Effect of Dimensionality Reduction on Performance in Artificial Neural Network for User Authentication

被引：0

作者：

Chauhan, Sucheta ^{[1
]}

Prema, K. V. ^{[1
]}

机构：

[1] MITS, Fac Engn & Technol, Lakshmangarh, Rajasthan, India

来源：

PROCEEDINGS OF THE 2013 3RD IEEE INTERNATIONAL ADVANCE COMPUTING CONFERENCE (IACC) | 2013年

关键词：

Keystroke-scan; Back Propagation (BP); Multilayer Perceptron (MLP); Principal Component Analysis (PCA); Multidimensional scaling (MDS); Probabilistic PCA;

D O I：

暂无

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

Security is an important concern for today's generation, where keystroke-scan had come out as a milestone. In this paper, a comparison approach is presented for user authentication using keystroke dynamics. Here we have shown the effect of Dimensionality Reduction techniques on the performance and the misclassification rate is between 9.17% and 9.53%. It helps in improving the performance of the system after reducing the dimensions of input data. We have used three dimensional reduction techniques like: Principal Component Analysis (PCA), Multidimensional scaling (MDS), and probabilistic PCA. Here, PCA provide 9.17% misclassification rate with better performance for keystroke samples of 10 users and each user is having 400 samples for the same password.

引用

页码：788 / 793

页数：6

共 50 条

[1] User authentication via neural network
Ahmad, AM
Abdullah, NN
ARTIFICIAL INTELLIGENCE: METHODOLOGY, SYSTEMS, APPLICATIONS, PROCEEDINGS, 2000, 1904 : 310 - 320
[2] Dimensionality reduction for evolving neural network
College of Computer Science and Technology, Jilin University, Changchun 130012, China
不详
不详
J. Comput. Inf. Syst., 2006, 3 (1079-1084):
[3] Artificial Neural Network for Dimensionality Reduction and Its Application to Microwave Filters Inverse Modeling
Wu, Yang
Pan, Guangyuan
Lu, Di
Yu, Ming
IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES, 2022, 70 (11) : 4683 - 4693
[4] A Folded Neural Network Autoencoder for Dimensionality Reduction
Wang, Jing
He, Haibo
Prokhorov, Danil V.
PROCEEDINGS OF THE INTERNATIONAL NEURAL NETWORK SOCIETY WINTER CONFERENCE (INNS-WC2012), 2012, 13 : 120 - 127
[5] Effect of the neural network size on performance of authentication systems for fingerprints
Tanaka, Akihiro
Kinoshita, Kentaro
Kishida, Satoru
IEEE INTERNATIONAL SYMPOSIUM ON INTELLIGENT SIGNAL PROCESSING AND COMMUNICATIONS SYSTEMS (ISPACS 2012), 2012,
[6] Model Reduction of Neural Network Trees Based on Dimensionality Reduction
Hayashi, Hirotomo
Zhao, Qiangfu
IJCNN: 2009 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1- 6, 2009, : 1119 - 1124
[7] Artificial Neural Network and Data Dimensionality Reduction Based on Machine Learning Methods for PMSM Model Order Reduction
Raia, Maria Raluca
Ruba, Mircea
Nemes, Raul Octavian
Martis, Claudia
IEEE ACCESS, 2021, 9 : 102345 - 102354
[8] Artificial Neural Network and Data Dimensionality Reduction Based on Machine Learning Methods for PMSM Model Order Reduction
Raia, Maria Raluca
Ruba, Mircea
Nemes, Raul Octavian
Martis, Claudia
IEEE Access, 2021, 9 : 102345 - 102354
[9] Effect of artificial neural network on performance of electronic nose
Qin, Shu-Ji
Xu, Chun-Hua
Wang, Zhan-Shan
Tongji Daxue Xuebao/Journal of Tongji University, 2005, 33 (06): : 804 - 808
[10] Dimensionality reduction in conic section function neural network
Tulay Yildirim
Lale Ozyilmaz
Sadhana, 2002, 27 : 675 - 683

← 1 2 3 4 5 →