Research on Classification Based on Autoencoder Combination Features Extraction Method

Authors

Congcong Gu, Engineering Research Center of Internet of Things Technology Applications Ministry of Education, Wuxi 214122, China;
Wang Yan, Engineering Research Center of Internet of Things Technology Applications Ministry of Education, Wuxi 214122, China;
Dahu Yan, Engineering Research Center of Internet of Things Technology Applications Ministry of Education, Wuxi 214122, China;
Zhicheng Ji, Engineering Research Center of Internet of Things Technology Applications Ministry of Education, Wuxi 214122, China;

Abstract

Abstract: For the problem that autoencoder can not obtain class information according to labels during the unsupervised training process, to improve the recognition accuracy, stacked class denoising autoencoder(SCDAE) is proposed to extract class information, and autoencoder combination features extraction method is adapted to extract combination features for classification. The method builds a stacked denoising autoencoder(SDAE) and a SCDAE. The method fine-tunes SDAE and SCDAE to form a combined model (CM). The combination features containing main information of the input data and class information are acquired through CM, and they are further used for classification. MNIST and USPS handwritten database are selected for testing the proposed method, and the results show its superiority on extracting features and improving recognition accuracy.

Recommended Citation

Gu, Congcong; Yan, Wang; Yan, Dahu; and Ji, Zhicheng (2019) "Research on Classification Based on Autoencoder Combination Features Extraction Method," Journal of System Simulation: Vol. 30: Iss. 11, Article 11.
DOI: 10.16182/j.issn1004731x.joss.201811011
Available at: https://dc-china-simulation.researchcommons.org/journal/vol30/iss11/11

First Page

4132

Revised Date

2018-06-30

DOI Link

https://doi.org/10.16182/j.issn1004731x.joss.201811011

Last Page

4140

CLC

TP391.9

Recommended Citation

Gu Congcong, Wang Yan, Yan Dahu, Ji Zhicheng. Research on Classification Based on Autoencoder Combination Features Extraction Method[J]. Journal of System Simulation, 2018, 30(11): 4132-4140.

DOI

10.16182/j.issn1004731x.joss.201811011