Recognizing daily and sports activities in two open source machine learning environments using body-worn sensor units

Simple item page
dc.citation.epage1667en_US
dc.citation.issueNumber11en_US
dc.citation.spage1649en_US
dc.citation.volumeNumber57en_US
dc.contributor.authorBarshan, B.en_US
dc.contributor.authorYüksek, M. C.en_US
dc.date.accessioned2016-02-08T09:42:25Z
dc.date.available2016-02-08T09:42:25Z
dc.date.issued2014-11en_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.description.abstractThis study provides a comparative assessment on the different techniques of classifying human activities performed while wearing inertial and magnetic sensor units on the chest, arms and legs. The gyroscope, accelerometer and the magnetometer in each unit are tri-axial. Naive Bayesian classifier, artificial neural networks (ANNs), dissimilarity-based classifier, three types of decision trees, Gaussian mixture models (GMMs) and support vector machines (SVMs) are considered. A feature set extracted from the raw sensor data using principal component analysis is used for classification. Three different cross-validation techniques are employed to validate the classifiers. A performance comparison of the classifiers is provided in terms of their correct differentiation rates, confusion matrices and computational cost. The highest correct differentiation rates are achieved with ANNs (99.2%), SVMs (99.2%) and a GMM (99.1%). GMMs may be preferable because of their lower computational requirements. Regarding the position of sensor units on the body, those worn on the legs are the most informative. Comparing the different sensor modalities indicates that if only a single sensor type is used, the highest classification rates are achieved with magnetometers, followed by accelerometers and gyroscopes. The study also provides a comparison between two commonly used open source machine learning environments (WEKA and PRTools) in terms of their functionality, manageability, classifier performance and execution times. © 2013 © The British Computer Society 2013. All rights reserved.en_US
dc.description.provenanceMade available in DSpace on 2016-02-08T09:42:25Z (GMT). No. of bitstreams: 1 bilkent-research-paper.pdf: 70227 bytes, checksum: 26e812c6f5156f83f0e77b261a471b5a (MD5) Previous issue date: 2013en
dc.identifier.doi10.1093/comjnl/bxt075en_US
dc.identifier.issn0010-4620
dc.identifier.urihttp://hdl.handle.net/11693/21172
dc.language.isoEnglishen_US
dc.publisherOxford University Pressen_US
dc.relation.isversionofhttp://dx.doi.org/10.1093/comjnl/bxt075en_US
dc.source.titleThe Computer Journalen_US
dc.subjectAccelerometeren_US
dc.subjectBody sensor networksen_US
dc.subjectClassifiersen_US
dc.subjectCross validationen_US
dc.subjectGyroscopeen_US
dc.subjectHuman activity classificationen_US
dc.subjectMachine learning environmentsen_US
dc.subjectMagnetometeren_US
dc.subjectPRToolsen_US
dc.subjectWearable sensorsen_US
dc.subjectWEKAen_US
dc.subjectAccelerometersen_US
dc.subjectBayesian networksen_US
dc.subjectDecision treesen_US
dc.subjectNeural networksen_US
dc.subjectPrincipal component analysisen_US
dc.subjectSupport vector machinesen_US
dc.subjectHuman activitiesen_US
dc.subjectInertial sensoren_US
dc.subjectLearning environmentsen_US
dc.subjectComputer aided instructionen_US
dc.titleRecognizing daily and sports activities in two open source machine learning environments using body-worn sensor unitsen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Recognizing daily and sports activities in two open source machine learning environments using body-worn sensor units.pdf
Size:
1.02 MB
Format:
Adobe Portable Document Format
Description:
Full Printable Version
Download

Collections

Scholarly Publications - Electrical and Electronics Engineering