Fourier series neural networks for regression

Yung Ming Wang; Li Jeng Huang

doi:10.1109/ICASI.2018.8394358

Fourier series neural networks for regression

Yung Ming Wang, Li Jeng Huang

Department of Civil Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

4 Citations (Scopus)

Abstract

An innovative efficient and fast neural networks in which hidden neurons are constructed based on Fourier series expansions (FSNN), half-range cosine (FCSNN) and sine expansions (FSSNN) are proposed and tested for linear and nonlinear regulation problems. The results of numerical examples using FSNN are compared with those obtained from traditional linear regression (LP), nonlinear regression (NLP), backward propagation neural networks (BPANN) and radial basis function neural networks (RBFNN). The results obtained from FSNN agree well with those obtained from LP, NLP, BPANN and RBFNN and show global approximation features to the fitting data. Only a few hidden neurons are required to obtain very good and fast convergence of regression as compared with BPANN and RBFNN.

Original language	English
Title of host publication	Proceedings of 4th IEEE International Conference on Applied System Innovation 2018, ICASI 2018
Editors	Artde Donald Kin-Tak Lam, Stephen D. Prior, Teen-Hang Meen
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	716-719
Number of pages	4
ISBN (Electronic)	9781538643426
DOIs	https://doi.org/10.1109/ICASI.2018.8394358
Publication status	Published - 2018 Jun 22
Event	4th IEEE International Conference on Applied System Innovation, ICASI 2018 - Chiba, Japan Duration: 2018 Apr 13 → 2018 Apr 17

Publication series

Name	Proceedings of 4th IEEE International Conference on Applied System Innovation 2018, ICASI 2018

Other

Other	4th IEEE International Conference on Applied System Innovation, ICASI 2018
Country/Territory	Japan
City	Chiba
Period	18-04-13 → 18-04-17

All Science Journal Classification (ASJC) codes

Computer Networks and Communications
Hardware and Architecture
Energy Engineering and Power Technology
Control and Systems Engineering
Mechanical Engineering
Control and Optimization
Modelling and Simulation
Biomedical Engineering

Access to Document

10.1109/ICASI.2018.8394358

Cite this

Wang, Y. M., & Huang, L. J. (2018). Fourier series neural networks for regression. In A. D. K.-T. Lam, S. D. Prior, & T.-H. Meen (Eds.), Proceedings of 4th IEEE International Conference on Applied System Innovation 2018, ICASI 2018 (pp. 716-719). (Proceedings of 4th IEEE International Conference on Applied System Innovation 2018, ICASI 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASI.2018.8394358

Wang, Yung Ming ; Huang, Li Jeng. / Fourier series neural networks for regression. Proceedings of 4th IEEE International Conference on Applied System Innovation 2018, ICASI 2018. editor / Artde Donald Kin-Tak Lam ; Stephen D. Prior ; Teen-Hang Meen. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 716-719 (Proceedings of 4th IEEE International Conference on Applied System Innovation 2018, ICASI 2018).

@inproceedings{3084f208758b48f8b6fe645dc2e07dee,

title = "Fourier series neural networks for regression",

abstract = "An innovative efficient and fast neural networks in which hidden neurons are constructed based on Fourier series expansions (FSNN), half-range cosine (FCSNN) and sine expansions (FSSNN) are proposed and tested for linear and nonlinear regulation problems. The results of numerical examples using FSNN are compared with those obtained from traditional linear regression (LP), nonlinear regression (NLP), backward propagation neural networks (BPANN) and radial basis function neural networks (RBFNN). The results obtained from FSNN agree well with those obtained from LP, NLP, BPANN and RBFNN and show global approximation features to the fitting data. Only a few hidden neurons are required to obtain very good and fast convergence of regression as compared with BPANN and RBFNN.",

author = "Wang, {Yung Ming} and Huang, {Li Jeng}",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE. Copyright: Copyright 2018 Elsevier B.V., All rights reserved.; 4th IEEE International Conference on Applied System Innovation, ICASI 2018 ; Conference date: 13-04-2018 Through 17-04-2018",

year = "2018",

month = jun,

day = "22",

doi = "10.1109/ICASI.2018.8394358",

language = "English",

series = "Proceedings of 4th IEEE International Conference on Applied System Innovation 2018, ICASI 2018",

