• Home
  • Search
  • A new supervised image classification using data set partition
  • https://doi.org/10.1109/fskd.2017.8393002Copy DOI Icon

A new supervised image classification using data set partition

  • Jul 1, 2017
  • Mengmeng Liao +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Random vector functional-link net (RVFL) is a single hidden layer network and extreme learning machine (ELM) is its special case with making weights from the output to the input be zero. RVFL (or ELM) and sparse representation classifier classification approach, called RVFLSRC or ELMSRC one, was an efficient hybrid model to balance between the time and the accuracy of classification. However, the classification time of RVFLSRC is still long. Besides, some images are wrongly classified by sparse representation classifier in RVFLSRC, which degrades the performance of RVFLSRC. In order to improve the recognition rate and reduce the classification time, we propose a new supervised image classification using data set partition (SIC-SP). In SIC-SP, we introduce a formula to estimate the number of images being divided wrongly by RVFLSRC (or ELMSRC), which are used to compute the division threshold. Using that division threshold can reduce the number of images being divided wrongly by RVFLSRC to improve the classification accuracy and reduce the classification time. In addition, we use principal component analysis to reduce the sample dimension, which also shortens the classification time. Experimental results on USPS handwritten digit database and UMIST face one show that the classification time of our SIC-SP is only 1/224 of classification time of SRC, and 1/30 of classification time of ELMSRC (or RVFLSRC). Meanwhile, the classification accuracy of SIC-SP is 97.62% on USPS, and 99.27% on UMIST, higher than those of ELM (or RVFL), SRC, and ELMSRC (or RVFLSRC).

Similar Papers
  • Research Article
  • Citations224

Extreme learning machine and adaptive sparse representation for image classification

  • Jun 23, 2016
  • Neural Networks
  • Jiuwen Cao +4
  • Research Article
  • Citations55

Extreme learning machine model for state-of-charge estimation of lithium-ion battery using salp swarm algorithm

  • Jun 13, 2022
  • Journal of Energy Storage
  • Jiaming Dou +6
  • Research Article
  • Citations4

Hybrid classification approach using extreme learning machine and sparse representation classifier with adaptive threshold

  • Sep 01, 2018
  • IET Signal Processing
  • Mengmeng Liao +1
  • Research Article
  • Citations82

Landmark recognition with sparse representation classification and extreme learning machine

  • Jul 15, 2015
  • Journal of the Franklin Institute
  • Jiuwen Cao +6
  • Research Article
  • Citations65

Ensemble extreme learning machine and sparse representation classification

  • Sep 03, 2016
  • Journal of the Franklin Institute
  • Jiuwen Cao +4
  • Conference Article
  • Citations2

Correlation Based Extreme Learning Machine

  • Aug 01, 2016
  • Sanyam Shukla +2
  • Dissertation
  • Citations3

Extreme learning machine for classification and regression

  • Jan 01, 2014
  • Hongming Zhou
  • Research Article
  • Citations42

Ensemble dropout extreme learning machine via fuzzy integral for data classification

  • Sep 22, 2017
  • Neurocomputing
  • Junhai Zhai +2
  • Research Article
  • Citations1

Method of Metal Button Defect Detection Based on Extreme Learning Machine and Sparse Representation

  • Sep 01, 2021
  • AATCC Journal of Research
  • Xiang Li +3
  • Dissertation
  • Citations1

Representation learning with efficient extreme learning machine auto-encoders

  • Jan 01, 2021
  • Guanghao Zhang
  • Research Article
  • Citations5

Projection vector machine

  • Jun 19, 2013
  • Neurocomputing
  • Wan-Yu Deng +2
  • Research Article
  • Citations8

RFSEN-ELM: SELECTIVE ENSEMBLE OF EXTREME LEARNING MACHINES USING ROTATION FOREST FOR IMAGE CLASSIFICATION

  • Jan 01, 2017
  • Neural Network World
  • Zhiyu Zhou +4
  • Book Chapter

The SVM-ELM Model Based on Particle Swarm Optimization

  • Jan 01, 2016
  • Miao-Miao Wang +1
  • Book Chapter

A Heterogeneous AdaBoost Ensemble Based Extreme Learning Machines for Imbalanced Data

  • May 13, 2022
  • Adnan Omer Abuassba +2
  • Research Article
  • Citations4

A Heterogeneous AdaBoost Ensemble Based Extreme Learning Machines for Imbalanced Data

  • Jul 01, 2019
  • International Journal of Cognitive Informatics and Natural Intelligence
  • Adnan Omer Abuassba +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.