Comparison of Autoencoder and Principal Component Analysis Followed by Neural Network for E-Learning Using Handwritten Recognition

被引：0

作者：

Almotiri, Jasem ^{[1
]}

Elleithy, Khaled ^{[1
]}

Elleithy, Abdelrahman ^{[2
]}

机构：

[1] Univ Bridgeport, Dept Comp Sci & Engn, Bridgeport, CT 06604 USA

[2] Texas A&M Univ Kingsville, Dept Elect Engn & Comp Sci, Kingsville, TX USA

来源：

2017 IEEE LONG ISLAND SYSTEMS, APPLICATIONS AND TECHNOLOGY CONFERENCE (LISAT) | 2017年

关键词：

autoencoder; PCA; neural networks; image processing; machine learning; data MNIST;

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

This paper presents two different implementations for recognition of handwritten numerals using a high performance autoencoder and Principal Component Analysis (PCA) by making use of neural networks. Different from other approaches, the non-linear mapping capability of neural networks is used extensively here. The implementation involves the deployment of a neural network, and the use of an auto encoder and PCA while carrying out the compression and classification of data. The performance of the system was analyzed, and an accuracy of 97.2% for Principal Component Analysis, and 98.1% accuracy for the autoencoder, was recorded in detection of numerals written by school children.

引用

页数：5

共 15 条

[1] Chen G, 2016, IEEE IMAGE PROC, P3673
[2] de Chazal P, 2015, INT CONF ACOUST SPEE, P2165, DOI 10.1109/ICASSP.2015.7178354
[3] Deep Neural Networks with Parallel Autoencoders for Learning Pairwise Relations: Handwritten Digits Subtraction
Du, Tianchuan
Liao, Li
[J]. 2015 IEEE 14TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA), 2015, : 582 - 587
[4] Ebrahimzadeh R., 2014, INT J COMPUT APPL, V104, P10, DOI DOI 10.5120/18229-9167
[5] Fundamental Technologies in Modern Speech Recognition
Furui, Sadaoki
Deng, Li
Gales, Mark
Ney, Hermann
Tokuda, Keiichi
[J]. IEEE SIGNAL PROCESSING MAGAZINE, 2012, 29 (06) : 16 - 17
[6] Gu R, 2013, IEEE INT CONF BIG DA
[7] Improving the Architecture of an Autoencoder for Dimension Reduction
Hu, Changjie
Hou, Xiaoli
Lu, Yonggang
[J]. 2014 IEEE 11TH INTL CONF ON UBIQUITOUS INTELLIGENCE AND COMPUTING AND 2014 IEEE 11TH INTL CONF ON AUTONOMIC AND TRUSTED COMPUTING AND 2014 IEEE 14TH INTL CONF ON SCALABLE COMPUTING AND COMMUNICATIONS AND ITS ASSOCIATED WORKSHOPS, 2014, : 855 - 858
[8] Kane A, 2016, INT CONF DAT MIN WOR, P639, DOI [10.1109/ICDMW.2016.95, 10.1109/ICDMW.2016.0096]
[9] Lin YQ, 2011, PROC CVPR IEEE, P1689, DOI 10.1109/CVPR.2011.5995477
[10] Handwritten digit recognition: benchmarking of state-of-the-art techniques
Liu, CL
Nakashima, K
Sako, H
Fujisawa, H
[J]. PATTERN RECOGNITION, 2003, 36 (10) : 2271 - 2285

← 1 2 →