Introduction
Bimonthly, started in 1957
Administrator
Shanxi Provincial Education Department
Sponsor
Taiyuan University of Technology
Publisher
Ed. Office of Journal of TYUT
Editor-in-Chief
SUN Hongbin
ISSN: 1007-9432
CN: 14-1220/N
Administrator
Shanxi Provincial Education Department
Sponsor
Taiyuan University of Technology
Publisher
Ed. Office of Journal of TYUT
Editor-in-Chief
SUN Hongbin
ISSN: 1007-9432
CN: 14-1220/N
location: home > paper >
PDFdownloadsize：2.96MBviewed：download：
An Improved ELM-LRF Image Classification Method
DOI:
10.16355/j.cnki.issn1007-9432tyut.2018.06.010
Received:
Accepted:
| Corresponding author | Institute | |
| XU Xinying | College of Electrical and Power Engineering, Taiyuan University of Technology |
abstract:
The input weight of each feature graph in convolution process of ELM-LRF is stochastic, the stability is poor.In this paper, particle swarm optimization (PSO) is used to optimize the ELM-LRF, to get an image classification algorithm with optimal parameters IPSO-ELMLRF.The experimental results show that, compared with traditional ELM-LRF algorithm, IPSO-ELM-LRF not only improves the stability of the algorithm, but also gives full play to the global optimization ability of particle swarm optimization and greatly improves classification accuracy.
Keywords:
particle swarm optimization (PSO) ; local receptive field; extreme learning machine (ELM) ; local receptive fields based extreme learning machine (ELM-LRF) ; image classification;