Interpolation Problem on Outlier Contaminated Seismogram Using Extreme Learning Machine

Hilal Nuha; Bo Liu; Mohamed Mohandes; Ali Al-Shaikhi

doi:10.1007/978-3-030-72896-0_46

Interpolation Problem on Outlier Contaminated Seismogram Using Extreme Learning Machine

Hilal Nuha, Bo Liu, Mohamed Mohandes^*, Ali Al-Shaikhi

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

Abstract

In this work, we present a weighted l₁ norm-based Extreme Learning Machine (ELM), namely, enhanced Regularized ELM (eRELM) for regression problems with outliers contaminated data. The enhancement includes the introduction of a weighting scheme based on l₁ norm to a regularization term in the optimization problem. Seismogram is typically recorded with high frequency. Therefore, it requires a large amount of storage. Interpolation allows the seismogram to be stored with the same quality with a smaller number of samples. Our proposed method shows its robustness on interpolation of outlier contaminated seismogram outperforming other ELM based regression techniques by achieving 0.001245 of root mean squared error.

Original language	English
Title of host publication	Advances in Science, Technology and Innovation
Publisher	Springer Nature
Pages	211-213
Number of pages	3
DOIs	https://doi.org/10.1007/978-3-030-72896-0_46
State	Published - 2022

Publication series

Name	Advances in Science, Technology and Innovation
ISSN (Print)	2522-8714
ISSN (Electronic)	2522-8722

Bibliographical note

Publisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Keywords

Extreme learning machine
L norm
Outlier
Seismogram interpolation

ASJC Scopus subject areas

Architecture
Environmental Chemistry
Renewable Energy, Sustainability and the Environment

Access to Document

10.1007/978-3-030-72896-0_46

Cite this

@inbook{33e624e6bedb4e368d255a9a4ad54ef4,

title = "Interpolation Problem on Outlier Contaminated Seismogram Using Extreme Learning Machine",

abstract = "In this work, we present a weighted l1 norm-based Extreme Learning Machine (ELM), namely, enhanced Regularized ELM (eRELM) for regression problems with outliers contaminated data. The enhancement includes the introduction of a weighting scheme based on l1 norm to a regularization term in the optimization problem. Seismogram is typically recorded with high frequency. Therefore, it requires a large amount of storage. Interpolation allows the seismogram to be stored with the same quality with a smaller number of samples. Our proposed method shows its robustness on interpolation of outlier contaminated seismogram outperforming other ELM based regression techniques by achieving 0.001245 of root mean squared error.",

keywords = "Extreme learning machine, L norm, Outlier, Seismogram interpolation",

author = "Hilal Nuha and Bo Liu and Mohamed Mohandes and Ali Al-Shaikhi",

note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.",

year = "2022",

doi = "10.1007/978-3-030-72896-0_46",

language = "English",

series = "Advances in Science, Technology and Innovation",

publisher = "Springer Nature",

pages = "211--213",

booktitle = "Advances in Science, Technology and Innovation",

address = "United States",

}

TY - CHAP

T1 - Interpolation Problem on Outlier Contaminated Seismogram Using Extreme Learning Machine

AU - Nuha, Hilal

AU - Liu, Bo

AU - Mohandes, Mohamed

AU - Al-Shaikhi, Ali

PY - 2022

Y1 - 2022

N2 - In this work, we present a weighted l1 norm-based Extreme Learning Machine (ELM), namely, enhanced Regularized ELM (eRELM) for regression problems with outliers contaminated data. The enhancement includes the introduction of a weighting scheme based on l1 norm to a regularization term in the optimization problem. Seismogram is typically recorded with high frequency. Therefore, it requires a large amount of storage. Interpolation allows the seismogram to be stored with the same quality with a smaller number of samples. Our proposed method shows its robustness on interpolation of outlier contaminated seismogram outperforming other ELM based regression techniques by achieving 0.001245 of root mean squared error.

AB - In this work, we present a weighted l1 norm-based Extreme Learning Machine (ELM), namely, enhanced Regularized ELM (eRELM) for regression problems with outliers contaminated data. The enhancement includes the introduction of a weighting scheme based on l1 norm to a regularization term in the optimization problem. Seismogram is typically recorded with high frequency. Therefore, it requires a large amount of storage. Interpolation allows the seismogram to be stored with the same quality with a smaller number of samples. Our proposed method shows its robustness on interpolation of outlier contaminated seismogram outperforming other ELM based regression techniques by achieving 0.001245 of root mean squared error.

KW - Extreme learning machine

KW - L norm

KW - Outlier

KW - Seismogram interpolation

UR - http://www.scopus.com/inward/record.url?scp=85125952125&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-72896-0_46

DO - 10.1007/978-3-030-72896-0_46

M3 - Chapter

AN - SCOPUS:85125952125

T3 - Advances in Science, Technology and Innovation

SP - 211

EP - 213

BT - Advances in Science, Technology and Innovation

PB - Springer Nature

ER -

Interpolation Problem on Outlier Contaminated Seismogram Using Extreme Learning Machine

Abstract

Publication series

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this