A New SVM Algorithm and AMR Sensor Based Vehicle Classification

Author

Feng, Zhou ; Mingzhe, Wang

Author_Institution

Dept. of Control Sci. & Eng., Huazhong Univ. of Sci. & Technol., Wuhan, China

Volume

2

fYear

2009

fDate

10-11 Oct. 2009

Firstpage

421

Lastpage

425

Abstract

This paper proposes a new and efficient vehicle classification system base on support vector machine (SVM) algorithm and anisotropic magnetoresistive (AMR) sensor. The main point is that the AMR sensors detect the change of earth magnetic field which will be disturbed differently by different types of passing traffic vehicle. The characteristics of AMR sensor output model of the sample data, SVM learning classification algorithm, kernel function and model parameters are analyzed in detail. The results of our experiments show that this vehicle classification system base on AMR sensor and SVM algorithm is effective and efficient.

Keywords

learning (artificial intelligence); magnetoresistive devices; pattern classification; support vector machines; traffic engineering computing; AMR sensor output model; Earth magnetic field; SVM algorithm; SVM learning classification; anisotropic magnetoresistive sensor; kernel function; model parameters; support vector machine; traffic vehicle; vehicle classification system; Anisotropic magnetoresistance; Change detection algorithms; Earth; Magnetic sensors; Sensor phenomena and characterization; Sensor systems; Support vector machine classification; Support vector machines; Traffic control; Vehicle detection; AMR Sensor; SVM; Vehicle Classification;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Computation Technology and Automation, 2009. ICICTA '09. Second International Conference on

Conference_Location

Changsha, Hunan

Print_ISBN

978-0-7695-3804-4

Type

conf

DOI

10.1109/ICICTA.2009.337

Filename

5287833