Publication:
Less-is-Better Protection (LBP) for memory errors in kNNs classifiers

Simple item page
dc.affiliation.dptoUC3M. Departamento de Ingeniería Telemáticaes
dc.affiliation.grupoinvUC3M. Grupo de Investigación: Network Technologieses
dc.contributor.authorLiu, Shanshan
dc.contributor.authorReviriego Vasallo, Pedro
dc.contributor.authorMontuschi, Paolo
dc.contributor.authorLombardi, Fabrizio
dc.contributor.funderMinisterio de Economía y Competitividad (España)es
dc.contributor.funderComunidad de Madrides
dc.date.accessioned2021-05-19T11:52:24Z
dc.date.available2023-04-01T23:00:05Z
dc.date.issued2021-04
dc.description.abstractClassification is used in a wide range of applications to determine the class of a new element; for example, it can be used to determine whether an object is a pedestrian based on images captured by the safety sensors of a vehicle. Classifiers are commonly implemented using electronic components and thus, they are subject to errors in memories and combinational logic. In some cases, classifiers are used in safety critical applications and thus, they must operate reliably. Therefore, there is a need to protect classifiers against errors. The k Nearest Neighbors (kNNs) classifier is a simple, yet powerful algorithm that is widely used; its protection against errors in the neighbor computations has been recently studied. This paper considers the protection of kNNs classifiers against errors in the memory that stores the dataset used to select the neighbors. Initially, the effects of errors in the most common memory configurations (unprotected, Parity-Check protected and Single Error Correction-Double Error Detection (SEC-DED) protected) are assessed. The results show that surprisingly, for most datasets, it is better to leave the memory unprotected than to use error detection codes to discard the element affected by an error in terms of tolerance. This observation is then leveraged to develop Less-is-Better Protection (LBP), a technique that does not require any additional parity bits and achieves better error tolerance than Parity-Check for single bit errors (reducing the classification errors by 59% for the Iris dataset) and SEC-DED codes for double bit errors (reducing the classification errors by 42% for the Iris dataset).en
dc.description.sponsorshipS. Liu and F. Lombardi would like to acknowledge the support of National Science Foundation, USA grants CCF-1953961 and 1812467, and P. Reviriego would like to acknowledge the support of the ACHILLES project PID2019-104207RB-I00 and the Go2Edge network RED2018-102585-T funded by the Spanish Ministry of Science and Innovation and by the Madrid Community research project TAPIR-CM P2018/TCS-4496.en
dc.format.extent11
dc.identifier.bibliographicCitationLiu, S., Reviriego, P., Montuschi, P. & Lombardi, F. (2021). Less-is-Better Protection (LBP) for memory errors in kNNs classifiers. Future Generation Computer Systems, vol. 117, pp. 401–411.en
dc.identifier.doihttps://doi.org/10.1016/j.future.2020.12.015
dc.identifier.issn0167-739X
dc.identifier.publicationfirstpage401
dc.identifier.publicationlastpage411
dc.identifier.publicationtitleFuture Generation Computer Systemsen
dc.identifier.publicationvolume117
dc.identifier.urihttps://hdl.handle.net/10016/32685
dc.identifier.uxxiAR/0000027531
dc.language.isoeng
dc.publisherElsevier
dc.relation.projectIDGobierno de España. PID2019-104207RB-I00es
dc.relation.projectIDGobierno de España. RED2018-102585-Tes
dc.relation.projectIDComunidad de Madrid. P2018/TCS-4496es
dc.rights© 2020 Elsevier B.V.
dc.rightsAtribución-NoComercial-SinDerivadas 3.0 España*
dc.rights.accessRightsopen access
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/*
dc.subject.ecienciaInformáticaes
dc.subject.otherClassificationen
dc.subject.otherMemoriesen
dc.subject.otherError toleranceen
dc.subject.otherK nearest neighborsen
dc.subject.otherError control codesen
dc.titleLess-is-Better Protection (LBP) for memory errors in kNNs classifiersen
dc.typeresearch article*
dc.type.hasVersionAM*
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
LBP_FGCS_2021_ps.pdf
Size:
1.27 MB
Format:
Adobe Portable Document Format
Download
Collections
DIT - RYSC - Artículos en Revistas Internacionales / International Journals