A Novel Approach for Activity Recognition with Down-Sampling 1D Local Binary Pattern Features

Basit Öğe Kaydı
dc.authoridKUNCAN, Melih/0000-0002-9749-0418
dc.authoridKUNCAN, Fatma/0000-0003-0712-6426
dc.contributor.authorKuncan, Fatma
dc.contributor.authorKaya, Yilmaz
dc.contributor.authorKuncan, Melih
dc.date.accessioned2024-12-24T19:32:52Z
dc.date.available2024-12-24T19:32:52Z
dc.date.issued2019
dc.departmentSiirt Üniversitesi
dc.description.abstractThe sensors on the mobile devices directly reflect the physical and demographic characteristics of the user. Sensor signals may contain information about the gender and movement of the person. Automatic recognition of physical activities often referred to as human activity recognition (HAR). In this study, a novel feature extraction approach for the HAR system using the mobile sensor signals, the Down Sampling One Dimensional Local Binary Pattern (DS-1D-LBP) method is proposed. Feature extraction from signals is one of the most critical stages of HAR because the success of the HAR system depends on the features extraction. The proposed HAR system consists of two stages. In the first stage, DS-ID-LBP conversion was applied to the sensor signals in order to extract statistical features from the newly formed signals. In the last stage, classification with Extreme Learning Machine (ELM) was performed using these features. The highest success rate was 96.87 percent in the experimental results according to the different parameters of DS-ID-LBP and ELM. As a result of this study, the novel approach demonstrated that the proposed model performed with a high success rate using mobile sensor signals for the HAR system.
dc.description.sponsorshipScientific Research Projects Coordination Unit of Siirt University [2018-SIUFEB-DR-009]; Siirt University
dc.description.sponsorshipThis work was supported by the Scientific Research Projects Coordination Unit of Siirt University as a project with the number 2018-SIUFEB-DR-009. The authors of this article thank Siirt University for their support.
dc.identifier.doi10.4316/AECE.2019.01005
dc.identifier.endpage44
dc.identifier.issn1582-7445
dc.identifier.issn1844-7600
dc.identifier.issue1
dc.identifier.scopus2-s2.0-85064195416
dc.identifier.scopusqualityQ3
dc.identifier.startpage35
dc.identifier.urihttps://doi.org/10.4316/AECE.2019.01005
dc.identifier.urihttps://hdl.handle.net/20.500.12604/7848
dc.identifier.volume19
dc.identifier.wosWOS:000459986900005
dc.identifier.wosqualityQ4
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherUniv Suceava, Fac Electrical Eng
dc.relation.ispartofAdvances in Electrical and Computer Engineering
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_20241222
dc.subjectdigital signal processing
dc.subjectfeature extraction
dc.subjectmachine learning
dc.subjectpattern recognition
dc.subjectwearable sensors
dc.titleA Novel Approach for Activity Recognition with Down-Sampling 1D Local Binary Pattern Features
dc.typeArticle

Dosyalar

Koleksiyon

WOS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu