A Constrained Optimization based Extreme Learning Machine for noisy data regression

Shen Yuong Wong, Keem Siah Yap, Hwa Jen Yap

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

Most of the existing Artificial Intelligence (AI) models for data regression commonly assume that the data samples are completely clean without noise or worst yet, only the symmetrical noise is in considerations. However in the real world applications, this is often not the case. This paper addresses a significant note of inefficiency in methods for regression when dealing with outliers, especially for cases with polarity of noise involved (i.e., one sided noise with either only positive noise or negative noise). Using soft margin loss function concept, we propose Constrained Optimization method based Extreme Learning Machine for Regression, hereafter denoted as CO-ELM-R. The proposed method incorporates the two Lagrange multipliers that mimic Support Vector Regression (SVR) into the basis of ELM to cope with infeasible constraints of the regression optimization problem. Thus, CO-ELM-R will complement the recursive iterations of SVR in the training phase due to the fact that ELM is much simpler in structure and faster in implementation. The proposed CO-ELM-R is evaluated empirically on a few benchmark data sets and a real world application of NO. x gas emission data set collected from one of the power plant in Malaysia. The obtained results have demonstrated its validity and efficacy in handling noisy data regression problems.

Original languageEnglish
Pages (from-to)1431-1443
Number of pages13
JournalNeurocomputing
Volume171
DOIs
Publication statusPublished - 01 Jan 2016

Fingerprint

Constrained optimization
Learning systems
Noise
Data handling
Lagrange multipliers
Carbon Monoxide
Gas emissions
Artificial intelligence
Power plants
Power Plants
Benchmarking
Artificial Intelligence
Malaysia
Machine Learning
Gases

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Cognitive Neuroscience
  • Artificial Intelligence

Cite this

@article{b65b209b47444f5181365daf7b622a60,
title = "A Constrained Optimization based Extreme Learning Machine for noisy data regression",
abstract = "Most of the existing Artificial Intelligence (AI) models for data regression commonly assume that the data samples are completely clean without noise or worst yet, only the symmetrical noise is in considerations. However in the real world applications, this is often not the case. This paper addresses a significant note of inefficiency in methods for regression when dealing with outliers, especially for cases with polarity of noise involved (i.e., one sided noise with either only positive noise or negative noise). Using soft margin loss function concept, we propose Constrained Optimization method based Extreme Learning Machine for Regression, hereafter denoted as CO-ELM-R. The proposed method incorporates the two Lagrange multipliers that mimic Support Vector Regression (SVR) into the basis of ELM to cope with infeasible constraints of the regression optimization problem. Thus, CO-ELM-R will complement the recursive iterations of SVR in the training phase due to the fact that ELM is much simpler in structure and faster in implementation. The proposed CO-ELM-R is evaluated empirically on a few benchmark data sets and a real world application of NO. x gas emission data set collected from one of the power plant in Malaysia. The obtained results have demonstrated its validity and efficacy in handling noisy data regression problems.",
author = "{Yuong Wong}, Shen and Yap, {Keem Siah} and {Jen Yap}, Hwa",
year = "2016",
month = "1",
day = "1",
doi = "10.1016/j.neucom.2015.07.065",
language = "English",
volume = "171",
pages = "1431--1443",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",

}

A Constrained Optimization based Extreme Learning Machine for noisy data regression. / Yuong Wong, Shen; Yap, Keem Siah; Jen Yap, Hwa.

In: Neurocomputing, Vol. 171, 01.01.2016, p. 1431-1443.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A Constrained Optimization based Extreme Learning Machine for noisy data regression

AU - Yuong Wong, Shen

AU - Yap, Keem Siah

AU - Jen Yap, Hwa

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Most of the existing Artificial Intelligence (AI) models for data regression commonly assume that the data samples are completely clean without noise or worst yet, only the symmetrical noise is in considerations. However in the real world applications, this is often not the case. This paper addresses a significant note of inefficiency in methods for regression when dealing with outliers, especially for cases with polarity of noise involved (i.e., one sided noise with either only positive noise or negative noise). Using soft margin loss function concept, we propose Constrained Optimization method based Extreme Learning Machine for Regression, hereafter denoted as CO-ELM-R. The proposed method incorporates the two Lagrange multipliers that mimic Support Vector Regression (SVR) into the basis of ELM to cope with infeasible constraints of the regression optimization problem. Thus, CO-ELM-R will complement the recursive iterations of SVR in the training phase due to the fact that ELM is much simpler in structure and faster in implementation. The proposed CO-ELM-R is evaluated empirically on a few benchmark data sets and a real world application of NO. x gas emission data set collected from one of the power plant in Malaysia. The obtained results have demonstrated its validity and efficacy in handling noisy data regression problems.

AB - Most of the existing Artificial Intelligence (AI) models for data regression commonly assume that the data samples are completely clean without noise or worst yet, only the symmetrical noise is in considerations. However in the real world applications, this is often not the case. This paper addresses a significant note of inefficiency in methods for regression when dealing with outliers, especially for cases with polarity of noise involved (i.e., one sided noise with either only positive noise or negative noise). Using soft margin loss function concept, we propose Constrained Optimization method based Extreme Learning Machine for Regression, hereafter denoted as CO-ELM-R. The proposed method incorporates the two Lagrange multipliers that mimic Support Vector Regression (SVR) into the basis of ELM to cope with infeasible constraints of the regression optimization problem. Thus, CO-ELM-R will complement the recursive iterations of SVR in the training phase due to the fact that ELM is much simpler in structure and faster in implementation. The proposed CO-ELM-R is evaluated empirically on a few benchmark data sets and a real world application of NO. x gas emission data set collected from one of the power plant in Malaysia. The obtained results have demonstrated its validity and efficacy in handling noisy data regression problems.

UR - http://www.scopus.com/inward/record.url?scp=84944463466&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84944463466&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2015.07.065

DO - 10.1016/j.neucom.2015.07.065

M3 - Article

AN - SCOPUS:84944463466

VL - 171

SP - 1431

EP - 1443

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

ER -