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

Handle URI:
http://hdl.handle.net/10754/564657
Title:
Poster abstract: A machine learning approach for vehicle classification using passive infrared and ultrasonic sensors
Authors:
Warriach, Ehsan Ullah; Claudel, Christian G. ( 0000-0003-0702-6548 )
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. Copyright © 2013 ACM.
KAUST Department:
Electrical Engineering Program; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Distributed Sensing Systems Laboratory (DSS)
Publisher:
Association for Computing Machinery (ACM)
Journal:
Proceedings of the 12th international conference on Information processing in sensor networks - IPSN '13
Conference/Event name:
12th International Conference on Information Processing in Sensor Networks, IPSN 2013 - Part of CPSWeek 2013
Issue Date:
2013
DOI:
10.1145/2461381.2461434
Type:
Conference Paper
ISBN:
9781450319591
Appears in Collections:
Conference Papers; Electrical Engineering Program; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorWarriach, Ehsan Ullahen
dc.contributor.authorClaudel, Christian G.en
dc.date.accessioned2015-08-04T07:11:11Zen
dc.date.available2015-08-04T07:11:11Zen
dc.date.issued2013en
dc.identifier.isbn9781450319591en
dc.identifier.doi10.1145/2461381.2461434en
dc.identifier.urihttp://hdl.handle.net/10754/564657en
dc.description.abstractThis 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. Copyright © 2013 ACM.en
dc.publisherAssociation for Computing Machinery (ACM)en
dc.subjectClusteringen
dc.subjectK-NNen
dc.subjectNaive bayesen
dc.subjectSVMen
dc.subjectVehicle classificationen
dc.titlePoster abstract: A machine learning approach for vehicle classification using passive infrared and ultrasonic sensorsen
dc.typeConference Paperen
dc.contributor.departmentElectrical Engineering Programen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentDistributed Sensing Systems Laboratory (DSS)en
dc.identifier.journalProceedings of the 12th international conference on Information processing in sensor networks - IPSN '13en
dc.conference.date8 April 2013 through 11 April 2013en
dc.conference.name12th International Conference on Information Processing in Sensor Networks, IPSN 2013 - Part of CPSWeek 2013en
dc.conference.locationPhiladelphia, PAen
dc.contributor.institutionDepartment of Mathematics and Computer Science, University of Groningen, Groningen, Netherlandsen
kaust.authorClaudel, Christian G.en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.