Detecting Outliers Using Modified Recursive PCA Algorithm For Dynamic Streaming Data

Simple item page
dc.contributor.authorDani, Yasi
dc.contributor.authorGunawan, Agus Yodi
dc.contributor.authorKhodra, Masayu Leylia
dc.contributor.authorIndratno, Sapto Wahyu
dc.coverage.issue2cs
dc.coverage.volume29cs
dc.date.accessioned2024-01-11T09:48:06Z
dc.date.available2024-01-11T09:48:06Z
dc.date.issued2023-12-31cs
dc.description.abstractOutlier analysis has been widely studied and has produced many methods. However, there is still rare a method to detect outliers for dynamically streaming batch data (online learning). In the present research, a novel online algorithm to detect outliers in such dataset is proposed. Data points are proceeded by applying a modified recursive PCA to predict sequentially parameters of the model; eigenvalues and eigenvectors of the statistical detection model are recursively updated using approximate values by perturbation methods. More specifically, the recursive eigenstructure is obtained from the derivation of the covariance matrix using the first-order perturbation technique. The Mahalanobis distance is then used as an outlier score. Our algorithm performances are evaluated using some metrics, namely accuration, precision, recall, F1-score, AUC-PR, and the execution time. Results show that the proposed online outlier detection is computationally efficient in time and the algorithm's performance effectiveness is comparable to that of the offline outlier detection algorithm via classical PCA.en
dc.formattextcs
dc.format.extent237-244cs
dc.format.mimetypeapplication/pdfen
dc.identifier.citationMendel. 2023 vol. 29, č. 2, s. 237-244. ISSN 1803-3814cs
dc.identifier.doi10.13164/mendel.2023.2.237en
dc.identifier.issn2571-3701
dc.identifier.issn1803-3814
dc.identifier.urihttps://hdl.handle.net/11012/244251
dc.language.isoencs
dc.publisherInstitute of Automation and Computer Science, Brno University of Technologycs
dc.relation.ispartofMendelcs
dc.relation.urihttps://mendel-journal.org/index.php/mendel/article/view/276cs
dc.rightsCreative Commons Attribution-NonCommercial-ShareAlike 4.0 International licenseen
dc.rights.accessopenAccessen
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0en
dc.subjectOutlieren
dc.subjectOnline learningen
dc.subjectRecursive PCAen
dc.subjectEigendecompositionen
dc.subjectPerturbation methoden
dc.titleDetecting Outliers Using Modified Recursive PCA Algorithm For Dynamic Streaming Dataen
dc.type.driverarticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
eprints.affiliatedInstitution.facultyFakulta strojního inženýrstvícs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
261-Article Text-850-2-10-20231219.pdf
Size:
5.39 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Vol. 29, No. 2