Improved pig behavior analysis by optimizing window sizes for individual behaviors on acceleration and angular velocity data

Simple item page
dc.contributor.authorAlghamdi, Salehen
dc.contributor.authorZhao, Zhuqingen
dc.contributor.authorHa, Dong S.en
dc.contributor.authorMorota, Gotaen
dc.contributor.authorHa, Sook S.en
dc.date.accessioned2023-02-20T16:15:10Zen
dc.date.available2023-02-20T16:15:10Zen
dc.date.issued2022-11-01en
dc.date.updated2023-02-19T15:52:12Zen
dc.description.abstractThis paper presents the application of machine learning algorithms to identify pigs' behaviors from data collected using the wireless sensor nodes mounted on pigs. The sensor node attached to a pig's back senses the acceleration and angular velocity in three axes, and the sensed data are transmitted to a host computer wirelessly. Two video cameras, one attached to the ceiling of the pigpen and the other one to a fence, provided ground truth for data annotations. The data were collected from pigs for 131 h over 2 mo. As the typical behavior period depends on the behavior type, we segmented the acceleration data with different window sizes (WS) and step sizes (SS), and tested how the classification performance of different activities varied with different WS and SS. After exploring the possible combinations, we selected the optimum WS and SS. To compare performance, we used five machine learning algorithms, specifically support vector machine, k-nearest neighbors, decision trees, naive Bayes, and random forest (RF). Among the five algorithms, RF achieved the highest F1 score for four major behaviors consisting of 92.36% in total. The F1 scores of the algorithm were 0.98 for "eating,"0.99 for "lying,"0.93 for "walking,"and 0.91 for "standing"behaviors. The optimal WS was 7 s for "eating"and "lying,"and 3 s for "walking"and "standing."The proposed work demonstrates that, based on the length of behavior, the adaptive window and step sizes increase the classification performance.en
dc.description.versionPublished versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.doihttps://doi.org/10.1093/jas/skac293en
dc.identifier.eissn1525-3163en
dc.identifier.issn0021-8812en
dc.identifier.issue11en
dc.identifier.orcidMorota, Gota [0000-0002-3567-6911]en
dc.identifier.other6691203 (PII)en
dc.identifier.pmid36056754en
dc.identifier.urihttp://hdl.handle.net/10919/113874en
dc.identifier.volume100en
dc.language.isoenen
dc.publisherOxford University Pressen
dc.relation.urihttps://www.ncbi.nlm.nih.gov/pubmed/36056754en
dc.rightsCreative Commons Attribution 4.0 Internationalen
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en
dc.subjectdata segmentationen
dc.subjectlabelingen
dc.subjectpig behavior classificationen
dc.subjectpig behavior monitoringen
dc.subjectwindow sizeen
dc.subjectwireless sensor nodeen
dc.subjectBehavioral and Social Scienceen
dc.subject.meshAnimalsen
dc.subject.meshSwineen
dc.subject.meshBayes Theoremen
dc.subject.meshAlgorithmsen
dc.subject.meshAccelerationen
dc.subject.meshMachine Learningen
dc.subject.meshSupport Vector Machineen
dc.titleImproved pig behavior analysis by optimizing window sizes for individual behaviors on acceleration and angular velocity dataen
dc.title.serialJournal of Animal Scienceen
dc.typeArticle - Refereeden
dc.type.dcmitypeTexten
dc.type.otherJournal Articleen
dcterms.dateAccepted2022-09-02en
pubs.organisational-group/Virginia Techen
pubs.organisational-group/Virginia Tech/Agriculture & Life Sciencesen
pubs.organisational-group/Virginia Tech/Engineeringen
pubs.organisational-group/Virginia Tech/Engineering/Electrical and Computer Engineeringen
pubs.organisational-group/Virginia Tech/All T&R Facultyen
pubs.organisational-group/Virginia Tech/Agriculture & Life Sciences/CALS T&R Facultyen

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Improved pig behavior analysis by optimizing window sizes for individual behaviors on acceleration and angular velocity data.pdf
Size:
1.25 MB
Format:
Adobe Portable Document Format
Description:
Published version
Download

Collections

All Faculty Deposits
Scholarly Works, Electrical and Computer Engineering
Scholarly Works, School of Animal Sciences