Volume 12 Number 4 (Apr. 2017)
Home > Archive > 2017 > Volume 12 Number 4 (Apr. 2017) >
JSW 2017 Vol.12(4): 292-302 ISSN: 1796-217X
doi: 10.17706/jsw.12.4.292-302

Comparative Analysis of Gaussian Process Regression Based Extreme Learning Machine

Jing Zhou1*, Rui Ying Liu1, Xu Zhou2, Rana Aamir Raza Ashfaq3*
1College of Science, Agricultural University of Hebei, Baoding 071001, China.
2Department of Basic Courses, Agricultural University of Hebei, Huanghua 061100, China
3Department of Computer Science, Bahauddin Zakariya University, Multan, Pakistan.

Abstract—It is an effective way to overcome the randomization sensibility of extreme learning machine (ELM) by using Gaussian process regression (GPR) to optimize the output-layer weights. The key of GPR based ELM (GPRELM) is the selection of kernel function which is used to measure the similarity between different hidden-layer output vectors. In this paper, we conduct an experimental analysis to compare the classification performances of radial basis function (RBF) kernel and polynomial (Poly) kernel based GPRELMs. The comparative results on 24 UCI data sets reveal that: (1) GPRELMs have the serious over-fitting; (2) GPRELMs can get the better classification accuracies with less hidden-layer nodes in comparison with the original ELM; and (3) the smaller regularization factors usually bring about the higher training accuracies for GPRELMs, while the larger regularization factors usually result in the higher testing accuracies. All these conclusions provide the useful enlightenments and instructions for the theoretical studies and practical applications of GPRELMs.

Index Terms—Extreme learning machine, gaussian process regression; radial basis function kernel; polynomial Kernel.


Cite: Jing Zhou, Rui Ying Liu, Xu Zhou, Rana Aamir Raza Ashfaq, "Comparative Analysis of Gaussian Process Regression Based Extreme Learning Machine," Journal of Software vol. 12, no. 4, pp. 292-302, 2017.

General Information

ISSN: 1796-217X
Frequency: Monthly
Editor-in-Chief: Prof. Antanas Verikas
Executive Editor: Ms. Yoyo Y. Zhou
Abstracting/ Indexing: DBLP, EBSCO, ProQuest, INSPEC, ULRICH's Periodicals Directory, WorldCat, CNKI,etc
E-mail: jsw@iap.org
  • May 11, 2018 News!

    Papers published in JSW Vol. 13, No. 1- Vol. 13 No. 4 have been indexed by DBLP.    [Click]

  • Dec 22, 2017 News!

    [CFP] 2018 the annual meeting of JSW Editorial Board, ICCSM 2018, will be held in Nice, France, July 17-19.   [Click]

  • Jun 25, 2018 News!

    Vol 13, No. 6 has been published with online version 4 original aritcles from 3 countries are published in this issue.     [Click]

  • Jun 25, 2018 News!

    The papers published in Vol.13, No. 6 have all received dois from Crossref.

  • Jun 12, 2018 News!

    The papers published in Vol.13, No. 5 have all received dois from Crossref.