.1109/LGRS.2021.3097041
Publication status	Published - 2022

Bibliographical note

Publisher Copyright:
© 2004-2012 IEEE.

Keywords

Convolutional neural network (CNN)
curriculum learning (CL)
earthquake event classification
feature fusion
feedback

ASJC Scopus subject areas

Geotechnical Engineering and Engineering Geology
Electrical and Electronic Engineering

Access to Document

10.1109/LGRS.2021.3097041

Cite this

@article{cd42c8d0e26947da9be22db420051102,

title = "Feedback Network with Curriculum Learning for Earthquake Event Classification",

abstract = "In this letter, we propose an earthquake event classification model utilizing a feedback network and curriculum learning (CL). In particular, we propose the CL method with a feature concatenation using gated convolution so that CL can be effectively performed in consideration of the feedback structure. We show that the proposed model is effective through comparison experiments with the existing model using the earthquake dataset for Korean Peninsula and the Stanford earthquake dataset. ",

keywords = "Convolutional neural network (CNN), curriculum learning (CL), earthquake event classification, feature fusion, feedback",

author = "Jeongki Min and Bonwha Ku and Hanseok Ko",

note = "Publisher Copyright: {\textcopyright} 2004-2012 IEEE.",

year = "2022",

doi = "10.1109/LGRS.2021.3097041",

language = "English",

volume = "19",

journal = "IEEE Geoscience and Remote Sensing Letters",

issn = "1545-598X",

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

}

TY - JOUR

T1 - Feedback Network with Curriculum Learning for Earthquake Event Classification

AU - Min, Jeongki

AU - Ku, Bonwha

AU - Ko, Hanseok

PY - 2022

Y1 - 2022

N2 - In this letter, we propose an earthquake event classification model utilizing a feedback network and curriculum learning (CL). In particular, we propose the CL method with a feature concatenation using gated convolution so that CL can be effectively performed in consideration of the feedback structure. We show that the proposed model is effective through comparison experiments with the existing model using the earthquake dataset for Korean Peninsula and the Stanford earthquake dataset.

AB - In this letter, we propose an earthquake event classification model utilizing a feedback network and curriculum learning (CL). In particular, we propose the CL method with a feature concatenation using gated convolution so that CL can be effectively performed in consideration of the feedback structure. We show that the proposed model is effective through comparison experiments with the existing model using the earthquake dataset for Korean Peninsula and the Stanford earthquake dataset.

KW - Convolutional neural network (CNN)

KW - curriculum learning (CL)

KW - earthquake event classification

KW - feature fusion

KW - feedback

UR - http://www.scopus.com/inward/record.url?scp=85112630287&partnerID=8YFLogxK

U2 - 10.1109/LGRS.2021.3097041

DO - 10.1109/LGRS.2021.3097041

M3 - Article

AN - SCOPUS:85112630287

SN - 1545-598X

VL - 19

JO - IEEE Geoscience and Remote Sensing Letters

JF - IEEE Geoscience and Remote Sensing Letters

ER -

Feedback Network with Curriculum Learning for Earthquake Event Classification

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this