Support Vector Machine for Behavior-Based Driver Identification SystemReportar como inadecuado




Support Vector Machine for Behavior-Based Driver Identification System - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

Journal of RoboticsVolume 2010 2010, Article ID 397865, 11 pages

Research Article

Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China

Department of Mechanical and Automation Engineering, Chinese University of Hong Kong, Hong Kong

Received 1 November 2009; Accepted 5 March 2010

Academic Editor: Zeng-Guang  Hou

Copyright © 2010 Huihuan Qian et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

We present an intelligent driveridentification system to handle vehicle theft based on modelingdynamic human behaviors. We propose to recognize illegitimatedrivers through their driving behaviors. Since human drivingbehaviors belong to a dynamic biometrical feature which iscomplex and difficult to imitate compared with static featuressuch as passwords and fingerprints, we find that this novelidea of utilizing human dynamic features for enhanced securityapplication is more effective. In this paper, we first describeour experimental platform for collecting and modeling humandriving behaviors. Then we compare fast Fourier transformFFT, principal component analysis PCA, and independentcomponent analysis ICA for data preprocessing. Using machinelearning method of support vector machine SVM, we derive the individualdriving behavior model and we then demonstratethe procedure for recognizing different drivers by analyzingthe corresponding models. The experimental results of learningalgorithms and evaluation are described.





Autor: Huihuan Qian, Yongsheng Ou, Xinyu Wu, Xiaoning Meng, and Yangsheng Xu

Fuente: https://www.hindawi.com/



DESCARGAR PDF




Documentos relacionados