Hybrid Solution for the Feature Selection in Personal Identification Problems through Keystroke Dynamics

Author

Azevedo, Gabriel L F B G ; Cavalcanti, George D C ; Filho, E. C B Carvalho

Author_Institution

Center of Inf., Fed. Univ. of Pernambuco, Recife

fYear

2007

fDate

12-17 Aug. 2007

Firstpage

1947

Lastpage

1952

Abstract

Techniques based on biometrics have been successfully applied to personal identification systems. One rather promising technique uses the keystroke dynamics of each user in order to recognize him/her. In this work, we present the development of a hybrid system based on support vector machines and stochastic optimization techniques. The main objective is the analysis of these optimization algorithms for feature selection. We evaluate two optimization techniques for this task: genetic algorithms (GA) and particle swarm optimization (PSO). In the present study, PSO outperformed GA with regard to classification error and processing time, but was inferior regarding the feature reduction rate.

Keywords

biometrics (access control); genetic algorithms; particle swarm optimisation; pattern classification; stochastic processes; support vector machines; PSO; classification error; feature selection; genetic algorithms; hybrid system; keystroke dynamics; particle swarm optimization; personal identification problems; stochastic optimization techniques; support vector machines; Algorithm design and analysis; Biometrics; Brazil Council; Data mining; Genetic algorithms; Neural networks; Particle swarm optimization; Stochastic systems; Support vector machine classification; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2007. IJCNN 2007. International Joint Conference on

Conference_Location

Orlando, FL

ISSN

1098-7576

Print_ISBN

978-1-4244-1379-9

Electronic_ISBN

1098-7576

Type

conf

DOI

10.1109/IJCNN.2007.4371256

Filename

4371256