Lasso Regression Based on Empirical Mode Decomposition

Lei Qin, Shuangge Ma, Jung Chen Lin, Ben Chang Shia

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

The Hilbert-Huang transform uses the empirical mode decomposition (EMD) method to analyze nonlinear and nonstationary data. This method breaks a time series of data into several orthogonal sequences based on differences in frequency. These data components include the intrinsic mode functions (IMFs) and the final residue. Although IMFs have been used in the past as predictors for other variables, very little effort has been devoted to identifying the most effective predictors among IMFs. As lasso is a widely used method for feature selection within complex datasets, the main objective of this article is to present a lasso regression based on the EMD method for choosing decomposed components that exhibit the strongest effects. Both numerical experiments and empirical results show that the proposed modeling process can use time-frequency structure within data to reveal interactions between two variables. This allows for more accurate predictions concerning future events.

Original languageEnglish
Pages (from-to)1281-1294
Number of pages14
JournalCommunications in Statistics: Simulation and Computation
Volume45
Issue number4
DOIs
Publication statusPublished - Apr 20 2016
Externally publishedYes

Fingerprint

Intrinsic Mode Function
Lasso
Regression
Decomposition Method
Decomposition
Decompose
Predictors
Hilbert-Huang Transform
Process Modeling
Feature Selection
Feature extraction
Time series
Data Structures
Numerical Experiment
Prediction
Interaction
Experiments

Keywords

  • EMD
  • Lasso
  • Time-frequency structure relationship
  • Two-variable model

ASJC Scopus subject areas

  • Modelling and Simulation
  • Statistics and Probability

Cite this

Lasso Regression Based on Empirical Mode Decomposition. / Qin, Lei; Ma, Shuangge; Lin, Jung Chen; Shia, Ben Chang.

In: Communications in Statistics: Simulation and Computation, Vol. 45, No. 4, 20.04.2016, p. 1281-1294.

Research output: Contribution to journalArticle

Qin, Lei ; Ma, Shuangge ; Lin, Jung Chen ; Shia, Ben Chang. / Lasso Regression Based on Empirical Mode Decomposition. In: Communications in Statistics: Simulation and Computation. 2016 ; Vol. 45, No. 4. pp. 1281-1294.
@article{8eeab86faead4fb88ae7c3eb3fdf7264,
title = "Lasso Regression Based on Empirical Mode Decomposition",
abstract = "The Hilbert-Huang transform uses the empirical mode decomposition (EMD) method to analyze nonlinear and nonstationary data. This method breaks a time series of data into several orthogonal sequences based on differences in frequency. These data components include the intrinsic mode functions (IMFs) and the final residue. Although IMFs have been used in the past as predictors for other variables, very little effort has been devoted to identifying the most effective predictors among IMFs. As lasso is a widely used method for feature selection within complex datasets, the main objective of this article is to present a lasso regression based on the EMD method for choosing decomposed components that exhibit the strongest effects. Both numerical experiments and empirical results show that the proposed modeling process can use time-frequency structure within data to reveal interactions between two variables. This allows for more accurate predictions concerning future events.",
keywords = "EMD, Lasso, Time-frequency structure relationship, Two-variable model",
author = "Lei Qin and Shuangge Ma and Lin, {Jung Chen} and Shia, {Ben Chang}",
year = "2016",
month = "4",
day = "20",
doi = "10.1080/03610918.2013.826361",
language = "English",
volume = "45",
pages = "1281--1294",
journal = "Communications in Statistics Part B: Simulation and Computation",
issn = "0361-0918",
publisher = "Taylor and Francis Ltd.",
number = "4",

}

TY - JOUR

T1 - Lasso Regression Based on Empirical Mode Decomposition

AU - Qin, Lei

AU - Ma, Shuangge

AU - Lin, Jung Chen

AU - Shia, Ben Chang

PY - 2016/4/20

Y1 - 2016/4/20

N2 - The Hilbert-Huang transform uses the empirical mode decomposition (EMD) method to analyze nonlinear and nonstationary data. This method breaks a time series of data into several orthogonal sequences based on differences in frequency. These data components include the intrinsic mode functions (IMFs) and the final residue. Although IMFs have been used in the past as predictors for other variables, very little effort has been devoted to identifying the most effective predictors among IMFs. As lasso is a widely used method for feature selection within complex datasets, the main objective of this article is to present a lasso regression based on the EMD method for choosing decomposed components that exhibit the strongest effects. Both numerical experiments and empirical results show that the proposed modeling process can use time-frequency structure within data to reveal interactions between two variables. This allows for more accurate predictions concerning future events.

AB - The Hilbert-Huang transform uses the empirical mode decomposition (EMD) method to analyze nonlinear and nonstationary data. This method breaks a time series of data into several orthogonal sequences based on differences in frequency. These data components include the intrinsic mode functions (IMFs) and the final residue. Although IMFs have been used in the past as predictors for other variables, very little effort has been devoted to identifying the most effective predictors among IMFs. As lasso is a widely used method for feature selection within complex datasets, the main objective of this article is to present a lasso regression based on the EMD method for choosing decomposed components that exhibit the strongest effects. Both numerical experiments and empirical results show that the proposed modeling process can use time-frequency structure within data to reveal interactions between two variables. This allows for more accurate predictions concerning future events.

KW - EMD

KW - Lasso

KW - Time-frequency structure relationship

KW - Two-variable model

UR - http://www.scopus.com/inward/record.url?scp=84963808628&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84963808628&partnerID=8YFLogxK

U2 - 10.1080/03610918.2013.826361

DO - 10.1080/03610918.2013.826361

M3 - Article

AN - SCOPUS:84963808628

VL - 45

SP - 1281

EP - 1294

JO - Communications in Statistics Part B: Simulation and Computation

JF - Communications in Statistics Part B: Simulation and Computation

SN - 0361-0918

IS - 4

ER -