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

pages = "716--719",

editor = "Lam, {Artde Donald Kin-Tak} and Prior, {Stephen D.} and Teen-Hang Meen",

booktitle = "Proceedings of 4th IEEE International Conference on Applied System Innovation 2018, ICASI 2018",

address = "United States",

}

Wang, YM & Huang, LJ 2018, Fourier series neural networks for regression. in ADK-T Lam, SD Prior & T-H Meen (eds), Proceedings of 4th IEEE International Conference on Applied System Innovation 2018, ICASI 2018. Proceedings of 4th IEEE International Conference on Applied System Innovation 2018, ICASI 2018, Institute of Electrical and Electronics Engineers Inc., pp. 716-719, 4th IEEE International Conference on Applied System Innovation, ICASI 2018, Chiba, Japan, 18-04-13. https://doi.org/10.1109/ICASI.2018.8394358

Fourier series neural networks for regression. / Wang, Yung Ming; Huang, Li Jeng.
Proceedings of 4th IEEE International Conference on Applied System Innovation 2018, ICASI 2018. ed. / Artde Donald Kin-Tak Lam; Stephen D. Prior; Teen-Hang Meen. Institute of Electrical and Electronics Engineers Inc., 2018. p. 716-719 (Proceedings of 4th IEEE International Conference on Applied System Innovation 2018, ICASI 2018).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Fourier series neural networks for regression

AU - Wang, Yung Ming

AU - Huang, Li Jeng

PY - 2018/6/22

Y1 - 2018/6/22

N2 - An innovative efficient and fast neural networks in which hidden neurons are constructed based on Fourier series expansions (FSNN), half-range cosine (FCSNN) and sine expansions (FSSNN) are proposed and tested for linear and nonlinear regulation problems. The results of numerical examples using FSNN are compared with those obtained from traditional linear regression (LP), nonlinear regression (NLP), backward propagation neural networks (BPANN) and radial basis function neural networks (RBFNN). The results obtained from FSNN agree well with those obtained from LP, NLP, BPANN and RBFNN and show global approximation features to the fitting data. Only a few hidden neurons are required to obtain very good and fast convergence of regression as compared with BPANN and RBFNN.

AB - An innovative efficient and fast neural networks in which hidden neurons are constructed based on Fourier series expansions (FSNN), half-range cosine (FCSNN) and sine expansions (FSSNN) are proposed and tested for linear and nonlinear regulation problems. The results of numerical examples using FSNN are compared with those obtained from traditional linear regression (LP), nonlinear regression (NLP), backward propagation neural networks (BPANN) and radial basis function neural networks (RBFNN). The results obtained from FSNN agree well with those obtained from LP, NLP, BPANN and RBFNN and show global approximation features to the fitting data. Only a few hidden neurons are required to obtain very good and fast convergence of regression as compared with BPANN and RBFNN.

UR - http://www.scopus.com/inward/record.url?scp=85050259875&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050259875&partnerID=8YFLogxK

U2 - 10.1109/ICASI.2018.8394358

DO - 10.1109/ICASI.2018.8394358

M3 - Conference contribution

AN - SCOPUS:85050259875

T3 - Proceedings of 4th IEEE International Conference on Applied System Innovation 2018, ICASI 2018

SP - 716

EP - 719

BT - Proceedings of 4th IEEE International Conference on Applied System Innovation 2018, ICASI 2018

A2 - Lam, Artde Donald Kin-Tak

A2 - Prior, Stephen D.

A2 - Meen, Teen-Hang

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 4th IEEE International Conference on Applied System Innovation, ICASI 2018

Y2 - 13 April 2018 through 17 April 2018

ER -

Wang YM, Huang LJ. Fourier series neural networks for regression. In Lam ADKT, Prior SD, Meen TH, editors, Proceedings of 4th IEEE International Conference on Applied System Innovation 2018, ICASI 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 716-719. (Proceedings of 4th IEEE International Conference on Applied System Innovation 2018, ICASI 2018). doi: 10.1109/ICASI.2018.8394358

Fourier series neural networks for regression

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this