Poster abstract: A machine learning approach for vehicle classification using passive infrared and ultrasonic sensors

Author

Warriach, Ehsan Ullah ; Claudel, Christian

Author_Institution

Dept. of Math. & Comput. Sci., Univ. of Groningen, Groningen, Netherlands

fYear

2013

fDate

8-11 April 2013

Firstpage

333

Lastpage

334

Abstract

This article describes the implementation of four different machine learning techniques for vehicle classification in a dual ultrasonic/passive infrared traffic flow sensors. Using k-NN, Naive Bayes, SVM and KNN-SVM algorithms, we show that KNN-SVM significantly outperforms other algorithms in terms of classification accuracy. We also show that some of these algorithms could run in real time on the prototype system.

Keywords

infrared detectors; learning (artificial intelligence); pattern classification; support vector machines; ultrasonic devices; wireless sensor networks; KNN-SVM algorithm; k-NN algorithm; k-nearest neighbor; machine learning techniques; naive Bayes algorithm; passive infrared traffic flow sensors; support vector machine; ultrasonic traffic flow sensors; vehicle classification; Acoustics; Clustering algorithms; Machine learning algorithms; Support vector machines; Temperature sensors; Vehicles; Clustering; K-NN; Naive Bayes; SVM; Vehicle Classification;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Processing in Sensor Networks (IPSN), 2013 ACM/IEEE International Conference on

Conference_Location

Philadelphia, PA

Type

conf

DOI

10.1109/IPSN.2013.6917602

Filename

6917602