Show simple item record

Bounds on the Number of Measurements for Reliable Compressive Classification

dc.creatorReboredo, H
dc.creatorRenna, Francesco
dc.creatorCalderbank, R
dc.creatorRodrigues, MRD
dc.date.accessioned2016-07-18
dc.date.accessioned2018-11-24T23:20:04Z
dc.date.available2017-05-22T09:06:02Z
dc.date.available2018-11-24T23:20:04Z
dc.date.issued2016-11-15
dc.identifierhttps://www.repository.cam.ac.uk/handle/1810/264328
dc.identifier.urihttp://repository.aust.edu.ng/xmlui/handle/123456789/3538
dc.description.abstractThis paper studies the classification of high-dimensional Gaussian signals from low-dimensional noisy, linear measurements. In particular, it provides upper bounds (sufficient conditions) on the number of measurements required to drive the probability of misclassification to zero in the low-noise regime, both for random measurements and designed ones. Such bounds reveal two important operational regimes that are a function of the characteristics of the source: 1) when the number of classes is less than or equal to the dimension of the space spanned by signals in each class, reliable classification is possible in the low-noise regime by using a one-vs-all measurement design; 2) when the dimension of the spaces spanned by signals in each class is lower than the number of classes, reliable classification is guaranteed in the low-noise regime by using a simple random measurement design. Simulation results both with synthetic and real data show that our analysis is sharp, in the sense that it is able to gauge the number of measurements required to drive the misclassification probability to zero in the low-noise regime.
dc.languageen
dc.publisherIEEE
dc.publisherIEEE Transactions on Signal Processing
dc.rightshttp://creativecommons.org/licenses/by/4.0/
dc.rightshttp://creativecommons.org/licenses/by/4.0/
dc.rightshttp://creativecommons.org/licenses/by/4.0/
dc.rightsAttribution 4.0 International
dc.rightsAttribution 4.0 International
dc.rightsAttribution 4.0 International
dc.subjectcompressed sensing
dc.subjectcompressive classification
dc.subjectclassification
dc.subjectdimensionality reduction
dc.subjectGaussian mixture models
dc.subjectmeasurement design
dc.subjectphase transitions
dc.subjectrandom measurements
dc.titleBounds on the Number of Measurements for Reliable Compressive Classification
dc.typeArticle


Files in this item

FilesSizeFormatView
Reboredo_et_al- ... n_Signal_Processing-AM.pdf414.5Kbapplication/pdfView/Open
Reboredo_et_al- ... _Signal_Processing-VoR.pdf1.052Mbapplication/pdfView/Open

This item appears in the following Collection(s)

Show simple item record